CN111226132B - Target detection method, target detection equipment, millimeter wave radar and movable platform - Google Patents

Abstract

Provided are a target detection method, a device, a millimeter wave radar and a movable platform, wherein the method comprises the following steps: acquiring detection information of a detection target and track reflection intensity of the detection target (S101); clustering the reflection points of the detection targets according to the detection information of the detection targets to generate clustered reflection points, and determining the number of the clustered reflection points (S102); determining the confidence of the type of the detected target according to the number of clustered reflection points and the track reflection intensity of the detected target (S103); according to the confidence of the type of the detection target, the detection target is determined to be a preset type (S104). Therefore, the detection targets are adaptively identified, and the identification efficiency and accuracy of the detection targets are improved.

Description

A target detection method, device, millimeter wave radar and movable platform

Technical Field

The present invention relates to the field of autonomous driving technology, and in particular to a target detection method, device, millimeter wave radar and a movable platform.

Background Art

At present, the application of target detection technology in various fields is becoming more and more extensive. Taking trucks in the field of autonomous driving as an example, the fields of Advanced Driver Assistant System (ADAS) and Autonomous Driving (AD) have developed rapidly in recent years. Millimeter-wave radar is widely used due to its advantages of all-day, all-weather, long-range and high speed measurement accuracy.

However, object recognition has always been a shortcoming of millimeter-wave radar, especially when detecting objects such as trucks, buses and container trucks, millimeter-wave radar often has target splitting and track splitting, making it impossible to determine the correct type of the target, causing a large number of misjudgments and false alarms for autonomous driving and assisted driving, which will bring safety risks to ADAS and AD systems. Therefore, how to more effectively improve the efficiency of target recognition and the safety of the system is of great significance.

Summary of the invention

The embodiments of the present invention provide a target detection method, a device, a millimeter wave radar and a movable platform, which can adaptively identify the detection target and improve the recognition efficiency and accuracy of the detection target.

In a first aspect, an embodiment of the present invention provides a target detection method, which is applied to a millimeter wave radar, comprising:

Acquire detection information of a detection target and a track reflection intensity of the detection target;

Clustering the reflection points of the detection target according to the detection information of the detection target to generate clustered reflection points, and determining the number of the clustered reflection points;

Determining the confidence of the type of the detection target according to the number of the clustered reflection points and the track reflection intensity of the detection target;

According to the confidence level of the type of the detection target, it is determined that the detection target is of a preset type.

In a second aspect, an embodiment of the present invention provides another target detection method, which is applied to a millimeter wave radar, including:

Acquire clustered reflection points of the detection target, and acquire position coordinates of the clustered reflection points, wherein the position coordinates are determined based on a pre-established coordinate system;

The length and width of the detection target are determined according to the position coordinates of the clustered reflection points.

In a third aspect, an embodiment of the present invention provides a target detection device, applied to a millimeter wave radar, comprising: one or more processors, working together or individually, the processors being configured to perform the following operations:

Acquire detection information of a detection target and a track reflection intensity of the detection target;

Clustering the reflection points of the detection target according to the detection information of the detection target to generate clustered reflection points, and determining the number of the clustered reflection points;

Determining the confidence of the type of the detection target according to the number of the clustered reflection points and the track reflection intensity of the detection target;

According to the confidence level of the type of the detection target, it is determined that the detection target is of a preset type.

In a fourth aspect, an embodiment of the present invention provides another target detection device, which is applied to a millimeter wave radar, wherein the millimeter wave radar can obtain reflection intensity information of the detection target and the number of clustered reflection points, and determine the confidence of the detection target according to the reflection intensity information and the number of clustered reflection points; the device includes one or more processors, working together or individually, and the processor is used to perform the following operations:

Acquire clustered reflection points of the detection target, and acquire position coordinates of the clustered reflection points, wherein the position coordinates are determined based on a pre-established coordinate system;

The length and width of the detection target are determined according to the position coordinates of the clustered reflection points.

In a fifth aspect, an embodiment of the present invention provides a millimeter wave radar, including:

An antenna, wherein the antenna is used to obtain an echo signal;

A processor is communicatively connected to the antenna, and the processor is configured to perform the following operations:

Acquire detection information of a detection target and a track reflection intensity of the detection target;

Clustering the reflection points of the detection target according to the detection information of the detection target to generate clustered reflection points, and determining the number of the clustered reflection points;

Determining the confidence of the type of the detection target according to the number of the clustered reflection points and the track reflection intensity of the detection target;

According to the confidence level of the type of the detection target, it is determined that the detection target is of a preset type.

In a sixth aspect, an embodiment of the present invention provides another millimeter wave radar, including:

An antenna, wherein the antenna is used to obtain an echo signal;

A processor is communicatively connected to the antenna, and the processor is configured to perform the following operations:

Acquire clustered reflection points of the detection target, and acquire position coordinates of the clustered reflection points, wherein the position coordinates are determined based on a pre-established coordinate system;

The length and width of the detection target are determined according to the position coordinates of the clustered reflection points.

In a seventh aspect, an embodiment of the present invention provides a movable platform, including:

Body;

A power system, installed on the movable platform, for providing power for the movable platform to move;

The device as provided in the third aspect or the fourth aspect above.

In an eighth aspect, an embodiment of the present invention provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the method described in the first or second aspect above.

In an embodiment of the present invention, the target detection device can obtain the detection information of the detection target and the track reflection intensity of the detection target, and cluster the reflection points of the detection target according to the detection information of the detection target to generate clustered reflection points, and determine the number of clustered reflection points. The target detection device can determine the confidence of the type of the detection target according to the number of clustered reflection points and the track reflection intensity of the detection target, and determine that the detection target is a preset type according to the confidence of the type of the detection target. Through this implementation, the detection target can be adaptively identified, which improves the recognition efficiency and accuracy of the detection target.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

FIG1 is a schematic diagram of a flow chart of a target detection method provided by an embodiment of the present invention;

FIG2a is a schematic diagram of the distribution of reflection points of a truck provided by an embodiment of the present invention;

FIG2b is a schematic diagram of the distribution of reflection points of another truck provided by an embodiment of the present invention;

FIG3 is a schematic diagram of a flow chart of another target detection method provided by an embodiment of the present invention;

FIG4a is a schematic diagram of the relationship between an energy envelope and a distance provided by an embodiment of the present invention;

FIG4b is a schematic diagram of the relationship between energy and distance of an unmanned vehicle provided by an embodiment of the present invention;

FIG5 is a schematic diagram of a coordinate system of a truck provided in an embodiment of the present invention;

FIG6 is a schematic diagram of the structure of a target detection device provided by an embodiment of the present invention;

FIG. 7 is a schematic diagram of the structure of another target detection device provided by an embodiment of the present invention.

DETAILED DESCRIPTION

The technical solutions in the embodiments of the present invention will be described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

Some embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

The target detection method provided in the embodiments of the present invention may be performed by a target detection device, and the target detection device may be applied to a millimeter wave radar. In some embodiments, the millimeter wave radar may be arranged on a movable platform; in some embodiments, the millimeter wave radar may be spatially independent of the movable platform. In some embodiments, the movable platform may be applied to intelligent terminals such as unmanned vehicles, unmanned ships, and unmanned aerial vehicles.

Taking unmanned vehicles in the field of autonomous driving as an example, currently on actual roads in the field of autonomous driving, large unmanned vehicles such as trucks are often mistaken for multiple target points by millimeter-wave radars, causing the ADAS system to misjudge whether the targets are the same object or whether the target is in a dangerous area, resulting in false alarms or alarm delays and other adverse situations.

In the embodiment of the present invention, when detecting a target, the target detection device can first use the millimeter wave radar to select the track of the detection target, and then cluster the reflection points of the detection target according to the distance information, speed information and other information of the detection target to select the clustered reflection points. After selecting the clustered reflection points, the target detection device can determine the confidence of the detection target according to the confidence of the clustered reflection points of the previous frame and the number of clustered reflection points of the current frame, and determine that the detection target is a preset type according to the confidence of the detection target. After determining that the detection target is a preset type, the target detection device can perform filtering processing according to the position coordinates of the clustered reflection points and the length and width of the detection target of the previous frame to determine the length and width of the detection target. After determining the length and width of the detection target, the target detection device can also expand the detection range to search whether there are other clustered reflection points on the track of the detection target. If so, the length and width of the detection target are recalculated, and the position information of the detection target is marked.

The target detection method proposed in the embodiment of the present invention can achieve efficient and high-accuracy target recognition by utilizing the spatial topological relationship and reflection intensity relationship between the reflection points of the detection target without adding new millimeter-wave radar hardware and processors, thereby solving the above-mentioned problems, improving the robustness of the entire ADAS and AD system, and enhancing the user experience.

Moreover, the identification of super-large detection targets has always been a difficulty and pain point in the industry. The method proposed in the embodiment of the present invention can also estimate the width, length and location information of the detection target, and can effectively identify different types of detection targets such as large detection targets, thereby effectively solving this problem.

The target detection method provided by the embodiment of the present invention is schematically described below with reference to the accompanying drawings.

Please refer to Figure 1 for details. Figure 1 is a flowchart of a target detection method provided by an embodiment of the present invention. The method can be performed by a target detection device, and the target detection device is applied to a millimeter wave radar, and the millimeter wave radar is arranged on a movable platform, as described above. Specifically, the method of the embodiment of the present invention includes the following steps.

S101: Acquire detection information of a detection target and the track reflection intensity of the detection target.

In an embodiment of the present invention, the target detection device can obtain detection information of the detection target and the track reflection intensity of the detection target. In some embodiments, the detection target includes but is not limited to intelligent terminals such as unmanned vehicles, unmanned ships, and unmanned aerial vehicles.

In some embodiments, the detection information of the detection target includes at least one of the following: speed information and distance information of the reflection point of the detection target. In some embodiments, the target detection device can determine the speed information of the reflection point of the detection target by acquiring the Doppler bin. In some embodiments, the Doppler bin refers to the Doppler frequency point, and the Doppler frequency point is proportional to the speed information of the reflection point of the detection target. In some embodiments, the target detection device can determine the distance information of the reflection point of the detection target by millimeter wave radar; in some embodiments, the distance information can include lateral distance and longitudinal distance.

In one embodiment, the target detection device may detect the detection target and record the track of the detection target before acquiring the detection information of the detection target and the track reflection intensity of the detection target. In some embodiments, the target detection device may select a mature track as the track of the detection target based on the recorded track of the detection target. In some embodiments, the mature track may be selected by the user or according to preset conditions, which is not specifically limited in the embodiments of the present invention.

Taking an unmanned vehicle as an example, the target detection device can obtain the Doppler bin of the reflection point of the unmanned vehicle, such as Dbin _candi , and obtain the Doppler bin of the track of the unmanned vehicle, such as Dbin _track , to obtain the speed information of the reflection point of the unmanned vehicle. The target detection device can obtain the longitudinal distance Ry _track and the lateral distance Rx _track of the track of the unmanned vehicle, and obtain the longitudinal distance Ry _candi and the lateral distance Rx _candi of the reflection point of the unmanned vehicle.

S102: Clustering the reflection points of the detection target according to the detection information of the detection target to generate clustered reflection points, and determining the number of the clustered reflection points.

In the embodiment of the present invention, the target detection device may cluster the reflection points of the detection target according to the detection information of the detection target to generate clustered reflection points, and determine the number of the clustered reflection points.

In some embodiments, the reflection points of the detection target may include multiple ones. Assuming that the detection target is a truck, the reflection points of the truck are illustrated by taking Figures 2a and 2b as examples. Figure 2a is a schematic diagram of the distribution of reflection points of a truck provided in an embodiment of the present invention, and Figure 2b is a schematic diagram of the distribution of reflection points of another truck provided in an embodiment of the present invention. As shown in Figures 2a and 2b, including the lane 21, the adjacent lane 22, the truck 23 and the millimeter wave radar 24, the distribution characteristics of the reflection points of the truck 23 are related to the viewing angle between the millimeter wave radar 24. As shown in Figure 2a, when the truck 23 is in the adjacent lane 22 on the side of the millimeter wave radar 24, the reflection points of the truck 23 are concentrated on the side of the irradiation surface of the millimeter wave radar 24, and the density of the reflection points gradually decreases with the increase of the distance. In addition, the reflection points at the wheels are also relatively concentrated. As shown in Figure 2b, when the truck 23 is directly in front of the lane 21 where the millimeter wave radar 24 is located, the reflection points are concentrated at the front and rear of the truck 23, and there are sporadic reflection points in the middle of the vehicle body due to the ground multipath effect.

In one embodiment, when the target detection device clusters the reflection points of the detection target based on the detection information of the detection target, it can obtain the detection information of multiple reflection points of the detection target and detect whether the detection information of the multiple reflection points meets a first preset condition. If so, the reflection points that meet the first preset condition can be clustered.

In some embodiments, the detection information includes the distance information and speed information of the reflection point of the detection target; the first preset condition is satisfied, including: the distance information is within a preset distance threshold range, and the speed information is within a preset speed information threshold range. In some embodiments, the speed information is determined by obtaining the Doppler frequency of the reflection point. In some embodiments, the distance information includes a longitudinal distance and a lateral distance; in some embodiments, the preset distance range includes a preset longitudinal distance range and a preset lateral distance range.

Taking an unmanned vehicle as an example, assuming that the Doppler bin of the reflection point of the unmanned vehicle is Dbin _candi , the Doppler bin of the track of the unmanned vehicle is Dbin _track , the longitudinal distance of the track of the unmanned vehicle is Ry _track and the lateral distance is Rx _track , and the longitudinal distance of the reflection point of the unmanned vehicle is Ry _candi and the lateral distance is Rx _candi , then the first preset condition satisfied may be as shown in the following formula (1):

Among them, 1.2>Ry _track -Ry _candi >-7.0 in the formula (1) indicates that the longitudinal distance in the distance information satisfies the preset longitudinal distance range, |Rx _track -Rx _candi |<2.0 indicates that the lateral distance in the distance information satisfies the preset lateral distance range, and since the speed information is determined by the Doppler bin, |Dbin _track -Dbin _candi |<5 in the formula (1) indicates that the speed information is within the preset speed information threshold range.

The embodiment of the present invention clusters the reflection points of the detection target by using the detection information of the detection target and the first preset condition to improve the accuracy and effectiveness of the clustering, thereby preparing for improving the confidence of the detection target.

S103: Determine the confidence level of the type of the detection target according to the number of the clustered reflection points and the track reflection intensity of the detection target.

In the embodiment of the present invention, the target detection device may determine the confidence level of the type of the detected target according to the number of the clustered reflection points and the track reflection intensity of the detected target.

In one embodiment, when the target detection device determines the confidence of the type of the detection target based on the number of clustered reflection points and the track reflection intensity of the detection target, the target detection device can obtain the number of clustered reflection points, and if the number of clustered reflection points meets a second preset condition, the confidence can be updated; and the target detection device can obtain the track reflection intensity of the detection target, and if the track reflection intensity of the detection target meets a third preset condition, the confidence can be updated.

In one embodiment, if the number of clustered reflection points meets the second preset condition, the target detection device may determine that the confidence level is increased by a first preset value; and/or, if the number of clustered reflection points does not meet the second preset condition, the target detection device may determine that the confidence level is the original value. In some embodiments, the second preset condition refers to that the number of clustered reflection points is greater than a preset number threshold.

In some embodiments, assuming that Cref represents the number of the clustered reflection points, the number of the clustered reflection points satisfying the second preset condition may be that the number of the clustered reflection points Cref> 5. In other embodiments, the second preset condition may also be satisfied that the number of the clustered reflection points is greater than other values, which is not specifically limited in the embodiments of the present invention.

In some embodiments, assuming that Cref represents the number of clustered reflection points, _Pn represents the current confidence of the detection target, and Pn _-1 represents the last confidence of the detection target, if the preset number threshold is 5 and the first preset value is 5, then when the number of clustered reflection points meets the second preset condition, the confidence is updated as shown in the following formula (2):

According to formula (2), if the number of clustered reflection points is greater than 5, the target detection device can determine that the confidence is increased by 5, that is, _Pn = _Pn-1 + 5; if the number of clustered reflection points is not greater than 5, the target detection device can determine that the confidence is the original value, that is, _Pn = Pn _-1 .

For example, assuming that the number of clustered reflection points Cref is 10 and the last confidence level Pn _-1 of the detection target is 15, the number of clustered reflection points 10>5, which satisfies the second preset condition. Therefore, according to the above formula (2), the current confidence level _Pn of the detection target is 15+5=20.

For another example, assuming that the number of clustered reflection points Cref is 4, and the last confidence level Pn _-1 of the detection target is 5, then the number of clustered reflection points 4<5. Therefore, according to the above formula (2), the current confidence level _Pn =Pn _-1 =5 of the detection target.

In some embodiments, when the target detection device detects that the track reflection intensity of the detection target satisfies a third preset condition and updates the confidence, if the track reflection intensity of the detection target is detected to be greater than a first preset intensity threshold, the confidence may be increased by a second preset value; and/or, if the track reflection intensity of the detection target is less than a second preset intensity threshold, the confidence may be subtracted from the first preset value; and/or, if the reflection intensity information of the detection target is between the first preset intensity threshold and the second preset intensity threshold, the confidence may be the original value.

In some embodiments, assuming that the Power _track represents the track reflection intensity of the detection target, the Power _truck represents the first preset intensity threshold of the detection target, and the Power _car represents the second preset intensity threshold, if the first preset value is 5 and the second preset value is 2, then when the target detection device detects that the track reflection intensity of the detection target meets the third preset condition, it can update the confidence according to the following formula (3).

According to formula (3), if the track reflection intensity of the detected target is greater than the first preset intensity threshold, i.e., Power _track >Power _truck , the confidence level can be increased by the second preset value, i.e., P _n +2; if the track reflection intensity of the detected target is less than the second preset intensity threshold, i.e., Power _track <Power _car , the confidence level can be subtracted by the first preset value, i.e., (P _n -5).

For example, assuming that the first preset value is 5, the second preset value is 2, and the current confidence _Pn is 5, if the track reflection intensity of the detected target is greater than the first preset intensity threshold, the confidence _Pn is increased by 2 to 10, and if the track reflection intensity of the detected target is less than the second preset intensity threshold, the confidence _Pn is subtracted by 5 to 0. If the reflection intensity information of the detected target is between the first preset intensity threshold and the second preset intensity threshold, the confidence is the original value of 5.

The embodiment of the present invention determines the confidence of the detected target by utilizing the number of clustered reflection points and the track reflection intensity of the detected target, thereby improving the accuracy of the confidence and thus improving the accuracy of determining the type of the detected target.

S104: Determine, according to the confidence level of the type of the detection target, that the detection target is of a preset type.

In the embodiment of the present invention, the target detection device may determine that the detected target is of a preset type according to the confidence level of the type of the detected target.

In one embodiment, when the target detection device determines that the detection target is of a preset type based on the confidence of the type of the detection target, it can detect the same detection target multiple times, and determine the current confidence of the detection target based on the current reflection intensity of the detection target and the number of clustered reflection points, as well as the previous confidence of the detection target, thereby determining that the detection target is of a preset type based on the current confidence.

In some embodiments, if the current confidence level is greater than a third preset value, the target detection device may determine that the detected target is of a preset type. In some embodiments, the preset type includes at least one of the following: a truck, a car, a bus, and a container truck.

For example, assuming that the preset type is a truck, and the third preset value corresponding to the truck is k, if the current confidence level _Pn =m is calculated according to the above formula (2) and/or formula (3), and m>k, the target detection device can determine that the detected target is a truck.

In one embodiment, the detection information of the detection target and the track reflection intensity of the detection target can be obtained by the above-mentioned methods of S101 and S102, and the reflection points of the detection target can be clustered according to the detection information of the detection target to generate cluster reflection points, and the number of the cluster reflection points can be determined. The target detection device can determine that the detection target is a preset type according to the number of cluster reflection points, and then according to the number of cluster reflection points and the track reflection intensity of the detection target. Thereby reducing the time for identifying the target. In an embodiment of the present invention, the target detection device can obtain the detection information of the detection target and the track reflection intensity of the detection target, and according to the detection information of the detection target, the reflection points of the detection target can be clustered to generate cluster reflection points, and the number of cluster reflection points can be determined. The target detection device can determine the confidence of the type of the detection target according to the number of cluster reflection points and the track reflection intensity of the detection target, so that the target detection device can determine that the detection target is a preset type according to the confidence of the type of the detection target. This implementation method can adaptively identify the detection target, thereby improving the recognition efficiency and accuracy of the detection target.

Please refer to Figure 3 specifically, which is a flow chart of another target detection method provided in an embodiment of the present invention, and the method can be executed by a target detection device, and the target detection device is applied to a millimeter wave radar, and the millimeter wave radar is arranged on a movable platform. It should be noted that in this embodiment, the clustered reflection points can be determined by the method for determining the clustered reflection points in the target detection method provided in the embodiment described in Figure 1. It can be understood that the method for determining the clustered reflection points in this embodiment includes but is not limited to this. For example, the reflection points are clustered according to the position-reflection intensity of the reflection points. The embodiment of the present invention is a schematic illustration of determining the length and width of the detection target based on the position coordinates of the clustered reflection points, and the method of the embodiment of the present invention includes the following steps.

S301: Acquire clustered reflection points of a detection target, and acquire position coordinates of the clustered reflection points.

In an embodiment of the present invention, the target detection device can obtain clustered reflection points of the detection target and obtain the position coordinates of the clustered reflection points, wherein the position coordinates are determined based on a pre-established coordinate system. In some embodiments, the pre-established coordinate system may be a coordinate system established with any position point of the detection target as the origin, which is not specifically limited in the embodiment of the present invention. Taking an unmanned vehicle as an example, the pre-established coordinate system may be a coordinate system established with the front end of the vehicle as the origin, the horizontal right side of the vehicle as the horizontal coordinate, and the vertical coordinate from the vehicle front to the rear as the vertical coordinate.

In some embodiments, the clustered reflection points are determined by clustering the reflection points of the detection target according to the detection information of the detection target. In some embodiments, the detection information includes at least one of the following: speed information and distance information of the reflection points of the detection target. The specific implementation examples are described above and will not be repeated here.

S302: Determine the length and width of the detection target according to the position coordinates of the clustered reflection points.

In the embodiment of the present invention, the target detection device may determine the length and width of the detection target according to the position coordinates of the clustered reflection points.

In some embodiments, the position coordinates include a horizontal coordinate and a vertical coordinate; the target detection device can determine the length and width of the detection target according to the horizontal coordinate and the vertical coordinate.

In some embodiments, the target detection device can determine the length and width of the current detection target based on the horizontal coordinates and the vertical coordinates of the clustered reflection points, and determine the length and width of the detection target based on the length and width of the current detection target and the length and width of the detection target last detected.

In some embodiments, when the target detection device determines the length and width of the current detection target based on the horizontal coordinates and vertical coordinates of the clustered reflection points, it can determine the width of the current detection target based on the horizontal coordinates of the clustered reflection points, and determine the length of the current detection target based on the vertical coordinates of the clustered reflection points.

In some embodiments, when the target detection device determines the width of the current detection target based on the lateral coordinates of the clustered reflection points, it can obtain the maximum and minimum values of the lateral coordinates of the clustered reflection points, and determine the difference between the maximum and minimum values of the lateral coordinates of the clustered reflection points as the width of the current detection target.

In some embodiments, when the target detection device determines the length of the current detection target based on the longitudinal coordinates of the clustered reflection points, it can obtain the maximum and minimum values of the longitudinal coordinates of the clustered reflection points, and determine the difference between the maximum and minimum values of the longitudinal coordinates of the clustered reflection points as the length of the current detection target.

In some embodiments, when the target detection device determines the length and width of the current detection target based on the horizontal coordinates and vertical coordinates of the clustered reflection points, it can determine the horizontal distance of the clustered reflection points based on the horizontal coordinates of the clustered reflection points, and determine the vertical distance of the clustered reflection points based on the vertical coordinates of the clustered reflection points.

Assume that _Xi represents the lateral distance of the i-th cluster reflection point, _Yi represents the longitudinal distance of the i-th cluster reflection point, if _Wtruckn represents the width of the current detection target, _Ltruckn represents the length of the current detection target, then the calculation formula of the length and width of the current detection target is shown in the following formula (4):

Wherein, the max(X _i ) represents the maximum value of the transverse coordinate, the min(X _i ) represents the minimum value of the transverse coordinate, the max(Y _i ) represents the maximum value of the longitudinal coordinate, and the min(Y _i ) represents the minimum value of the longitudinal coordinate. Taking the truck shown in FIG5 as an example, FIG5 is a schematic diagram of a coordinate system of a truck provided by an embodiment of the present invention. Assuming that the origin of the pre-established coordinate system is at the center position 51 of the front end of the truck head, the horizontal right direction of the head is the horizontal coordinate, and the vertical coordinate is from the head to the parking space. If the minimum value of the transverse coordinate of the detected cluster reflection point 52 is -0.8m and the maximum value is 0.8, it can be determined that the transverse distance of the cluster reflection point 52 is 0.8-(-0.8)=1.6m.

In some embodiments, when the target detection device determines the length and width of the detection target based on the current length and width of the detection target and the length and width of the detection target last detected, it can obtain the length and width obtained by the last detection of the detection target, and filter the length and width of the detection target based on the current length and width of the detection target and the length and width of the detection target last detected, and determine the length and width of the detection target based on the result of the filtering process.

In some embodiments, assuming that Wtruck _n-1 is the width of the detection target detected last time, and Ltruck _n-1 is the length of the detection target detected last time, if Wtruck _n represents the width of the current detection target, and Ltruck _n represents the length of the current detection target, then the calculation formula for the length and width of the current detection target can be as shown in the following formula (5):

For example, assuming that the width Wtruck _n-1 of the detection target detected last time is 1.6 m, and the length Ltruck _n-1 of the detection target detected last time is 4.6, then the width 1.6 of the detection target detected last time and the length 4.6 of the detection target detected last time are substituted into the above formula (5) to calculate that Wtruck _n is equal to 1.6 and Ltruck _n is equal to 4.6.

In one embodiment, after determining the length and width of the detection target based on the position coordinates of the clustered reflection points, the target detection device can also detect whether other emission points acquired by the millimeter-wave radar meet a fourth preset condition. If so, the reflection points that meet the fourth preset condition are added to the current clustered reflection points, and the length and width of the detection target are re-determined based on the position coordinates of the clustered reflection points.

In some embodiments, satisfying the fourth preset condition includes: the difference between the longitudinal coordinates of the other reflection points and the longitudinal coordinates of the current clustered reflection points is greater than the current length of the detection target and less than a specified search distance; and, the absolute value of the difference between the lateral coordinates of the current clustered reflection points and the other reflection points is less than a first preset threshold; and, the speed information of the other reflection points is within a preset speed information threshold range; and, the difference between the track reflection intensity of the detection target and the reflection intensity of the other reflection points is greater than the energy envelope of the detection target; and, the reflection intensity of the other reflection points is greater than a preset reflection intensity threshold.

In some embodiments, assuming that L _expand represents the specified search distance, L truck _n represents the length of the current detection target, Power _track represents the track reflection intensity, Power _candi represents the reflection intensity of the reflection point, Power _{delta_cri} represents the energy envelope of the detection target, Dbin _candi represents the Doppler bin of the reflection point, Dbin _track represents the Doppler bin of the track, the first preset threshold is 2, and the preset speed information threshold range is a range less than 5, then the fourth preset condition can be as shown in the following formula (6):

In some embodiments, the energy envelope of the reflection point of the detection target includes multiple energy points, and the energy envelope and the distance satisfy a certain statistical law. Taking Figure 4a as an example, Figure 4a is a schematic diagram of the relationship between an energy envelope and a distance provided by an embodiment of the present invention. It can be seen from Figure 4a that the strongest energy point is closest to the millimeter wave radar, and due to the effect of surface reflection, the energy of the remaining reflection points is at the envelope or slightly below the envelope.

Taking the relationship between energy and distance of an unmanned vehicle shown in FIG4b as an example, FIG4b is a schematic diagram of the relationship between energy and distance of an unmanned vehicle provided by an embodiment of the present invention. As shown in FIG4b, the relationship between energy and distance of the unmanned vehicle includes the relationship between energy and distance of a truck and the relationship between energy and distance of a car. As can be seen from FIG4b, the strongest point energy of a truck is greater than that of an ordinary vehicle at all distances.

In some embodiments, the specified search distance is calculated based on the length of the detection target; in some embodiments, the specified search distance includes the maximum length of the detection target. The specified search distance can be calculated using the following formula (7):

L _expand =max(L _truck *1.5,40) (7)

For example, assuming that the length L _truck of the detection target is 5 m, the length 5 m of the detection target is substituted into the above formula (7) to calculate that the specified search distance is 40.

The embodiment of the present invention expands the search range. If there are other clustered reflection points that meet the fourth preset condition on the track where the detection target is located, the length and width of the detection target can be re-determined. This implementation method can avoid misjudgment of the type of the detection target, identify super-large detection targets, and improve detection efficiency.

In some embodiments, after determining the length and width of the detection target, the target detection device may also obtain the position information of the detection target, and determine the designated center position of the detection target based on the position information and a preset position compensation value. In some embodiments, the position information includes but is not limited to being determined based on the lateral coordinates of the reflection point. In some embodiments, the preset position compensation value includes but is not limited to a lateral position compensation value, wherein the preset position compensation value is provided by an empirical value.

Taking a truck as an example, assuming that the designated center position of the detection target is the center position of the front of the truck, X _center represents the center position of the front, X _offset represents the lateral position compensation value, _Xi represents the lateral coordinate of the i-th cluster reflection point, and n represents the number of cluster reflection points. Then the calculation formula of X _center can be as shown in the following formula (8):

Among them, the It is used to calculate the sum of the lateral coordinates from the first cluster reflection point to the nth cluster reflection point.

The embodiment of the present invention can adjust the position of the detection target by determining the designated center position of the detection target, avoid collisions caused by the detection target deviating from the track, and improve the safety of the detection target. The problem of inaccurate estimation of the vehicle head position by the radar is solved.

In some embodiments, after determining the length and width of the detection target, the target detection device may also determine that the detection target is a preset type according to the length and width of the detection target. In some embodiments, the preset type includes at least one of the following: a truck, a car, a bus, and a container truck.

In the embodiment of the present invention, the target detection device can obtain the clustered reflection points of the detection target, obtain the position coordinates of the clustered reflection points, and determine the length and width of the detection target based on the position coordinates of the clustered reflection points, so as to more accurately and effectively determine the length and width of the detection target, identify super-large detection targets, so as to more effectively judge the type of the detection target, thereby improving the detection efficiency. By determining the designated center position of the detection target, the collision caused by the detection target deviating from the track and other problems are avoided, thereby improving the safety of the detection target.

Please refer to FIG. 6 , which is a schematic diagram of the structure of a target detection device provided by an embodiment of the present invention, wherein the device includes a memory 601 , a processor 602 , and a data interface 603 ;

The memory 601 may include a volatile memory; the memory 601 may also include a non-volatile memory; the memory 601 may also include a combination of the above-mentioned types of memories. The processor 602 may be a central processing unit (CPU). The processor 602 may further include a hardware chip. The above-mentioned hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD) or a combination thereof. The above-mentioned PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA) or any combination thereof.

The processor 602 is used to call the program instruction, and when the program instruction is executed, is used to perform the following operations:

Acquire detection information of a detection target and a track reflection intensity of the detection target;

Clustering the reflection points of the detection target according to the detection information of the detection target to generate clustered reflection points, and determining the number of the clustered reflection points;

Determining the confidence of the type of the detection target according to the number of the clustered reflection points and the track reflection intensity of the detection target;

According to the confidence level of the type of the detection target, it is determined that the detection target is of a preset type.

Furthermore, the detection information includes at least one of the following: speed information and distance information of the reflection point of the detection target.

Furthermore, the detection target has multiple reflection points.

Further, before acquiring the detection information of the detection target and the track reflection intensity of the detection target, the processor 602 is further configured to:

The detection target is detected and the track of the detection target is recorded.

Further, when the processor 602 clusters the reflection points of the detection target according to the detection information of the detection target, it is specifically used to:

Acquire detection information of multiple reflection points of the detection target;

Detecting whether the detection information of the plurality of reflection points meets a first preset condition;

If so, cluster the reflection points that meet the first preset condition.

Further, when the processor 602 determines the confidence of the type of the detection target according to the number of the clustered reflection points and the reflection intensity information of the detection target, it is specifically used to:

Acquiring the number of the clustered reflection points, and if the number of the clustered reflection points satisfies a second preset condition, updating the confidence level;

The track reflection intensity of the detection target is obtained, and if the track reflection intensity of the detection target meets a third preset condition, the confidence level is updated.

Further, the processor 602 is specifically configured to:

If the number of the clustered reflection points meets a second preset condition, determining that the confidence level is increased by a first preset value; and/or,

If the number of the clustered reflection points does not satisfy the second preset condition, the confidence level is determined to be the original value.

Further, the detection information includes distance information and speed information of the reflection point of the detection target;

The satisfying of the first preset condition includes: the distance information is within a preset distance threshold range, and the speed information is within a preset speed information threshold range.

Furthermore, the velocity information is determined by acquiring the Doppler frequency of the reflection point.

Furthermore, the second preset condition refers to that the number of the clustered reflection points is greater than a preset number threshold.

Further, if the track reflection intensity of the detected target satisfies a third preset condition, the processor 602 updates the confidence level by:

If the track reflection intensity of the detected target is greater than a first preset intensity threshold, the confidence level is increased by a first preset value; and/or,

If the track reflection intensity of the detected target is less than a second preset intensity threshold, the confidence level is reduced by a second preset value; and/or,

If the reflection intensity information of the detection target is between the first preset intensity threshold and the second preset intensity threshold, the confidence level is the original value.

Furthermore, the third preset condition refers to that the reflection intensity information is greater than a preset reflection intensity threshold.

Further, when the processor 602 determines that the detection target is of a preset type according to the confidence level of the type of the detection target, it is specifically configured to:

Detect the same detection target multiple times;

Determining the current confidence of the detection target according to the current reflection intensity of the detection target and the number of clustered reflection points, and the last confidence of the detection target;

According to the current confidence level, it is determined that the detection target is of a preset type.

Further, when the processor 602 determines the type of the detected target according to the current confidence level, it is specifically configured to:

If the current confidence level is greater than a third preset value, the detection target is determined to be of a preset type.

Furthermore, the preset types include at least one of the following: a truck, a car, a bus, and a container truck.

In an embodiment of the present invention, the target detection device can obtain the detection information of the detection target and the track reflection intensity of the detection target, and cluster the reflection points of the detection target according to the detection information of the detection target to generate clustered reflection points and determine the number of clustered reflection points. The target detection device can determine the confidence of the type of the detection target according to the number of clustered reflection points and the track reflection intensity of the detection target, so that the target detection device can determine that the detection target is a preset type according to the confidence of the type of the detection target. Through this implementation, the detection target can be adaptively identified, which improves the recognition efficiency and accuracy of the detection target.

Please refer to FIG. 7 , which is a schematic diagram of the structure of another target detection device provided by an embodiment of the present invention, wherein the device includes a memory 701 , a processor 702 , and a data interface 703 ;

The memory 701 may include a volatile memory; the memory 701 may also include a non-volatile memory; the memory 701 may also include a combination of the above-mentioned types of memories. The processor 702 may be a central processing unit (CPU). The processor 702 may further include a hardware chip. The above-mentioned hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD) or a combination thereof. The above-mentioned PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA) or any combination thereof.

The processor 702 is used to call the program instruction, and when the program instruction is executed, is used to perform the following operations:

Acquire clustered reflection points of the detection target, and acquire position coordinates of the clustered reflection points, wherein the position coordinates are determined based on a pre-established coordinate system;

The length and width of the detection target are determined according to the position coordinates of the clustered reflection points.

Furthermore, the clustered reflection points are determined by clustering the reflection points of the detection target according to the detection information of the detection target.

Furthermore, the detection information includes at least one of the following: speed information and distance information of the reflection point of the detection target.

Further, the position coordinates include a horizontal coordinate and a vertical coordinate; when the processor 702 determines the length and width of the detection target according to the position coordinates of the clustered reflection points, it is specifically used to:

The length and width of the detection target are determined according to the horizontal coordinate and the vertical coordinate.

Further, the processor 702 is specifically configured to:

Determine the length and width of the current detection target according to the horizontal coordinates and the vertical coordinates of the clustered reflection points;

The length and width of the detection target are determined according to the current length and width of the detection target and the length and width of the detection target detected last time.

Further, when the processor 702 determines the length and width of the detection target according to the current length and width of the detection target and the length and width of the detection target detected last time, it is specifically used to:

Obtain the length and width of the detection target obtained in the last detection;

According to the current length and width of the detection target and the length and width of the detection target detected last time, filtering the length and width of the detection target;

The length and width of the detection target are determined according to the result of the filtering process.

Further, when the processor 702 determines the length and width of the current detection target according to the horizontal coordinates and the vertical coordinates of the clustered reflection points, it is specifically configured to:

Determining the width of the current detection target according to the lateral coordinates of the clustered reflection points;

The length of the current detection target is determined according to the longitudinal coordinates of the clustered reflection points.

Further, when the processor 702 determines the width of the current detection target according to the lateral coordinates of the clustered reflection points, it is specifically configured to:

Obtaining the maximum and minimum values of the lateral coordinates of the clustered reflection points;

The difference between the maximum value and the minimum value of the lateral coordinates of the clustered reflection points is determined as the width of the current detection target.

Further, when the processor 702 determines the length of the current detection target according to the longitudinal coordinates of the clustered reflection points, it is specifically configured to:

Obtaining the maximum and minimum values of the longitudinal coordinates of the clustered reflection points;

The difference between the maximum value and the minimum value of the longitudinal coordinates of the clustered reflection points is determined as the length of the current detection target.

Further, after determining the length and width of the detection target according to the position coordinates of the clustered reflection points, the processor 702 is further configured to:

Detecting whether other emission points acquired by the millimeter-wave radar meet a fourth preset condition;

If so, the reflection points satisfying the fourth preset condition are added to the current clustered reflection points, and the length and width of the detection target are re-determined according to the position coordinates of the clustered reflection points.

Furthermore, the satisfying of the fourth preset condition includes:

The difference between the longitudinal coordinates of the other reflection points and the longitudinal coordinates of the current cluster reflection points is greater than the current length of the detection target and less than the specified search distance;

And, the absolute value of the difference between the current lateral coordinates of the clustered reflection point and the other reflection points is less than a first preset threshold;

And, the speed information of the other reflection points is within a preset speed information threshold range;

and, the difference between the track reflection intensity of the detection target and the reflection intensity of other reflection points is greater than the energy envelope of the detection target;

And, the reflection intensity of the other reflection points is greater than a preset reflection intensity threshold.

Furthermore, the specified search distance is calculated based on the length of the detection target.

Furthermore, the specified search distance includes a maximum length of the detected target.

Further, after determining the length and width of the detection target, the processor 702 is further configured to:

Acquire location information of the detection target;

The designated center position of the detection target is determined according to the position information and a preset position compensation value.

Further, after determining the length and width of the detection target, the processor 702 is further configured to:

According to the length and width of the detection target, it is determined that the detection target is of a preset type.

Furthermore, the preset types include at least one of the following: a truck, a car, a bus, and a container truck.

In the embodiment of the present invention, the target detection device can obtain the clustered reflection points of the detection target, obtain the position coordinates of the clustered reflection points, and determine the length and width of the detection target according to the position coordinates of the clustered reflection points. This implementation method can more accurately and effectively determine the length and width of the detection target, so as to more effectively determine the type of the detection target.

An embodiment of the present invention provides a millimeter wave radar, including: an antenna, the antenna is used to obtain an echo signal; a processor, which is communicatively connected to the antenna, and the processor is used to perform the following operations:

Acquire detection information of a detection target and a track reflection intensity of the detection target;

Clustering the reflection points of the detection target according to the detection information of the detection target to generate clustered reflection points, and determining the number of the clustered reflection points;

Determining the confidence of the type of the detection target according to the number of the clustered reflection points and the track reflection intensity of the detection target;

According to the confidence level of the type of the detection target, it is determined that the detection target is of a preset type.

Furthermore, the detection information includes at least one of the following: speed information and distance information of the reflection point of the detection target.

Furthermore, the detection target has multiple reflection points.

Furthermore, before acquiring the detection information of the detection target and the track reflection intensity of the detection target, the processor is further used to:

The detection target is detected and the track of the detection target is recorded.

Further, when the processor clusters the reflection points of the detection target according to the detection information of the detection target, it is specifically used to:

Acquire detection information of multiple reflection points of the detection target;

Detecting whether the detection information of the plurality of reflection points meets a first preset condition;

If so, cluster the reflection points that meet the first preset condition.

Further, when the processor determines the confidence of the type of the detection target according to the number of the clustered reflection points and the reflection intensity information of the detection target, it is specifically used to:

Acquiring the number of the clustered reflection points, and if the number of the clustered reflection points satisfies a second preset condition, updating the confidence level;

The track reflection intensity of the detection target is obtained, and if the track reflection intensity of the detection target meets a third preset condition, the confidence level is updated.

Furthermore, the processor is specifically configured to:

If the number of the clustered reflection points meets a second preset condition, determining that the confidence level is increased by a first preset value; and/or,

If the number of the clustered reflection points does not satisfy the second preset condition, the confidence level is determined to be the original value.

Further, the detection information includes distance information and speed information of the reflection point of the detection target;

The satisfying of the first preset condition includes: the distance information is within a preset distance threshold range, and the speed information is within a preset speed information threshold range.

Furthermore, the velocity information is determined by acquiring the Doppler frequency of the reflection point.

Furthermore, the second preset condition refers to that the number of the clustered reflection points is greater than a preset number threshold.

Further, if the track reflection intensity of the detected target satisfies a third preset condition, the processor updates the confidence level by:

If the track reflection intensity of the detected target is greater than a first preset intensity threshold, the confidence level is increased by a first preset value; and/or,

If the track reflection intensity of the detected target is less than a second preset intensity threshold, the confidence level is reduced by a second preset value; and/or,

If the reflection intensity information of the detection target is between the first preset intensity threshold and the second preset intensity threshold, the confidence level is the original value.

Furthermore, the third preset condition refers to that the reflection intensity information is greater than a preset reflection intensity threshold.

Further, when the processor determines, based on the confidence level of the type of the detection target, that the detection target is of a preset type, it is specifically configured to:

Detect the same detection target multiple times;

Determining the current confidence of the detection target according to the current reflection intensity of the detection target and the number of clustered reflection points, and the last confidence of the detection target;

According to the current confidence level, it is determined that the detection target is of a preset type.

Further, when the processor determines the type of the detection target according to the current confidence level, it is specifically used to:

If the current confidence level is greater than a third preset value, the detection target is determined to be of a preset type.

Furthermore, the preset types include at least one of the following: a truck, a car, a bus, and a container truck.

In an embodiment of the present invention, the millimeter wave radar can obtain detection information of the detection target and the track reflection intensity of the detection target, and cluster the reflection points of the detection target according to the detection information of the detection target to generate clustered reflection points and determine the number of clustered reflection points. The target detection device can determine the confidence of the type of the detection target according to the number of clustered reflection points and the track reflection intensity of the detection target, so that the target detection device can determine that the detection target is a preset type according to the confidence of the type of the detection target. This implementation method can adaptively identify the detection target, thereby improving the recognition efficiency and accuracy of the detection target.

The embodiment of the present invention further provides another millimeter wave radar, comprising: an antenna, the antenna being used to obtain an echo signal; and a processor, being communicatively connected to the antenna, the processor being used to perform the following operations:

Acquire clustered reflection points of the detection target, and acquire position coordinates of the clustered reflection points, wherein the position coordinates are determined based on a pre-established coordinate system;

The length and width of the detection target are determined according to the position coordinates of the clustered reflection points.

Furthermore, the clustered reflection points are determined by clustering the reflection points of the detection target according to the detection information of the detection target.

Furthermore, the detection information includes at least one of the following: speed information and distance information of the reflection point of the detection target.

Further, the position coordinates include a horizontal coordinate and a vertical coordinate; when the processor determines the length and width of the detection target according to the position coordinates of the clustered reflection points, it is specifically used to:

The length and width of the detection target are determined according to the horizontal coordinate and the vertical coordinate.

Furthermore, the processor is specifically configured to:

Determine the length and width of the current detection target according to the horizontal coordinates and the vertical coordinates of the clustered reflection points;

The length and width of the detection target are determined according to the current length and width of the detection target and the length and width of the detection target detected last time.

Further, when the processor determines the length and width of the detection target according to the current length and width of the detection target and the length and width of the detection target detected last time, it is specifically used to:

Obtain the length and width of the detection target obtained in the last detection;

According to the current length and width of the detection target and the length and width of the detection target detected last time, filtering the length and width of the detection target;

The length and width of the detection target are determined according to the result of the filtering process.

Further, when the processor determines the length and width of the current detection target according to the horizontal coordinates and the vertical coordinates of the clustered reflection points, it is specifically used to:

Determining the width of the current detection target according to the lateral coordinates of the clustered reflection points;

The length of the current detection target is determined according to the longitudinal coordinates of the clustered reflection points.

Further, when the processor determines the width of the current detection target according to the lateral coordinates of the clustered reflection points, it is specifically used to:

Obtaining the maximum and minimum values of the lateral coordinates of the clustered reflection points;

The difference between the maximum value and the minimum value of the lateral coordinates of the clustered reflection points is determined as the width of the current detection target.

Further, when the processor determines the length of the current detection target according to the longitudinal coordinates of the clustered reflection points, it is specifically used to:

Obtaining the maximum and minimum values of the longitudinal coordinates of the clustered reflection points;

The difference between the maximum value and the minimum value of the longitudinal coordinates of the clustered reflection points is determined as the length of the current detection target.

Furthermore, after determining the length and width of the detection target according to the position coordinates of the clustered reflection points, the processor is further configured to:

Detecting whether other emission points acquired by the millimeter-wave radar meet a fourth preset condition;

If so, the reflection points satisfying the fourth preset condition are added to the current clustered reflection points, and the length and width of the detection target are re-determined according to the position coordinates of the clustered reflection points.

Furthermore, the satisfying of the fourth preset condition includes:

The difference between the longitudinal coordinates of the other reflection points and the longitudinal coordinates of the current cluster reflection points is greater than the current length of the detection target and less than the specified search distance;

And, the absolute value of the difference between the current lateral coordinates of the clustered reflection point and the other reflection points is less than a first preset threshold;

And, the speed information of the other reflection points is within a preset speed information threshold range;

and, the difference between the track reflection intensity of the detection target and the reflection intensity of other reflection points is greater than the energy envelope of the detection target;

And, the reflection intensity of the other reflection points is greater than a preset reflection intensity threshold.

Furthermore, the specified search distance is calculated based on the length of the detection target.

Furthermore, the specified search distance includes a maximum length of the detected target.

Further, after determining the length and width of the detection target, the processor is further configured to:

Acquire location information of the detection target;

The designated center position of the detection target is determined according to the position information and a preset position compensation value.

Further, after determining the length and width of the detection target, the processor is further configured to:

According to the length and width of the detection target, it is determined that the detection target is of a preset type.

Furthermore, the preset types include at least one of the following: a truck, a car, a bus, and a container truck.

In the embodiment of the present invention, the millimeter wave radar can obtain the clustered reflection points of the detection target, obtain the position coordinates of the clustered reflection points, and determine the length and width of the detection target according to the position coordinates of the clustered reflection points. This implementation method can more accurately and effectively determine the length and width of the detection target, so as to more effectively determine the type of the detection target.

An embodiment of the present invention provides a movable platform, comprising: a body; a power system installed on the movable platform and used to provide power for the movable platform to move;

A processor is used to obtain detection information of a detection target and the track reflection intensity of the detection target; cluster the reflection points of the detection target according to the detection information of the detection target to generate clustered reflection points, and determine the number of the clustered reflection points; determine the confidence of the type of the detection target according to the number of the clustered reflection points and the track reflection intensity of the detection target; and determine that the detection target is a preset type according to the confidence of the type of the detection target.

Furthermore, the detection information includes at least one of the following: speed information and distance information of the reflection point of the detection target.

Furthermore, the detection target has multiple reflection points.

Furthermore, before acquiring the detection information of the detection target and the track reflection intensity of the detection target, the processor is further used to:

The detection target is detected and the track of the detection target is recorded.

Further, when the processor clusters the reflection points of the detection target according to the detection information of the detection target, it is specifically used to:

Acquire detection information of multiple reflection points of the detection target;

Detecting whether the detection information of the plurality of reflection points meets a first preset condition;

If so, cluster the reflection points that meet the first preset condition.

Further, when the processor determines the confidence of the type of the detection target according to the number of the clustered reflection points and the reflection intensity information of the detection target, it is specifically used to:

Acquiring the number of the clustered reflection points, and if the number of the clustered reflection points satisfies a second preset condition, updating the confidence level;

The track reflection intensity of the detection target is obtained, and if the track reflection intensity of the detection target meets a third preset condition, the confidence level is updated.

Furthermore, the processor is specifically configured to:

If the number of the clustered reflection points meets a second preset condition, determining that the confidence level is increased by a first preset value; and/or,

If the number of the clustered reflection points does not satisfy the second preset condition, the confidence level is determined to be the original value.

Further, the detection information includes distance information and speed information of the reflection point of the detection target;

The satisfying of the first preset condition includes: the distance information is within a preset distance threshold range, and the speed information is within a preset speed information threshold range.

Furthermore, the velocity information is determined by acquiring the Doppler frequency of the reflection point.

Furthermore, the second preset condition refers to that the number of the clustered reflection points is greater than a preset number threshold.

Further, if the track reflection intensity of the detected target satisfies a third preset condition, the processor updates the confidence level by:

If the track reflection intensity of the detected target is greater than a first preset intensity threshold, the confidence level is increased by a first preset value; and/or,

If the track reflection intensity of the detected target is less than a second preset intensity threshold, the confidence level is reduced by a second preset value; and/or,

If the reflection intensity information of the detection target is between the first preset intensity threshold and the second preset intensity threshold, the confidence level is the original value.

Furthermore, the third preset condition refers to that the reflection intensity information is greater than a preset reflection intensity threshold.

Further, when the processor determines, based on the confidence level of the type of the detection target, that the detection target is of a preset type, it is specifically configured to:

Detect the same detection target multiple times;

Determining the current confidence of the detection target according to the current reflection intensity of the detection target and the number of clustered reflection points, and the last confidence of the detection target;

According to the current confidence level, it is determined that the detection target is of a preset type.

Further, when the processor determines the type of the detection target according to the current confidence level, it is specifically used to:

If the current confidence level is greater than a third preset value, the detection target is determined to be of a preset type.

Furthermore, the preset types include at least one of the following: a truck, a car, a bus, and a container truck.

In an embodiment of the present invention, the movable platform can obtain detection information of the detection target and the track reflection intensity of the detection target, and cluster the reflection points of the detection target according to the detection information of the detection target to generate clustered reflection points and determine the number of clustered reflection points. The target detection device can determine the confidence of the type of the detection target according to the number of clustered reflection points and the track reflection intensity of the detection target, so that the target detection device can determine that the detection target is a preset type according to the confidence of the type of the detection target. This implementation method can adaptively identify the detection target, thereby improving the recognition efficiency and accuracy of the detection target.

The embodiment of the present invention further provides another movable platform, comprising: a body; a power system installed on the movable platform and used to provide power for the movable platform to move;

A processor is used to obtain clustered reflection points of a detection target and obtain position coordinates of the clustered reflection points, wherein the position coordinates are determined based on a pre-established coordinate system; and determine the length and width of the detection target based on the position coordinates of the clustered reflection points.

Furthermore, the clustered reflection points are determined by clustering the reflection points of the detection target according to the detection information of the detection target.

Furthermore, the detection information includes at least one of the following: speed information and distance information of the reflection point of the detection target.

Further, the position coordinates include a horizontal coordinate and a vertical coordinate; when the processor determines the length and width of the detection target according to the position coordinates of the clustered reflection points, it is specifically used to:

The length and width of the detection target are determined according to the horizontal coordinate and the vertical coordinate.

Furthermore, the processor is specifically configured to:

Determine the length and width of the current detection target according to the horizontal coordinates and the vertical coordinates of the clustered reflection points;

The length and width of the detection target are determined according to the current length and width of the detection target and the length and width of the detection target detected last time.

Further, when the processor determines the length and width of the detection target according to the current length and width of the detection target and the length and width of the detection target detected last time, it is specifically used to:

Obtain the length and width of the detection target obtained in the last detection;

According to the current length and width of the detection target and the length and width of the detection target detected last time, filtering the length and width of the detection target;

The length and width of the detection target are determined according to the result of the filtering process.

Further, when the processor determines the length and width of the current detection target according to the horizontal coordinates and the vertical coordinates of the clustered reflection points, it is specifically used to:

Determining the width of the current detection target according to the lateral coordinates of the clustered reflection points;

The length of the current detection target is determined according to the longitudinal coordinates of the clustered reflection points.

Further, when the processor determines the width of the current detection target according to the lateral coordinates of the clustered reflection points, it is specifically used to:

Obtaining the maximum and minimum values of the lateral coordinates of the clustered reflection points;

The difference between the maximum value and the minimum value of the lateral coordinates of the clustered reflection points is determined as the width of the current detection target.

Further, when the processor determines the length of the current detection target according to the longitudinal coordinates of the clustered reflection points, it is specifically used to:

Obtaining the maximum and minimum values of the longitudinal coordinates of the clustered reflection points;

The difference between the maximum value and the minimum value of the longitudinal coordinates of the clustered reflection points is determined as the length of the current detection target.

Furthermore, after determining the length and width of the detection target according to the position coordinates of the clustered reflection points, the processor is further configured to:

Detecting whether other emission points acquired by the millimeter-wave radar meet a fourth preset condition;

If so, the reflection points satisfying the fourth preset condition are added to the current clustered reflection points, and the length and width of the detection target are re-determined according to the position coordinates of the clustered reflection points.

Furthermore, the satisfying of the fourth preset condition includes:

The difference between the longitudinal coordinates of the other reflection points and the longitudinal coordinates of the current cluster reflection points is greater than the current length of the detection target and less than the specified search distance;

And, the absolute value of the difference between the current lateral coordinates of the clustered reflection point and the other reflection points is less than a first preset threshold;

And, the speed information of the other reflection points is within a preset speed information threshold range;

and, the difference between the track reflection intensity of the detection target and the reflection intensity of other reflection points is greater than the energy envelope of the detection target;

And, the reflection intensity of the other reflection points is greater than a preset reflection intensity threshold.

Furthermore, the specified search distance is calculated based on the length of the detection target.

Furthermore, the specified search distance includes a maximum length of the detected target.

Further, after determining the length and width of the detection target, the processor is further configured to:

Acquire location information of the detection target;

The designated center position of the detection target is determined according to the position information and a preset position compensation value.

Further, after determining the length and width of the detection target, the processor is further configured to:

According to the length and width of the detection target, it is determined that the detection target is of a preset type.

Furthermore, the preset types include at least one of the following: a truck, a car, a bus, and a container truck.

In the embodiment of the present invention, the movable platform can obtain the clustered reflection points of the detection target and the position coordinates of the clustered reflection points, and determine the length and width of the detection target according to the position coordinates of the clustered reflection points. This embodiment can more accurately and effectively determine the length and width of the detection target, so as to more effectively determine the type of the detection target.

An embodiment of the present invention further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the method described in the embodiment of the present invention, and can also implement the device corresponding to the embodiment of the present invention, which will not be described in detail here.

The computer-readable storage medium may be an internal storage unit of the device described in any of the foregoing embodiments, such as a hard disk or memory of the device. The computer-readable storage medium may also be an external storage device of the device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the device. Furthermore, the computer-readable storage medium may also include both an internal storage unit of the device and an external storage device. The computer-readable storage medium is used to store the computer program and other programs and data required by the terminal. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.

The above disclosure is only part of the embodiments of the present invention, which certainly cannot be used to limit the scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims (89)

1. A target detection method applied to a millimeter wave radar, characterized by comprising:

Acquiring detection information of a detection target and track reflection intensity of the detection target;

Clustering the reflection points of the detection targets according to the detection information of the detection targets to generate clustered reflection points, and determining the number of the clustered reflection points;

Determining the confidence level of the type of the detection target according to the number of the clustered reflection points and the track reflection intensity of the detection target;

and determining that the detection target is of a preset type according to the confidence coefficient of the type of the detection target.

2. The method of claim 1, wherein the detection information comprises at least one of: and the speed information and the distance information of the reflection point of the detection target.

3. The method of claim 1, wherein the detection target has a plurality of reflection points.

4. The method of claim 1, further comprising, prior to the acquiring the detection information of the detection target and the track reflection intensity of the detection target:

Detecting the detection target and recording the track of the detection target.

5. A method according to claim 3, wherein said clustering the reflection points of the detection target based on the detection information of the detection target comprises:

Acquiring detection information of a plurality of reflection points of the detection target;

Detecting whether the detection information of the plurality of reflection points meets a first preset condition;

if yes, clustering the reflection points meeting the first preset condition.

6. The method of claim 5, wherein determining the confidence level of the type of the detected object based on the number of clustered reflection points and the track reflection intensity of the detected object comprises:

Acquiring the number of the clustered reflection points, and if the number of the clustered reflection points meets a second preset condition, updating the confidence coefficient;

and acquiring the track reflection intensity of the detection target, and if the track reflection intensity of the detection target meets a third preset condition, updating the confidence coefficient.

7. The method according to claim 6, comprising:

if the number of the clustered reflection points meets a second preset condition, determining that the confidence coefficient is increased by a first preset value; and/or the number of the groups of groups,

And if the number of the clustered reflection points does not meet a second preset condition, determining the confidence coefficient as an original value.

8. The method of claim 5, wherein the step of determining the position of the probe is performed,

The detection information comprises distance information and speed information of a reflection point of the detection target;

The meeting the first preset condition includes: the distance information is within a preset distance threshold range, and the speed information is within a preset speed information threshold range.

9. The method of claim 8, wherein the velocity information is determined by acquiring doppler bins for the reflection points.

10. The method of claim 6, wherein the step of providing the first layer comprises,

The second preset condition means that the number of the clustered reflection points is greater than a preset number threshold.

11. The method of claim 6, wherein updating the confidence level if the track reflection intensity of the detection target meets a third preset condition comprises:

if the track reflection intensity of the detection target is larger than a first preset intensity threshold value, the confidence coefficient is increased by a second preset value; and/or the number of the groups of groups,

If the track reflection intensity of the detection target is smaller than a second preset intensity threshold value, subtracting a first preset value from the confidence coefficient; and/or the number of the groups of groups,

If the track reflection intensity of the detection target is between a first preset intensity threshold value and a second preset intensity threshold value, the confidence coefficient is an original value.

12. The method of claim 11, wherein the third predetermined condition is that the track reflected intensity is greater than a predetermined reflected intensity threshold.

13. The method of claim 1, wherein determining that the detection target is of a preset type according to the confidence of the type of the detection target comprises:

Detecting the same detection target for multiple times;

Determining the current confidence coefficient of the detection target according to the current track reflection intensity of the detection target, the number of clustered reflection points and the last confidence coefficient of the detection target;

And determining that the detection target is of a preset type according to the current confidence.

14. The method of claim 13, wherein determining the type of the detection target based on the current confidence comprises:

And if the current confidence coefficient is larger than a third preset value, determining that the detection target is of a preset type.

15. The method of claim 1, wherein the preset type comprises at least one of: trucks, cars, buses.

16. A target detection method applied to a millimeter wave radar, characterized by comprising:

Acquiring a clustered reflection point of a detection target, and acquiring a position coordinate of the clustered reflection point, wherein the position coordinate is determined based on a pre-established coordinate system; the clustering reflection points are obtained by carrying out clustering determination on the reflection points of the detection targets according to the detection information of the detection targets;

determining the length and the width of the detection target according to the position coordinates of the clustered reflection points;

acquiring the position information of the detection target; the position information of the detection target is determined according to the position coordinates of the clustered reflection points;

And determining the designated center position of the detection target according to the position information of the detection target and a preset position compensation value.

17. The method of claim 16, wherein the detection information includes at least one of: and the speed information and the distance information of the reflection point of the detection target.

18. The method of claim 16, wherein the position coordinates comprise lateral coordinates and longitudinal coordinates; the determining the length and the width of the detection target according to the position coordinates of the clustered reflection points comprises the following steps:

and determining the length and the width of the detection target according to the transverse coordinates and the longitudinal coordinates.

19. The method according to claim 18, characterized in that the method comprises:

Determining the length and width of the current detection target according to the transverse coordinates and the longitudinal coordinates of the clustered reflection points;

and determining the length and the width of the detection target according to the length and the width of the current detection target and the length and the width of the last detection target.

20. The method of claim 19, wherein the determining the length and width of the detection target based on the length and width of the current detection target and the length and width of the last detection target comprises:

acquiring the length and the width obtained by detecting the detection target last time;

According to the length and width of the current detection target and the length and width of the last detection target, filtering the length and width of the detection target;

And determining the length and the width of the detection target according to the result of the filtering process.

21. The method of claim 19, wherein determining the length and width of the current detection target according to the lateral and longitudinal coordinates of the clustered reflection points comprises:

determining the width of the current detection target according to the transverse coordinates of the clustered reflection points;

And determining the length of the current detection target according to the longitudinal coordinates of the clustered reflection points.

22. The method of claim 21, wherein determining the width of the current detection target based on the lateral coordinates of the clustered reflection points comprises:

Obtaining the maximum value and the minimum value of the transverse coordinates of the clustered reflection points;

And determining the difference between the maximum value and the minimum value of the transverse coordinates of the clustered reflection points as the width of the current detection target.

23. The method of claim 21, wherein determining the length of the current detection target based on the longitudinal coordinates of the clustered reflection points comprises:

Obtaining the maximum value and the minimum value of the longitudinal coordinates of the clustered reflection points;

And determining the difference between the maximum value and the minimum value of the longitudinal coordinates of the clustered reflection points as the length of the current detection target.

24. The method of claim 18, wherein after determining the length and width of the detection target, further comprising:

Detecting whether other reflection points acquired by the millimeter wave radar meet a fourth preset condition;

If yes, adding other reflection points meeting the fourth preset condition into the current clustering reflection points, and redetermining the length and the width of the detection target according to the position coordinates of the clustering reflection points.

25. The method of claim 24, wherein the meeting a fourth predetermined condition comprises:

the difference between the longitudinal coordinates of the other reflecting points and the longitudinal coordinates of the current clustering reflecting points is larger than the current length of the detection target and smaller than a specified searching distance;

the absolute value of the difference between the transverse coordinates of the current clustered reflection points and the other reflection points is smaller than a first preset threshold value;

The speed information of the other reflection points is within a preset speed information threshold range;

and the difference between the track reflection intensity of the detection target and the reflection intensity of other reflection points is larger than the energy envelope of the detection target;

and the reflection intensity of the other reflection points is larger than a preset reflection intensity threshold value.

26. The method of claim 25, wherein the step of determining the position of the probe is performed,

The specified search distance is calculated according to the length of the detection target.

27. The method of claim 26, wherein the specified search distance comprises a maximum length of the detection target.

28. The method of claim 16, wherein after determining the length and width of the detection target, further comprising:

and determining that the detection target is of a preset type according to the length and the width of the detection target.

29. The method of claim 28, wherein the preset type comprises at least one of: trucks, cars, buses.

30. An object detection apparatus applied to a millimeter wave radar, comprising: one or more processors, working together or individually, for performing the following:

Acquiring detection information of a detection target and track reflection intensity of the detection target;

Clustering the reflection points of the detection targets according to the detection information of the detection targets to generate clustered reflection points, and determining the number of the clustered reflection points;

Determining the confidence level of the type of the detection target according to the number of the clustered reflection points and the track reflection intensity of the detection target;

and determining that the detection target is of a preset type according to the confidence coefficient of the type of the detection target.

31. The apparatus of claim 30, wherein the detection information comprises at least one of: and the speed information and the distance information of the reflection point of the detection target.

32. The apparatus of claim 30, wherein the detection target has a plurality of reflection points.

33. The apparatus of claim 30, wherein the processor, prior to obtaining the detection information of the detection target and the track reflection intensity of the detection target, is further configured to:

Detecting the detection target and recording the track of the detection target.

34. The apparatus of claim 32, wherein the processor is configured to, when clustering the reflection points of the detection target according to the detection information of the detection target:

Acquiring detection information of a plurality of reflection points of the detection target;

Detecting whether the detection information of the plurality of reflection points meets a first preset condition;

if yes, clustering the reflection points meeting the first preset condition.

35. The apparatus of claim 34, wherein the processor is configured to, when determining the confidence level of the type of the detected object based on the number of clustered reflection points and the track reflection intensity of the detected object:

Acquiring the number of the clustered reflection points, and if the number of the clustered reflection points meets a second preset condition, updating the confidence coefficient;

and acquiring the track reflection intensity of the detection target, and if the track reflection intensity of the detection target meets a third preset condition, updating the confidence coefficient.

36. The apparatus of claim 35, wherein the processor is specifically configured to:

if the number of the clustered reflection points meets a second preset condition, determining that the confidence coefficient is increased by a first preset value; and/or the number of the groups of groups,

And if the number of the clustered reflection points does not meet a second preset condition, determining the confidence coefficient as an original value.

37. The apparatus of claim 34, wherein the device comprises a plurality of sensors,

The detection information comprises distance information and speed information of a reflection point of the detection target;

The meeting the first preset condition includes: the distance information is within a preset distance threshold range, and the speed information is within a preset speed information threshold range.

38. The apparatus of claim 37, wherein the velocity information is determined by acquiring doppler bins for the reflection points.

39. The apparatus of claim 35, wherein the device comprises a plurality of sensors,

The second preset condition means that the number of the clustered reflection points is greater than a preset number threshold.

40. The apparatus of claim 35, wherein the processor is configured to update the confidence level if the track reflection intensity of the detection target meets a third preset condition:

if the track reflection intensity of the detection target is larger than a first preset intensity threshold value, the confidence coefficient is increased by a first preset value; and/or the number of the groups of groups,

If the track reflection intensity of the detection target is smaller than a second preset intensity threshold value, subtracting a second preset value from the confidence coefficient; and/or the number of the groups of groups,

If the track reflection intensity of the detection target is between a first preset intensity threshold value and a second preset intensity threshold value, the confidence coefficient is an original value.

41. The apparatus of claim 40, wherein the third predetermined condition is that the track reflected intensity is greater than a predetermined reflected intensity threshold.

42. The apparatus of claim 30, wherein the processor is configured to, when determining that the detection target is of the preset type according to the confidence level of the type of the detection target:

Detecting the same detection target for multiple times;

Determining the current confidence coefficient of the detection target according to the current track reflection intensity of the detection target, the number of clustered reflection points and the last confidence coefficient of the detection target;

And determining that the detection target is of a preset type according to the current confidence.

43. The apparatus of claim 42, wherein the processor, when determining the type of the detection target based on the current confidence, is specifically configured to:

And if the current confidence coefficient is larger than a third preset value, determining that the detection target is of a preset type.

44. The apparatus of claim 30, wherein the preset type comprises at least one of: trucks, cars, buses.

45. The target detection equipment is applied to a millimeter wave radar, and is characterized in that the millimeter wave radar can acquire track reflection intensity information and the number of clustered reflection points of a detection target, and the confidence coefficient of the detection target is determined according to the track reflection intensity information and the number of clustered reflection points; the device comprises one or more processors, working together or individually, for performing the following operations:

Acquiring clustered reflection points of the detection target, and acquiring position coordinates of the clustered reflection points, wherein the position coordinates are determined based on a pre-established coordinate system; the clustering reflection points are obtained by carrying out clustering determination on the reflection points of the detection targets according to the detection information of the detection targets;

determining the length and the width of the detection target according to the position coordinates of the clustered reflection points;

acquiring the position information of the detection target; the position information of the detection target is determined according to the position coordinates of the clustered reflection points;

And determining the designated center position of the detection target according to the position information of the detection target and a preset position compensation value.

46. The apparatus of claim 45, wherein the detection information includes at least one of: and the speed information and the distance information of the reflection point of the detection target.

47. The apparatus of claim 45, wherein the position coordinates comprise lateral coordinates and longitudinal coordinates; the processor is specifically configured to, when determining the length and the width of the detection target according to the position coordinates of the clustered reflection points:

and determining the length and the width of the detection target according to the transverse coordinates and the longitudinal coordinates.

48. The apparatus of claim 47, wherein the processor is specifically configured to:

Determining the length and width of the current detection target according to the transverse coordinates and the longitudinal coordinates of the clustered reflection points;

and determining the length and the width of the detection target according to the length and the width of the current detection target and the length and the width of the last detection target.

49. The apparatus according to claim 48, wherein the processor is further configured to, when determining the length and width of the detection target based on the length and width of the detection target at the present time and the length and width of the detection target detected last time:

acquiring the length and the width obtained by detecting the detection target last time;

According to the length and width of the current detection target and the length and width of the last detection target, filtering the length and width of the detection target;

And determining the length and the width of the detection target according to the result of the filtering process.

50. The apparatus of claim 48, wherein the processor is configured to, based on the lateral and longitudinal coordinates of the clustered reflective dots, determine a length and a width of the current detection target when:

determining the width of the current detection target according to the transverse coordinates of the clustered reflection points;

And determining the length of the current detection target according to the longitudinal coordinates of the clustered reflection points.

51. The apparatus of claim 50, wherein the processor is configured to determine a width of the current detection target based on lateral coordinates of the clustered reflection points, in particular:

Obtaining the maximum value and the minimum value of the transverse coordinates of the clustered reflection points;

And determining the difference between the maximum value and the minimum value of the transverse coordinates of the clustered reflection points as the width of the current detection target.

52. The apparatus of claim 50, wherein the processor is configured to determine a length of the current detection target based on the longitudinal coordinates of the clustered reflection points, in particular:

Obtaining the maximum value and the minimum value of the longitudinal coordinates of the clustered reflection points;

And determining the difference between the maximum value and the minimum value of the longitudinal coordinates of the clustered reflection points as the length of the current detection target.

53. The apparatus of claim 47, wherein after determining the length and width of the detection target, the processor is further configured to:

Detecting whether other reflection points acquired by the millimeter wave radar meet a fourth preset condition;

If yes, adding other reflection points meeting the fourth preset condition into the current clustering reflection points, and redetermining the length and the width of the detection target according to the position coordinates of the clustering reflection points.

54. The apparatus of claim 53, wherein the satisfaction of a fourth preset condition comprises:

the difference between the longitudinal coordinates of the other reflecting points and the longitudinal coordinates of the current clustering reflecting points is larger than the current length of the detection target and smaller than a specified searching distance;

the absolute value of the difference between the transverse coordinates of the current clustered reflection points and the other reflection points is smaller than a first preset threshold value;

The speed information of the other reflection points is within a preset speed information threshold range;

and the difference between the track reflection intensity of the detection target and the reflection intensity of other reflection points is larger than the energy envelope of the detection target;

and the reflection intensity of the other reflection points is larger than a preset reflection intensity threshold value.

55. The apparatus of claim 54, wherein the device comprises,

The specified search distance is calculated according to the length of the detection target.

56. The apparatus of claim 55, wherein the specified search distance comprises a maximum length of the detection target.

57. The apparatus of claim 45, wherein after the processor determines the length and width of the detection target, the processor is further configured to:

and determining that the detection target is of a preset type according to the length and the width of the detection target.

58. The device of claim 57, wherein the preset type comprises at least one of: trucks, cars, buses.

59. A millimeter wave radar, comprising:

The antenna is used for acquiring echo signals;

a processor in communication with the antenna, the processor configured to:

Acquiring detection information of a detection target and track reflection intensity of the detection target;

Clustering the reflection points of the detection targets according to the detection information of the detection targets to generate clustered reflection points, and determining the number of the clustered reflection points;

Determining the confidence level of the type of the detection target according to the number of the clustered reflection points and the track reflection intensity of the detection target;

and determining that the detection target is of a preset type according to the confidence coefficient of the type of the detection target.

60. The millimeter wave radar of claim 59, wherein the detection information comprises at least one of: and the speed information and the distance information of the reflection point of the detection target.

61. The millimeter wave radar of claim 59, wherein the detection targets have a plurality of reflection points.

62. The millimeter wave radar of claim 59, wherein said processor, prior to obtaining detection information of a detection target and said trace reflection intensity of said detection target, is further configured to:

Detecting the detection target and recording the track of the detection target.

63. The millimeter wave radar of claim 61, wherein the processor is configured to, when clustering the reflection points of the detection target according to the detection information of the detection target:

Acquiring detection information of a plurality of reflection points of the detection target;

Detecting whether the detection information of the plurality of reflection points meets a first preset condition;

if yes, clustering the reflection points meeting the first preset condition.

64. The millimeter wave radar of claim 63, wherein the processor is configured, when determining the confidence level of the type of the detected object based on the number of clustered reflection points and the track reflection intensity of the detected object, to:

Acquiring the number of the clustered reflection points, and if the number of the clustered reflection points meets a second preset condition, updating the confidence coefficient;

and acquiring the track reflection intensity of the detection target, and if the track reflection intensity of the detection target meets a third preset condition, updating the confidence coefficient.

65. The millimeter wave radar of claim 64, wherein the processor is operable in particular to:

if the number of the clustered reflection points meets a second preset condition, determining that the confidence coefficient is increased by a first preset value; and/or the number of the groups of groups,

And if the number of the clustered reflection points does not meet a second preset condition, determining the confidence coefficient as an original value.

66. The millimeter wave radar of claim 63, wherein,

The detection information comprises distance information and speed information of a reflection point of the detection target;

The meeting the first preset condition includes: the distance information is within a preset distance threshold range, and the speed information is within a preset speed information threshold range.

67. The millimeter wave radar of claim 66, wherein said velocity information is determined by acquiring doppler bins for said reflection points.

68. The millimeter wave radar of claim 64, wherein,

The second preset condition means that the number of the clustered reflection points is greater than a preset number threshold.

69. The millimeter wave radar of claim 64, wherein the processor is configured to update the confidence level if the track reflection intensity of the detection target meets a third preset condition:

if the track reflection intensity of the detection target is larger than a first preset intensity threshold value, the confidence coefficient is increased by a first preset value; and/or the number of the groups of groups,

If the track reflection intensity of the detection target is smaller than a second preset intensity threshold value, subtracting a second preset value from the confidence coefficient; and/or the number of the groups of groups,

If the track reflection intensity of the detection target is between a first preset intensity threshold value and a second preset intensity threshold value, the confidence coefficient is an original value.

70. The millimeter wave radar of claim 69, wherein the third preset condition is that the track reflection intensity is greater than a preset reflection intensity threshold.

71. The millimeter wave radar of claim 59, wherein the processor is configured to, when determining that the detected target is of a preset type based on a confidence level of the type of the detected target:

Detecting the same detection target for multiple times;

Determining the current confidence coefficient of the detection target according to the current track reflection intensity of the detection target, the number of clustered reflection points and the last confidence coefficient of the detection target;

And determining that the detection target is of a preset type according to the current confidence.

72. The millimeter wave radar of claim 71, wherein the processor, when determining the type of detection target based on the current confidence level, is specifically configured to:

And if the current confidence coefficient is larger than a third preset value, determining that the detection target is of a preset type.

73. The millimeter wave radar of claim 59, wherein the preset type comprises at least one of: trucks, cars, buses.

74. A millimeter wave radar, comprising:

The antenna is used for acquiring echo signals;

a processor in communication with the antenna, the processor configured to:

Acquiring a clustered reflection point of a detection target, and acquiring a position coordinate of the clustered reflection point, wherein the position coordinate is determined based on a pre-established coordinate system; the clustering reflection points are obtained by carrying out clustering determination on the reflection points of the detection targets according to the detection information of the detection targets;

determining the length and the width of the detection target according to the position coordinates of the clustered reflection points;

acquiring the position information of the detection target; the position information of the detection target is determined according to the position coordinates of the clustered reflection points;

And determining the designated center position of the detection target according to the position information of the detection target and a preset position compensation value.

75. The millimeter-wave radar of claim 74, wherein the detection information comprises at least one of: and the speed information and the distance information of the reflection point of the detection target.

76. The millimeter-wave radar of claim 74, wherein said position coordinates comprise lateral coordinates and longitudinal coordinates; the processor is specifically configured to, when determining the length and the width of the detection target according to the position coordinates of the clustered reflection points:

and determining the length and the width of the detection target according to the transverse coordinates and the longitudinal coordinates.

77. The millimeter wave radar of claim 76, wherein the processor is operable in particular to:

Determining the length and width of the current detection target according to the transverse coordinates and the longitudinal coordinates of the clustered reflection points;

and determining the length and the width of the detection target according to the length and the width of the current detection target and the length and the width of the last detection target.

78. The millimeter wave radar of claim 77, wherein the processor is configured to, when determining the length and width of the detection target based on the length and width of the detection target currently and the length and width of the detection target last detected:

acquiring the length and the width obtained by detecting the detection target last time;

According to the length and width of the current detection target and the length and width of the last detection target, filtering the length and width of the detection target;

And determining the length and the width of the detection target according to the result of the filtering process.

79. The millimeter wave radar of claim 77, wherein the processor is configured to, when determining the length and width of the current detection target based on the lateral and longitudinal coordinates of the clustered reflection points:

determining the width of the current detection target according to the transverse coordinates of the clustered reflection points;

And determining the length of the current detection target according to the longitudinal coordinates of the clustered reflection points.

80. The millimeter wave radar of claim 79, wherein the processor is configured to, when determining the width of the current detection target based on the lateral coordinates of the clustered reflection points:

Obtaining the maximum value and the minimum value of the transverse coordinates of the clustered reflection points;

And determining the difference between the maximum value and the minimum value of the transverse coordinates of the clustered reflection points as the width of the current detection target.

81. The millimeter wave radar of claim 79, wherein the processor is configured to, when determining the length of the current detection target based on the longitudinal coordinates of the clustered reflection points:

Obtaining the maximum value and the minimum value of the longitudinal coordinates of the clustered reflection points;

And determining the difference between the maximum value and the minimum value of the longitudinal coordinates of the clustered reflection points as the length of the current detection target.

82. The millimeter wave radar of claim 76, wherein after the processor determines the length and width of the detection target, further configured to:

Detecting whether other reflection points acquired by the millimeter wave radar meet a fourth preset condition;

If yes, adding other reflection points meeting the fourth preset condition into the current clustering reflection points, and redetermining the length and the width of the detection target according to the position coordinates of the clustering reflection points.

83. The millimeter wave radar of claim 82, wherein the meeting a fourth preset condition comprises:

the difference between the longitudinal coordinates of the other reflecting points and the longitudinal coordinates of the current clustering reflecting points is larger than the current length of the detection target and smaller than a specified searching distance;

the absolute value of the difference between the transverse coordinates of the current clustered reflection points and the other reflection points is smaller than a first preset threshold value;

The speed information of the other reflection points is within a preset speed information threshold range;

and the difference between the track reflection intensity of the detection target and the reflection intensity of other reflection points is larger than the energy envelope of the detection target;

and the reflection intensity of the other reflection points is larger than a preset reflection intensity threshold value.

84. The millimeter wave radar of claim 83, wherein,

The specified search distance is calculated according to the length of the detection target.

85. The millimeter wave radar of claim 84, wherein the specified search distance comprises a maximum length of the detection target.

86. The millimeter-wave radar of claim 74, wherein after the processor determines the length and width of the detection target, further configured to:

and determining that the detection target is of a preset type according to the length and the width of the detection target.

87. The millimeter wave radar of claim 86, wherein the preset type comprises at least one of: trucks, cars, buses.

88. A movable platform, comprising:

A body;

The power system is arranged on the movable platform and is used for providing moving power for the movable platform;

the apparatus of any one of claims 30-58.

89. A computer readable storage medium storing a computer program, which when executed by a processor performs the method of any one of claims 1 to 29.