CN112712040B - Method, device, equipment and storage medium for calibrating lane marking information based on radar - Google Patents

Abstract

The application discloses a method, a device, equipment and a storage medium for calibrating lane line information based on a radar, wherein the method comprises the following steps: acquiring static target information on two sides of a road through radar equipment installed on a vehicle; clustering the static target information, and performing curve fitting on the classified clusters; and performing feature matching on the fitted curve and the lane line information identified by the camera, if the matching is successful, executing a normal vehicle control instruction, and if the matching is unsuccessful, calibrating the lane line information according to the fitted curve. According to the method for calibrating the lane line information, the millimeter wave radar is adopted to extract the road information, and the road information can be mutually checked with the lane line information identified by the camera under the condition that a system sensor is not added, so that the accuracy rate of lane line identification is greatly improved.

Description

Method, device, equipment and storage medium for calibrating lane line information based on radar

technical field

The present invention relates to the technical field of smart cars, in particular to a method, device, equipment and storage medium for calibrating lane line information based on radar.

Background technique

Accurately identifying the lane line information of the road is an important technical issue in the field of intelligent driving vehicles. At present, LKA (Lane Keeping Assistance) is mainly based on a single-camera solution. The single-camera on the vehicle recognizes the lane line, and finally calculates the deviation between the vehicle and the center of the lane. By controlling the steering, the deviation is reduced to achieve the centering of the vehicle. purpose of driving. However, this function only relies on a single forward-facing camera to perceive lane information. Blurred and damaged lane lines on the actual road will cause great interference to the camera, and sometimes misidentification will occur, which will cause great danger in high-speed situations. There is also a solution based on dual-camera recognition. The dual-camera not only increases the cost, but also recognizes lane line information. If the lane line is damaged, the detection of the two cameras will not be accurate, so the two cameras cannot be very good. for redundant design.

Contents of the invention

Embodiments of the present disclosure provide a method, device, device and storage medium for calibrating lane line information based on radar. In order to provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is presented below. This summary is not an overview, nor is it intended to identify key/critical elements or delineate the scope of these embodiments. Its sole purpose is to present some concepts in a simplified form as a prelude to the more detailed description that is presented later.

In a first aspect, an embodiment of the present disclosure provides a method for calibrating lane line information based on radar, including:

Obtain stationary target information on both sides of the road through the radar equipment installed on the vehicle;

Cluster the stationary target information and perform curve fitting on the classified clusters;

Match the fitted curve with the lane line information identified by the camera. If the match is successful, execute the normal vehicle control command. If the match is unsuccessful, calibrate the lane line information according to the fitted curve.

In one embodiment, before obtaining the stationary target information on both sides of the road through the radar equipment installed on the vehicle, it also includes:

Obtain the lane line information recognized by the vehicle camera and the confidence level information of the lane line.

In one embodiment, after obtaining the lane line information identified by the vehicle camera and the confidence information of the lane line, it further includes:

Determine the road type according to the lane line information;

If the road type is a straight road, the lane line information is not calibrated, and the vehicle control command is directly executed;

If the road type is a curved road, the stationary target information on both sides of the road is acquired through the radar equipment installed on the vehicle.

In one embodiment, the stationary target information is clustered, and the classified clusters are subjected to curve fitting, including:

Clustering of stationary target information by clustering algorithm based on density growth;

Curve fitting is performed on each cluster after classification to obtain the fitted cubic function curve.

In one embodiment, after performing curve fitting on the classified clusters, further comprising:

Determine the confidence of the fitting curve according to the distance between the vehicle and the fitting curve and the number of stationary objects in the cluster where the fitting curve is located;

When the confidence level is greater than or equal to the preset first threshold, the fitted curve is matched with the lane line information identified by the camera. If the matching is successful, the normal vehicle control command will be executed. If the matching is unsuccessful, according to the fitted The curve calibration lane line information;

When the confidence level is less than the preset first threshold, the obstacle information output by the radar and the camera is extracted, and the trajectory of the vehicle is determined according to the control instruction to be executed. If there is no obstacle in the trajectory within the preset time period, the control instruction is executed. , otherwise it will not be executed and an alarm message will be issued.

In one embodiment, feature matching is performed on the fitted curve with the lane line information identified by the camera, including:

Determine the first curvature and first curvature change rate of the road according to the lane line information identified by the camera;

determining the second curvature and the second curvature change rate of the road according to the fitted curve;

If the difference between the first curvature and the second curvature is smaller than a preset second threshold and the difference between the first curvature change rate and the second curvature change rate is smaller than a preset third threshold, it is determined that the matching is successful.

In one embodiment, the lane marking information is calibrated according to the fitted curve, including:

Obtain the confidence of the fitted curve and the confidence of the lane line identified by the camera;

According to the confidence of the two, the feature information of the lane line is corrected by means of weighted average.

In a second aspect, an embodiment of the present disclosure provides a device for calibrating lane line information based on radar, including:

An acquisition module, configured to acquire stationary target information on both sides of the road through the radar equipment installed on the vehicle;

A curve fitting module is used for clustering stationary target information and performing curve fitting on the classified clusters;

The calibration module is used to perform feature matching between the fitted curve and the lane line information recognized by the camera. If the matching is successful, normal vehicle control instructions will be executed. If the matching is unsuccessful, the lane line information will be calibrated according to the fitted curve.

In a third aspect, an embodiment of the present disclosure provides a device for calibrating lane line information based on radar, including a processor and a memory storing program instructions. A method for radar calibration of lane line information.

In a fourth aspect, an embodiment of the present disclosure provides a computer-readable medium on which computer-readable instructions are stored, and the computer-readable instructions can be executed by a processor to implement the radar-based calibration lane line information provided by the above-mentioned embodiments. Methods.

The technical solutions provided by the embodiments of the present disclosure may include the following beneficial effects:

According to the method for calibrating lane line information provided by the embodiments of the present disclosure, millimeter-wave radar is used to extract stationary target information on both sides of the road, road guardrails, trees and other information are used to extract road features, and the lane line information identified by the camera is mutually verified. By using different road information for verification, the accuracy of the verification and the security of the system are greatly improved. The problem of inaccurate lane line recognition. Moreover, the methods in the embodiments of the present disclosure do not increase system sensors, which reduces costs.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention.

Description of drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description serve to explain the principles of the invention.

Fig. 1 is a schematic flowchart of a method for calibrating lane line information based on radar according to an exemplary embodiment;

Fig. 2 is a schematic flowchart of a method for calibrating lane line information based on radar according to an exemplary embodiment;

Fig. 3 is a schematic diagram showing clustering of stationary objects according to an exemplary embodiment;

Fig. 4 is a schematic diagram of performing curve fitting on clustered clusters according to an exemplary embodiment;

Fig. 5 is a schematic structural diagram of a device for calibrating lane line information based on radar according to an exemplary embodiment;

Fig. 6 is a schematic structural diagram of a device for calibrating lane line information based on radar according to an exemplary embodiment;

Fig. 7 is a schematic diagram of a computer storage medium according to an exemplary embodiment.

Detailed ways

The following description and drawings illustrate specific embodiments of the invention sufficiently to enable those skilled in the art to practice them.

It should be clear that the described embodiments are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

When the following description refers to the accompanying drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the present invention. Rather, they are merely examples of systems and methods consistent with aspects of the invention as recited in the appended claims.

In the description of the present invention, it should be understood that the terms "first", "second" and so on are used for descriptive purposes only, and cannot be interpreted as indicating or implying relative importance. Those of ordinary skill in the art can understand the specific meanings of the above terms in the present invention in specific situations. In addition, in the description of the present invention, unless otherwise specified, "plurality" means two or more. "And/or" describes the association relationship of associated objects, indicating that there may be three types of relationships, for example, A and/or B may indicate: A exists alone, A and B exist simultaneously, and B exists independently. The character "/" generally indicates that the contextual objects are an "or" relationship.

The embodiment of the present disclosure provides a method for assisting the verification camera to detect lane lines. The vehicle's forward millimeter-wave radar is used to extract the information of stationary targets on both sides of the road, and the stationary targets are fitted into a cubic equation according to the extracted information. Through this equation To verify the lane line information identified by the camera, if the two can match, the system is allowed to control the vehicle at a large angle, otherwise it is only allowed to control the vehicle in a small range. The millimeter-wave radar is used to extract road information, and it can be mutually verified with the camera without adding sensors, which greatly improves the security of the system and solves the functional safety bottleneck of the system in terms of sensors.

The method for calibrating lane line information based on radar provided in the embodiment of the present application will be described in detail below in conjunction with accompanying drawings 1-4. Referring to FIG. 1, the method specifically includes the following steps:

S101 Obtain information of stationary targets on both sides of the road through the radar equipment installed on the vehicle.

In a possible implementation, before step S101 is executed, it also includes obtaining the lane line information recognized by the forward camera installed on the vehicle. In the prior art, the recognized lane line information can be output by the camera installed on the vehicle. and the confidence of the lane line.

Further, the road type is judged according to the identified lane lines, for example, the curvature of the road is calculated according to the identified lane line information, the greater the curvature, the more curved the road is, and when the road curvature is greater than the preset curvature threshold, it is determined that the road is a curved road , the curvature threshold in the embodiments of the present disclosure can be set by those skilled in the art.

If the determined road type is a straight road, it means that the road condition is simple, and there is no need to further verify the road route information, and the control command of the vehicle is directly executed. If the determined road type is a curved road, it means that the road conditions are more complicated. In order to improve the accuracy of road line information recognition, the radar equipment on the vehicle is introduced to further verify the lane line information.

Specifically, the information on both sides of the road can be obtained through the millimeter-wave radar equipment installed on the vehicle, and then the stationary target information on both sides of the road can be extracted from the data captured by the millimeter-wave radar, including information on trees planted on both sides of the road, information on guardrails on both sides of the road, Street light information on both sides of the road, etc.

In this step, the system cost is greatly reduced by using the millimeter-wave radar on the vehicle to obtain the stationary target information on both sides of the road, and the road information is extracted from different directions, showing the multi-dimensionality of the information.

S102 clustering the stationary target information, and performing curve fitting on the classified clusters.

In order to determine road features based on the extracted stationary object information, the stationary object information is clustered first. In a possible implementation, the stationary target information is clustered through a clustering algorithm based on density growth. Commonly used clustering algorithms usually need to specify the number of clusters to be clustered. However, in this application scenario, due to the environmental The number of complex and stationary targets is unknown, so the clustering algorithm to determine the number of clusters is not applicable. In a possible implementation, according to the DBSCAN clustering algorithm, OPTICS clustering algorithm, DENCLUE clustering algorithm and the concept of region growth, starting from a seed point, processing points within a certain spatial radius will meet the requirements The points are included in the same cluster, and the points that do not meet the requirements are discarded. Get the stationary target cluster after clustering.

Fig. 3 is a schematic diagram of clustering stationary objects according to an exemplary embodiment. As shown in Fig. 3, the left half is to cluster stationary objects on both sides of a straight road, and two clusters can be obtained after clustering, are located on both sides of the road. The right half is to cluster the stationary targets on both sides of the curved road. Through clustering, two clusters located on both sides of the road can be obtained.

Further, in order to conveniently represent road information, curve fitting is performed on each classified cluster to obtain a fitted cubic function curve. Fig. 4 is a schematic diagram of curve fitting for clustered clusters according to an exemplary embodiment. As shown in Fig. 4, the two thick vertical lines in the left half are the fitted curves, and the right Half of the curved thick line is also a fitted curve. The fitted curve is a cubic function curve, expressed by the equation ax ³ +bx ² +cx+d=0. By solving the equation, the fitted curve can be obtained information about the curve.

S103 performs feature matching on the fitted curve and the lane marking information recognized by the camera. If the matching is successful, normal vehicle control instructions are executed. If the matching is unsuccessful, the lane marking information is calibrated according to the fitted curve.

In one embodiment, after performing curve fitting on the classified clusters, it also includes determining the confidence of the fitting curve according to the distance between the vehicle and the fitting curve and the number of stationary objects in the cluster where the fitting curve is located, specifically , the closer the distance between the vehicle and the fitting curve is, and the more stationary targets are in the cluster where the fitting curve is located, the higher the confidence of the fitting curve is, and the higher the confidence, it means that it can accurately represent actual characteristics of the road.

Further, the relationship between the confidence degree of the fitting curve and the preset first threshold value is judged, wherein the preset first threshold value can be set by those skilled in the art by themselves, and the embodiment of the present disclosure does not specifically limit it. When the confidence level is less than the preset first threshold, it indicates that the fitting curve has a relatively low reliability. At this time, the lane line information is not calibrated through the fitting curve. Instead, it extracts the obstacle information output by the radar and the camera, and previews the trajectory of the vehicle according to the turning control command to be executed. If there is no obstacle in the trajectory within the preset time period, the turning control command is executed, otherwise it is not executed. And send an alarm message to notify the driver.

When the confidence level is greater than or equal to the preset first threshold, the fitted curve is matched with the lane line information identified by the camera, and if the matching is successful, normal vehicle control instructions are executed. If the matching is unsuccessful, the lane line information is calibrated according to the fitted curve.

Specifically, if the confidence of the fitted curve reaches a threshold, it means that the fitted curve has a high degree of confidence. At this time, the lane marking information can be further calibrated according to the fitted curve information. Select a fitting curve with the highest confidence on both sides of the road, calculate the second curvature and second curvature change rate of the curve, and then calculate the first curvature and first curvature change rate of the road based on the lane line information recognized by the camera Information, match the road features determined by the two methods, calculate the difference between the first curvature and the second curvature, and calculate the difference between the first curvature change rate and the second curvature change rate, if the first curvature and the second curvature The curvature difference is less than the preset second threshold and the difference between the first curvature change rate and the second curvature change rate is less than the preset third threshold, indicating that the difference is within the preset range, and the lane information identified by the two methods is similar , road feature matching. Wherein, the second threshold and the third threshold are a difference range, which can be set by those skilled in the art.

If the road characteristics match, normal vehicle control commands can be executed, and large-angle steering control can be performed on the vehicle. If the road features do not match, the lane line information recognized by the camera can be corrected according to the fitting curve information. Take the result of the fusion of the two to control the vehicle.

In a possible implementation manner, the confidence of the fitted curve and the confidence of the lane line recognized by the camera are obtained, and the characteristic information of the lane line is corrected by means of a weighted average according to the confidence of the two. For example, the road curvature calculated according to the fitting curve is 0.8, the confidence of the fitting curve is 0.7, the road curvature calculated according to the lane line recognized by the camera is 0.4, and the confidence degree of the lane line recognized by the camera is 0.3, then The fused road curvature is 0.8*0.7+0.4*0.3=0.68, so the final road curvature is 0.68.

Take the result of the fusion of the two to control the vehicle, for example, judge the distance between the vehicle and the lane lines on both sides through the distance from the vehicle to the lane line, road curvature, road curvature change rate, etc., and finally calculate the distance between the vehicle and the center of the lane Deviation, by controlling the steering to reduce this deviation to achieve the purpose of the vehicle driving in the center.

According to this method, mutual verification can be carried out, using different sensors to detect different characteristics of the road, and extracting lane line information. From the perspective of functional safety, this is a mutually independent system, and its mutual verification can maximize the accuracy of inspection sex.

In order to facilitate understanding of the lane line calibration method provided by the embodiment of the present application, the following description will be made in conjunction with FIG. 2 . As shown in Figure 2, the method mainly includes the following steps:

First, obtain the lane line information identified by the vehicle through the camera, and classify the road type according to the lane line information. If the road type is a straight road, the vehicle's control command will be directly executed. If the road type is a curved road, it will be obtained through the millimeter wave radar on the vehicle Data on both sides of the road. Lane lines are calibrated based on data extracted from millimeter wave radar.

Specifically, the millimeter-wave radar is used to obtain the stationary target information on both sides of the road, the stationary target information is clustered through the clustering algorithm based on density growth, and the curve fitting is performed on each cluster after classification to obtain the fitted cubic function curve. Determine the confidence degree of the fitting curve according to the distance between the vehicle and the fitting curve and the number of stationary objects in the cluster where the fitting curve is located. When the confidence degree is less than the preset first threshold, analyze the obstacle and the preview trajectory, and extract The obstacle information output by the radar and the camera determines the trajectory of the vehicle according to the control command to be executed. If there is no obstacle in the trajectory within the preset time period, the control command will be executed, otherwise it will not be executed and an alarm message will be issued.

When the confidence is greater than or equal to the preset first threshold, the fitted curve is matched with the lane line information identified by the camera. If the matching is successful, the normal vehicle control command will be executed. If the matching is unsuccessful, the fitting will be obtained. The confidence of the curve and the confidence of the lane line recognized by the camera, according to the confidence of the two, the characteristic information of the lane line is corrected by weighted average, and the vehicle is controlled according to the fused data.

According to the method for calibrating lane line information provided by the embodiments of the present disclosure, millimeter-wave radar is used to extract stationary target information on both sides of the road, road guardrails, trees and other information are used to extract road features, and the lane line information identified by the camera is mutually verified. By using different road information for verification, the accuracy of the verification and the security of the system are greatly improved. The problem of inaccurate lane line recognition. Moreover, the methods in the embodiments of the present disclosure do not increase system sensors, which reduces costs.

An embodiment of the present disclosure also provides a device for calibrating lane line information based on radar, which is used to implement the method for calibrating lane line information based on radar in the above embodiment, as shown in FIG. 5 , the device includes:

An acquisition module 501, configured to acquire stationary target information on both sides of the road through radar equipment installed on the vehicle;

The curve fitting module 502 is used for clustering the stationary target information, and performing curve fitting on the classified clusters;

The calibration module 503 is used to perform feature matching on the fitted curve and the lane line information identified by the camera. If the matching is successful, execute normal vehicle control instructions. If the matching is unsuccessful, calibrate the lane line information according to the fitted curve .

It should be noted that when the device for calibrating lane line information based on radar provided in the above-mentioned embodiments executes the method for calibrating lane line information based on radar, it only uses the division of the above-mentioned functional modules as an example for illustration. The above function allocation is completed by different functional modules, that is, the internal structure of the device is divided into different functional modules, so as to complete all or part of the functions described above. In addition, the device for calibrating lane line information based on radar and the method embodiment for calibrating lane line information based on radar provided in the above embodiments belong to the same concept, and the implementation process thereof is detailed in the method embodiment, and will not be repeated here.

Embodiments of the present disclosure further provide an electronic device corresponding to the method for calibrating lane line information based on radar provided in the foregoing embodiments, so as to execute the method for calibrating lane line information based on radar.

Please refer to FIG. 6 , which shows a schematic diagram of an electronic device provided by some embodiments of the present application. As shown in Figure 6, the electronic equipment includes: processor 600, memory 601, bus 602 and communication interface 603, processor 600, communication interface 603 and memory 601 are connected by bus 602; Running computer program, the processor 600 executes the method for calibrating lane line information based on radar provided in any one of the foregoing embodiments of the present application when running the computer program.

Wherein, the memory 601 may include a high-speed random access memory (RAM: Random Access Memory), and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 603 (which may be wired or wireless), and the Internet, wide area network, local network, metropolitan area network, etc. can be used.

The bus 602 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus can be divided into address bus, data bus, control bus and so on. Wherein, the memory 601 is used to store the program, and the processor 600 executes the program after receiving the execution instruction. The method for calibrating lane line information based on radar disclosed in any of the above-mentioned embodiments of the present application can be applied to the processor 600, or implemented by the processor 600.

The processor 600 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method may be implemented by an integrated logic circuit of hardware in the processor 600 or an instruction in the form of software. The above-mentioned processor 600 can be a general-purpose processor, including a central processing unit (Central Processing Unit, referred to as CPU), a network processor (Network Processor, referred to as NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), off-the-shelf programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. Various methods, steps, and logic block diagrams disclosed in the embodiments of the present application may be implemented or executed. A general-purpose processor may be a microprocessor, or the processor may be any conventional processor, or the like. The steps of the method disclosed in connection with the embodiments of the present application may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module can be located in a mature storage medium in the field such as random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, register. The storage medium is located in the memory 601, and the processor 600 reads the information in the memory 601, and completes the steps of the above method in combination with its hardware.

The electronic device provided in the embodiment of the present application is based on the same inventive concept as the method for calibrating lane line information based on radar provided in the embodiment of the present application, and has the same beneficial effect as the method adopted, operated or implemented.

The embodiment of the present application also provides a computer-readable storage medium corresponding to the method for calibrating lane line information based on radar provided in the foregoing embodiments, please refer to FIG. 7 , the computer-readable storage medium shown is an optical disc 700, which A computer program (that is, a program product) is stored on the computer, and when the computer program is run by the processor, it will execute the method for calibrating lane line information based on radar provided in any of the foregoing embodiments.

It should be noted that examples of computer-readable storage media may also include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access Memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical and magnetic storage media will not be repeated here.

The computer-readable storage medium provided by the above-mentioned embodiments of the present application is based on the same inventive concept as the method for calibrating lane line information based on radar provided by the embodiments of the present application, and has the same method adopted, run or implemented by its stored application program beneficial effect.

The technical features of the above embodiments can be combined arbitrarily. To make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be It is considered to be within the range described in this specification.

The above examples only express several implementations of the present invention, and the description thereof is relatively specific and detailed, but should not be construed as limiting the patent scope of the present invention. It should be noted that, for those skilled in the art, several modifications and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent for the present invention should be based on the appended claims.

Claims (8)

1. A method for calibrating lane line information based on radar, characterized in that, comprising: Obtain stationary target information on both sides of the road through the radar equipment installed on the vehicle; Clustering the stationary target information, and performing curve fitting on the classified clusters; determining the confidence of the fitting curve according to the distance between the vehicle and the fitting curve and the number of stationary targets in the cluster where the fitting curve is located; When the confidence level is greater than or equal to the preset first threshold, feature matching is performed on the fitted curve with the lane line information identified by the camera. If the matching is successful, normal vehicle control instructions are executed; The combined curve calibrates the lane line information, including obtaining the confidence of the fitted curve and the confidence of the lane line identified by the camera; according to the confidence of the two, the feature information of the lane line is calculated in a weighted average manner make corrections; When the confidence level is less than the preset first threshold, the obstacle information output by the radar and the camera is extracted, and the track to be driven by the vehicle is determined according to the control command to be executed. If there is no obstacle in the track within the preset time period, Then execute the control instruction, otherwise it will not execute and send out an alarm message. 2. The method according to claim 1, wherein, before obtaining the stationary target information on both sides of the road through the radar equipment installed on the vehicle, it also includes: The lane line information recognized by the vehicle camera and the confidence level information of the lane line are acquired. 3. The method according to claim 2, characterized in that after acquiring the lane line information identified by the vehicle camera and the confidence level information of the lane line, further comprising: judging the road type according to the lane line information; If the road type is a straight road, the vehicle control instruction is directly executed without calibrating the lane line information; If the road type is a curved road, the stationary target information on both sides of the road is acquired through the radar equipment installed on the vehicle. 4. The method according to claim 1, wherein clustering the stationary target information and performing curve fitting on the classified clusters includes: clustering the stationary target information through a clustering algorithm based on density growth; Curve fitting is performed on each cluster after classification to obtain the fitted cubic function curve. 5. The method according to claim 1, characterized in that, performing feature matching on the fitted curve and the lane line information identified by the camera, comprising: Determine the first curvature and first curvature change rate of the road according to the lane line information identified by the camera; determining the second curvature and the second curvature change rate of the road according to the fitted curve; If the difference between the first curvature and the second curvature is smaller than a preset second threshold and the difference between the first curvature change rate and the second curvature change rate is smaller than a preset third threshold, it is determined that the matching is successful. 6. A device for calibrating lane line information based on radar, characterized in that it comprises: An acquisition module, configured to acquire stationary target information on both sides of the road through the radar equipment installed on the vehicle; A curve fitting module, configured to cluster the stationary target information and perform curve fitting on the classified clusters; The calibration module is used to determine the confidence of the fitting curve according to the distance between the vehicle and the fitting curve and the number of stationary targets in the cluster where the fitting curve is located; when the confidence is greater than or equal to the preset first threshold, the fitting curve will be Perform feature matching on the combined curve and the lane line information identified by the camera. If the matching is successful, normal vehicle control instructions are executed. If the matching is unsuccessful, the lane line information is calibrated according to the fitted curve, including obtaining the proposed The confidence degree of the composite curve and the confidence degree of the lane line recognized by the camera; according to the confidence degree of the two, the characteristic information of the lane line is corrected by means of a weighted average; When the confidence level is less than the preset first threshold, the obstacle information output by the radar and the camera is extracted, and the track to be driven by the vehicle is determined according to the control command to be executed. If there is no obstacle in the track within the preset time period, Then execute the control instruction, otherwise it will not execute and send out an alarm message. 7. A device for calibrating lane line information based on radar, characterized in that it includes a processor and a memory storing program instructions, the processor is configured to execute the program as claimed in claims 1 to 5 when executing the program instructions. The method for calibrating lane line information based on radar according to any one of them. 8. A computer-readable medium, characterized in that computer-readable instructions are stored thereon, and the computer-readable instructions can be executed by a processor to implement a method based on any one of claims 1 to 5. A method for radar calibration of lane line information.