CN112950999A - Automobile early warning method and device, electronic equipment and storage medium - Google Patents
Automobile early warning method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112950999A CN112950999A CN202110227650.XA CN202110227650A CN112950999A CN 112950999 A CN112950999 A CN 112950999A CN 202110227650 A CN202110227650 A CN 202110227650A CN 112950999 A CN112950999 A CN 112950999A
- Authority
- CN
- China
- Prior art keywords
- automobile
- track
- vehicle
- early warning
- coming
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000013507 mapping Methods 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 7
- 230000002441 reversible effect Effects 0.000 claims description 3
- 230000006870 function Effects 0.000 description 14
- 238000010586 diagram Methods 0.000 description 11
- 238000001514 detection method Methods 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000003111 delayed effect Effects 0.000 description 2
- 238000002592 echocardiography Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000001154 acute effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000001427 coherent effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/166—Anti-collision systems for active traffic, e.g. moving vehicles, pedestrians, bikes
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/168—Driving aids for parking, e.g. acoustic or visual feedback on parking space
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The application provides an automobile early warning method, an automobile early warning device, electronic equipment and a storage medium, wherein the method comprises the following steps: when detecting that a coming vehicle exists at the side rear part of the automobile, acquiring a running track of the coming vehicle; correcting the driving track according to the included angle between the parking space corresponding to the automobile and the automobile to obtain the corrected driving track; and acquiring a reversing track of the automobile, and performing early warning according to the reversing track and the corrected running track. In the implementation process, the change of the attitude information of the automobile leads to the error of the running track of the vehicle coming from the side and the rear, which is acquired by the radar system, and the running track of the vehicle coming from the side and the rear is corrected, so that the error is reduced, and the accuracy of the rear transverse vehicle-coming early warning of the automobile is effectively improved.
Description
Technical Field
The application relates to the technical field of rear transverse incoming vehicle early warning, in particular to an automobile early warning method and device, electronic equipment and a storage medium.
Background
Rear Cross Traffic Alert (RCTA) is a driver assistance function used to warn the driver of the incoming Traffic on both sides and behind when backing a car. RCTA is supplementary to blind area safety assistance, mainly used for detecting vehicles; smaller objects, such as riders and pedestrians, may also be detected under favorable conditions.
When the current RCTA is used in actual work, the driver finds that the accuracy of the current RCTA function early warning of the automobile is not high when the driver backs the automobile in a garage (namely, the automobile is obliquely stopped to a specified parking space) at a certain included angle between the automobile body and the parking space, sometimes early warning is performed for several seconds, sometimes early warning is delayed for several seconds, and the risk that the automobile collides with a vehicle coming from the side rear part when backing the automobile exists.
Disclosure of Invention
The embodiment of the application aims to provide an automobile early warning method, an automobile early warning device, electronic equipment and a storage medium, which are used for solving the problem that the accuracy of automobile RCTA function early warning is not high.
The embodiment of the application provides an automobile early warning method, which comprises the following steps: when detecting that a coming vehicle exists at the side rear part of the automobile, acquiring a running track of the coming vehicle; correcting the driving track according to the included angle between the parking space corresponding to the automobile and the automobile to obtain the corrected driving track; and acquiring a reversing track of the automobile, and performing early warning according to the reversing track and the corrected running track. In the implementation process, the driving track of the vehicle coming from the side rear part is corrected according to the included angle between the parking space corresponding to the vehicle and the vehicle, and early warning is performed according to the backing track of the vehicle and the corrected driving track, so that the problem that the driving track of the vehicle coming from the side rear part, which is acquired by a radar system, has an error due to the change of the posture information of the vehicle when the vehicle obliquely stops to the specified parking space is avoided, the driving track of the vehicle coming from the side rear part is corrected, the error is reduced, and the accuracy of the RCTA function early warning of the vehicle is effectively improved.
Optionally, in this embodiment of the present application, acquiring a driving track of an incoming vehicle includes: detecting a position point of an incoming vehicle by using a radar system of the vehicle to obtain a plurality of position points; and fitting the plurality of position points to obtain the driving track of the coming vehicle. In the implementation process, the position points of the coming vehicle detected by the radar system of the vehicle are fitted, so that the problem that the driving track is not accurate to predict according to a single position point and speed is solved, and the accuracy of the fitted driving track is effectively improved.
Optionally, in this embodiment of the present application, before fitting the plurality of position points, the method further includes: judging whether each position point in the plurality of position points is a clutter point or not; if yes, deleting the position point from the plurality of position points. In the implementation process, the clutter points are deleted from the plurality of position points, and then the position points after the clutter points are deleted are fitted, so that the problem that the clutter points interfere the plurality of position points to fit the track is solved, and the accuracy of the fitted running track is effectively improved.
Optionally, in an embodiment of the present application, fitting a plurality of position points includes: performing straight line fitting on every two adjacent position points of the plurality of position points; alternatively, a curve fit is performed for a plurality of location points.
Optionally, in this embodiment of the application, correcting the driving track according to an included angle between a parking space corresponding to the vehicle and the vehicle includes: and (5) performing deflection correction on the running track by taking the included angle as a deflection angle value. In the implementation process, the included angle is used as the deflection angle value to perform deflection correction on the driving track, so that the problem that the acquired driving track of the coming vehicle has errors due to the change of the posture information of the vehicle is solved, and the accuracy of acquiring the driving track is effectively improved.
Optionally, in this embodiment of the present application, after performing the yaw correction on the driving trajectory, the method further includes: acquiring a historical track of a passing vehicle behind the automobile, wherein the historical track comprises: historical predicted trajectories and historical true trajectories; and extracting a mapping relation between the historical predicted track and the historical real track, and correcting the running track according to the mapping relation. In the implementation process, the driving track is corrected according to the mapping relation between the historical predicted track and the historical real track, so that the image of the historical track acquired by the automobile is fully utilized, and the accuracy of acquiring the driving track is effectively improved.
Optionally, in this embodiment of the application, performing early warning according to the reversing trajectory and the corrected driving trajectory includes: calculating the collision probability of the automobile and the coming automobile according to the reversing track and the corrected running track; and if the collision probability is greater than a preset threshold value, generating and outputting an early warning signal. In the implementation process, the early warning signal is output according to the collision probability calculated according to the backing track and the corrected running track, so that the problem that the early warning signal is sent out in a delayed mode due to the fact that the running track of the coming vehicle has errors is solved, and the accuracy rate of sending the early warning signal is effectively improved.
The embodiment of the application further provides an automobile early warning device, including: the driving track acquiring module is used for acquiring the driving track of the coming vehicle when the coming vehicle is detected to be in the lateral rear of the vehicle; the driving track correction module is used for correcting the driving track according to an included angle between a parking space corresponding to the automobile and the automobile to obtain a corrected driving track; and the driving track early warning module is used for acquiring the backing track of the automobile and carrying out early warning according to the backing track and the corrected driving track.
Optionally, in an embodiment of the present application, the driving track obtaining module includes: the system comprises an incoming vehicle position detection module, a data processing module and a data processing module, wherein the incoming vehicle position detection module is used for detecting the position points of an incoming vehicle by using a radar system of an automobile to obtain a plurality of position points; and the vehicle-coming track fitting module is used for fitting the plurality of position points to obtain the driving track of the coming vehicle.
Optionally, in an embodiment of the present application, the driving track obtaining module further includes: the clutter position judging module is used for judging whether each position point in the plurality of position points is a clutter point; and the clutter position deleting module is used for deleting the position point from the plurality of position points if the position point is a clutter point.
Optionally, in this embodiment of the present application, the incoming vehicle trajectory fitting module includes: the position point fitting module is used for performing straight line fitting on every two adjacent position points of the plurality of position points; alternatively, a curve fit is performed for a plurality of location points.
Optionally, in an embodiment of the present application, the driving track correction module includes: and the included angle deflection correction module is used for carrying out deflection correction on the running track by taking the included angle as a deflection angle value.
Optionally, in an embodiment of the present application, the driving track correction module further includes: the historical track acquisition module is used for acquiring the historical track of the passing vehicle behind the automobile, and the historical track comprises: historical predicted trajectories and historical true trajectories; and the mapping relation correction module is used for extracting the mapping relation between the historical predicted track and the historical real track and correcting the driving track according to the mapping relation.
Optionally, in this embodiment of the present application, the driving track early warning module includes: the collision probability calculation module is used for calculating the collision probability of the automobile and the coming automobile according to the reversing track and the corrected running track; and the early warning signal output module is used for generating and outputting an early warning signal if the collision probability is greater than a preset threshold value.
An embodiment of the present application further provides an electronic device, including: a processor and a memory, the memory storing processor-executable machine-readable instructions, the machine-readable instructions when executed by the processor performing the method as described above.
Embodiments of the present application also provide a storage medium having a computer program stored thereon, where the computer program is executed by a processor to perform the method as described above.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and that those skilled in the art can also obtain other related drawings based on the drawings without inventive efforts.
Fig. 1 is a schematic flow chart of a vehicle warning method provided in an embodiment of the present application;
FIG. 2 is a schematic diagram illustrating a driving track of an incoming vehicle according to an embodiment of the present application;
FIG. 3 is a schematic diagram of detection using a radar system provided by an embodiment of the present application;
FIG. 4 is a schematic diagram illustrating a method for calculating a collision probability between an automobile and an incoming automobile according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of an automobile early warning device provided in an embodiment of the present application.
Detailed Description
The technical solution in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application.
Before introducing the automobile early warning method provided by the embodiment of the application, some concepts related in the embodiment of the application are introduced:
clutter is a term of art in the radar industry, and refers to unwanted sources of reflections that are generated in the effective bandwidth and radar search window and appear as spatially coherent reflectors, the definition of clutter being largely dependent on the desired target. Radar clutter refers to radar scattered echoes of objects other than the target of interest, which can interfere with the normal operation of the radar.
Straight line fitting is one form of curve fitting. Let x and y both be the quantities observed, and y be a function of x: and y is f (x; b), the curve fitting is to find the optimal estimated value of the parameter b through the observed values of x and y, and to find the optimal theoretical curve y is f (x; b). When the function y is a linear function of i with respect to b, such a curve fit is said to be a straight line fit.
It should be noted that the vehicle early warning method provided in the embodiment of the present application may be executed by an electronic device, where the electronic device refers to a device terminal having a function of executing a computer program on a vehicle, and the device terminal includes: a Central Processing Unit (CPU) or a main control board on the automobile.
Before introducing the automobile early warning method provided by the embodiment of the application, an application scenario applicable to the automobile early warning method is introduced, where the application scenario includes but is not limited to: the automobile early warning method is used for enhancing the rear transverse incoming vehicle early warning (RCTA) function of a vehicle, wherein the vehicle comprises the following components: cars, vans, and drones, among others.
Please refer to fig. 1, which illustrates a flow diagram of an automobile early warning method provided in the embodiment of the present application; the automobile early warning method has the main ideas that the running track of a side rear coming automobile is corrected according to the included angle between the parking space corresponding to the automobile and the automobile, and early warning is carried out according to the backing track and the corrected running track of the automobile, so that the problem that the running track of the side rear coming automobile obtained by a radar system has an error due to the change of the posture information of the automobile when the automobile is obliquely stopped to a specified parking space is avoided, the running track of the side rear coming automobile is corrected, the error is reduced, and the accuracy of the RCTA function early warning of the automobile is effectively improved; the automobile early warning method comprises the following steps:
step S110: when the fact that an automobile arrives at the side rear part of the automobile is detected, the driving track of the automobile is obtained.
Please refer to fig. 2, which illustrates a schematic diagram of obtaining a driving track of an incoming vehicle according to an embodiment of the present application; for convenience of understanding and explanation, the drawings only show the motor vehicle passing by from the side to the rear of the vehicle, and actually, the coming vehicle may be a motor vehicle, a tricycle, a motorcycle, a battery car, and the like. It will be appreciated that the millimeter wave radar system may be mounted at the rear of the rear seat of the vehicle, thereby increasing the area of the radar to monitor the side and rear. Furthermore, in order to increase the accuracy of the driving track, cameras for shooting the rear parts of the two sides of the automobile can be arranged on rearview mirrors on the two sides of the automobile, cameras for shooting the rear parts of the two sides of the automobile can be arranged on a rear windscreen wiper, and the accuracy of obtaining the driving track of the coming automobile is further improved through videos shot by the cameras. As shown in fig. 2, during the process of backing up the car to the parking space, the angle between the car body and the parking space is not fixed, however, the position of the millimeter wave radar system installed on the car body is fixed, so that the driving track of the coming car obtained when the car is parked in the parking space when the car is parked vertically (i.e. when the car is parked in the parking space when the car is vertical to the parking space) is different from the driving track of the coming car obtained when the car is parked in an inclined parking space (i.e. when the car is parked in the parking space when the car is at a sharp included angle with the parking space), and the specific difference will be analyzed in detail below.
There are many embodiments of the above step S110, including but not limited to the following:
in a first embodiment, a radar system of an automobile is used to detect a position point of an incoming automobile and to fit the position point of the incoming automobile, so as to obtain a driving track of the incoming automobile, and the embodiment may include:
step S111: when an incoming vehicle is detected to the side rear of the automobile, the radar system of the automobile is used for detecting the position point of the incoming vehicle, and a plurality of position points are obtained.
Please refer to fig. 3, which is a schematic diagram of detection using a radar system according to an embodiment of the present application; the embodiment of step S111 described above is, for example: when the automobile is parked vertically (i.e. the automobile body is perpendicular to the parking space), the angular deviation between the automobile body and the parking space is assumed to be 0 degrees, that is, when the millimeter wave radar of the automobile detects that there is an incoming car from the side rear of the automobile, a coordinate system is established by taking the R coordinate as the ordinate and taking the L coordinate as the abscissa, then the included angle between the R coordinate and the length of the parking space is assumed to be 0 degrees, and the coordinate of the right-side rear incoming car is assumed to be (20, -5). In the process that the automobile is poured into the parking space, the automobile body and the posture information of the automobile are constantly changed, the included angle between the changed automobile body and the parking space is not 0 degree any more and is likely to be a sharp included angle, and the operation of detecting the position points of the coming automobile by using the radar system of the automobile is repeated, so that a plurality of position points of the coming automobile can be obtained. When the automobile is parked obliquely (i.e., an acute included angle is formed between an automobile body and a parking space), and when the millimeter wave radar system detects that an incoming car is located behind the automobile, if the R coordinate is still used as the ordinate, and the L coordinate is used as the abscissa to establish the coordinate system, then the attitude information of the automobile at the moment changes, which causes the coordinate of the incoming car behind the right side to deviate from the coordinate when the automobile is parked vertically, obviously, the coordinate of the incoming car behind the right side is no longer (20, -5), therefore, after the millimeter wave radar system of the automobile is used to detect the fitting of a plurality of position points of the incoming car, the driving track obtained by the fitting needs to be corrected, and a specific correction process will be described in detail below.
Step S112: and fitting the plurality of position points to obtain the driving track of the coming vehicle.
Alternatively, when the millimeter wave radar system is used for detecting the position point of an incoming vehicle, there may be many interference signals, so that the obtained position point is a clutter point, where the clutter point refers to an interference position point (i.e. not a real position point of the incoming vehicle) caused by radar scattering echoes. Therefore, before fitting the plurality of position points, the clutter points in the plurality of position points may be removed, and the specific process may include: performing probability density estimation on the driving track of the coming vehicle aiming at each position point in the plurality of position points to obtain an estimation result of the probability density estimation; then, judging whether the position point is a clutter point according to the estimation result; if the position point is a clutter point, the position point is deleted from the plurality of position points, so that the accuracy of the driving track of the coming vehicle is improved.
The fitting method in step S112 includes: the first fitting method is to obtain a driving track of an incoming vehicle by using a straight line fitting method, and the fitting method may specifically include: and performing straight line fitting on every two adjacent position points of the plurality of position points to obtain a driving track of the coming vehicle, such as a driving track formed by connecting a plurality of line segments with arrows at the lower right part of the figure 3. The second fitting method, which obtains the driving track of the coming vehicle by using a curve fitting method, may specifically include: curve fitting is performed on the plurality of position points to obtain a driving track of the coming vehicle, which is shown as a curve with an arrow at the lower right of fig. 3.
In a second implementation manner, a camera for shooting from the side to the rear can be installed on a rearview mirror of an automobile, a video stream is obtained by shooting with multiple cameras of the automobile, a key feature point of an incoming automobile in each video frame of the video stream is analyzed by using a key point Detection Network (Keypoints Detection Network) algorithm, multiple key feature points of the incoming automobile are obtained, and then the multiple key feature points are fitted, so that a driving track of the incoming automobile is obtained; among the key point detection networks that may be used are: openpos networks and Cascaded Pyramid Networks (CPNs), among others. In a specific implementation process, in combination with the first implementation manner and the second implementation manner, the feature points in the video stream and the position points detected by the millimeter wave radar system are used for performing calculation (for example, weighting calculation), so as to determine a final position point of the coming vehicle, and then the final position point is fitted, so as to obtain the driving track of the coming vehicle.
After step S110, step S120 is performed: and correcting the running track according to the included angle between the parking space corresponding to the automobile and the automobile to obtain the corrected running track.
The implementation of step S120 may include:
step S121: and acquiring an included angle between the parking space corresponding to the automobile and the automobile.
The embodiment of step S121 described above includes: in a first embodiment, the body attitude information of the vehicle is obtained by using a conventional sensor on the vehicle, where the conventional sensor may be a (centimeter-level or millimeter-level) radar installed on the vehicle, and after the radar obtains the body attitude information, a processor of the radar may calculate an included angle between the parking space and the vehicle according to the body attitude information. In the second embodiment, a video of a parking space is captured by using cameras (and cameras in front of a vehicle) attached to the rear-view mirrors on both sides, and an angle between the parking space and the vehicle is calculated from the video. In the third embodiment, the vehicle body posture information is acquired through a traditional sensor, then the orientation angle of the vehicle body is acquired from the vehicle body posture information, then the video shot by the cameras (and the cameras in front of the vehicle) arranged on the rearview mirrors at the two sides of the vehicle body is used for shooting the parking space, the orientation angle of the parking space is calculated from the video, and finally the included angle between the parking space corresponding to the vehicle and the vehicle is calculated according to the orientation angle of the vehicle body and the orientation angle of the parking space.
Step S122: and (4) carrying out deflection correction on the running track by taking the included angle as a deflection angle value to obtain the corrected running track.
The embodiment of step S122 described above is, for example: as shown in fig. 3, assuming that the travel track before correction is acquired when the automobile is asleep, the attitude information (the orientation angle of the vehicle body) of the automobile has changed since the automobile was asleep. Therefore, the rotation direction is determined according to the oblique stop position of the automobile by taking the included angle θ as a deflection angle value, the rotation direction is clockwise or counterclockwise, and the running track is deflected by θ degrees according to the rotation direction, so that the corrected running track is obtained.
Alternatively, although there are some differences in the travel locus of different vehicles on the lanes behind and on the side of the automobile, the directions of the travel loci of most of the vehicles are stably aligned, and therefore, these travel loci that are most stably aligned may be taken as the history locus, and the travel locus may be corrected using the history locus. That is, after the yaw correction of the travel locus in step S122, the correction may also be performed according to a history locus, and this embodiment may include:
step S123: acquiring a historical track of a passing vehicle behind the automobile, wherein the historical track comprises: historical predicted trajectories and historical true trajectories.
The embodiment of step S123 described above is, for example: the method includes the steps of obtaining a historical track of a vehicle passing behind the automobile from a Memory or a Memory database of a Graphics Processing Unit (GPU) by using a Direct Memory Access (DMA), wherein the historical track may include: historical predicted trajectories and historical true trajectories; the historical predicted track and the historical real track can be data added manually or data obtained by measuring the automobile through hardware such as a radar, a camera and a sensor.
Step S124: and extracting a mapping relation between the historical predicted track and the historical real track, and correcting the running track according to the mapping relation to obtain the corrected running track.
The embodiment of the step S124 includes: in the first embodiment, the driving trajectory is corrected by a kalman filter, specifically, for example: predicting a theoretical running track of the automobile according to the historical real track, measuring the measured running track by using a sensor of the automobile and calculating by using a processor, and performing weighted linear fusion and iterative operation on the theoretical running track and the measured running track by using a Kalman filter to obtain each iterative operation result; in the iterative operation process, the driving track can be continuously corrected according to each iterative operation result to obtain the corrected driving track. In the second embodiment, a Deep Neural Network (DNN) is used to extract a mapping relation between a historical predicted trajectory and a historical real trajectory from historical data, and a travel trajectory is corrected according to the mapping relation to obtain a corrected travel trajectory; the deep neural network that can be used specifically includes: VGG networks, ResNet networks, Wide ResNet networks, inclusion networks, and the like; the VGG network specifically includes: VGG16 or VGG 19; the ResNet network specifically includes: ResNet12, ResNet18, ResNet50, or ResNet 101; the Wide ResNet network is specifically, for example, a Wide ResNet-28-10 network, wherein the Wide ResNet-28-10 network is sometimes abbreviated as WRN-28-10; the inclusion network is specifically exemplified by: inclusion v1, inclusion v2, or inclusion v3, and the like.
After step S120, step S130 is performed: and acquiring a reversing track of the automobile, and performing early warning according to the reversing track and the corrected running track.
There are many embodiments of the above step S130, including but not limited to the following:
in a first embodiment, a collision probability is calculated according to a reverse trajectory and a corrected driving trajectory, and an early warning is performed according to the collision probability, which may include:
step S131: and acquiring a backing track of the automobile.
The embodiment of the step S131 includes: in the first implementation mode, the steering wheel rotation angle information and the automobile tire information of an automobile are acquired through a sensor, and then the backing track of the automobile is calculated according to the steering wheel rotation angle information and the automobile tire information; wherein, automobile tire information includes: tire rotation speed, rotation angle, tire pressure, rotation diameter, and the like. In the second implementation mode, the surrounding environment is shot through the front camera, the side camera and the rear camera to obtain the environment video, the environment video is used for modeling the motion track of the automobile, and the backing track of the automobile is simulated. In the third embodiment, the relative position of the automobile and the charging pile is positioned in real time by using a close-range positioning technology to obtain a plurality of relative position points, and the plurality of relative position points are fitted to obtain a fitted backing track.
Step S132: and calculating the collision probability of the automobile and the coming automobile according to the reversing track and the corrected running track.
Step S133: and if the collision probability is greater than a preset threshold value, generating and outputting an early warning signal.
Please refer to fig. 4, which is a schematic diagram illustrating a method for calculating a collision probability between an automobile and an incoming automobile according to an embodiment of the present application; the embodiments of the above steps S132 to S133 are, for example: the collision probability between the vehicle and the coming vehicle is calculated according to the reversing track and the corrected driving track, as shown in fig. 4, the parking lot has two rows of parking spaces, which are respectively started at S and started at T, and if the vehicle parked at S1 is the vehicle, when the vehicle backs from S1 and the vehicle parked at T1 moves upward, the probability that the vehicle collides with the vehicle parked at T1 is greater than a preset threshold value, and an early warning signal should be generated and output, and when the vehicle parked at T2 moves upward, the vehicle should not output the early warning signal. Similarly, if the vehicle backs up from the parking space S1 and the vehicle on the adjacent road moves to the upper right, the probability of collision between the vehicle and the vehicle on the adjacent road is greater than the preset threshold value, and an early warning signal should be generated and output; if the collision probability is larger than a preset threshold value, generating and outputting an early warning signal; the preset threshold value here may be set according to specific situations, for example, set to 50%, 70%, or 90%, etc.
In a second embodiment, a collision duration between a collision time of an automobile and an incoming automobile and a current time is calculated according to a reversing track and a corrected driving track, and an early warning is performed according to the collision duration, where the embodiment may include:
step S134: and acquiring a backing track of the automobile.
The implementation principle and implementation manner of step S134 are similar to those of step S131, and therefore, the implementation principle and implementation manner will not be described here, and if it is not clear, reference may be made to the description of step S131.
Step S135: and calculating the collision duration between the collision moment of the automobile and the coming automobile and the current moment according to the reversing track and the corrected running track.
Step S136: and if the collision time length is less than the preset time length threshold value, generating and outputting an early warning signal.
The embodiments of the above steps S135 to S136 are, for example: calculating the Collision distance between the automobile and the coming automobile according To the backing track and the corrected running track, and dividing the Collision distance by the relative speed between the automobile and the coming automobile To obtain the Collision duration (Time To Collision) between the Collision Time of the automobile and the coming automobile and the current Time; if the collision duration is less than a preset duration threshold (for example: 2.5 seconds or 2.7 seconds, etc.), generating an early warning signal, playing the early warning signal through a loudspeaker (for example, playing a sound for reminding the driver of a collision soon through a loudspeaker), and displaying the early warning signal through a display (for example, prompting the driver of a collision soon on a display screen).
In the implementation process, the driving track of the coming vehicle is firstly acquired, then the driving track is corrected according to the included angle between the parking space corresponding to the vehicle and the vehicle, and finally early warning is carried out according to the backing track and the corrected driving track. That is to say, the running track of the vehicle coming from the side rear is corrected according to the included angle between the parking space corresponding to the vehicle and the vehicle, and early warning is performed according to the backing track of the vehicle and the corrected running track, so that the problem that the running track of the vehicle coming from the side rear, which is acquired by a radar system, has an error due to the change of the posture information of the vehicle when the vehicle is obliquely stopped to a specified parking space is avoided, the running track of the vehicle coming from the side rear is corrected, the error is reduced, and the accuracy of the RCTA function early warning of the vehicle is effectively improved.
Please refer to fig. 5 for a schematic structural diagram of an automobile early warning device provided in the embodiment of the present application. The embodiment of the application provides an automobile early warning device 200, including:
the driving track obtaining module 210 is configured to obtain a driving track of an incoming vehicle when it is detected that the incoming vehicle is located behind the vehicle.
And a driving track correcting module 220, configured to correct the driving track according to an included angle between a parking space corresponding to the vehicle and the vehicle, so as to obtain a corrected driving track.
And the driving track early warning module 230 is configured to obtain a reversing track of the vehicle, and perform early warning according to the reversing track and the corrected driving track.
Optionally, in an embodiment of the present application, the driving track obtaining module includes:
and the coming vehicle position detection module is used for detecting the position points of the coming vehicle by using a radar system of the automobile to obtain a plurality of position points.
And the vehicle-coming track fitting module is used for fitting the plurality of position points to obtain the driving track of the coming vehicle.
Optionally, in an embodiment of the present application, the driving track obtaining module further includes:
and the clutter position judging module is used for judging whether the position point is a clutter point or not aiming at each position point in the plurality of position points.
And the clutter position deleting module is used for deleting the position point from the plurality of position points if the position point is a clutter point.
Optionally, in this embodiment of the present application, the incoming vehicle trajectory fitting module includes:
the position point fitting module is used for performing straight line fitting on every two adjacent position points of the plurality of position points; alternatively, a curve fit is performed for a plurality of location points.
Optionally, in an embodiment of the present application, the driving track correction module includes:
and the included angle deflection correction module is used for carrying out deflection correction on the running track by taking the included angle as a deflection angle value.
Optionally, in an embodiment of the present application, the driving track correction module further includes:
the historical track acquisition module is used for acquiring the historical track of the passing vehicle behind the automobile, and the historical track comprises: historical predicted trajectories and historical true trajectories.
And the mapping relation correction module is used for extracting the mapping relation between the historical predicted track and the historical real track and correcting the driving track according to the mapping relation.
Optionally, in this embodiment of the present application, the driving track early warning module includes:
and the collision probability calculation module is used for calculating the collision probability of the automobile and the coming automobile according to the reversing track and the corrected running track.
And the early warning signal output module is used for generating and outputting an early warning signal if the collision probability is greater than a preset threshold value.
It should be understood that the device corresponds to the above-mentioned embodiment of the vehicle early warning method, and can perform the steps related to the above-mentioned embodiment of the method, the specific functions of the device can be referred to the above description, and the detailed description is appropriately omitted herein to avoid redundancy. The device includes at least one software function that can be stored in memory in the form of software or firmware (firmware) or solidified in the Operating System (OS) of the device.
An electronic device provided in an embodiment of the present application includes: a processor and a memory, the memory storing processor-executable machine-readable instructions, the machine-readable instructions when executed by the processor performing the method as above.
The embodiment of the application also provides a storage medium, wherein the storage medium is stored with a computer program, and the computer program is executed by a processor to execute the method.
The storage medium may be implemented by any type of volatile or nonvolatile storage device or combination thereof, such as a Static Random Access Memory (SRAM), an Electrically Erasable Programmable Read-Only Memory (EEPROM), an Erasable Programmable Read-Only Memory (EPROM), a Programmable Read-Only Memory (PROM), a Read-Only Memory (ROM), a magnetic Memory, a flash Memory, a magnetic disk, or an optical disk.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The apparatus embodiments described above are merely illustrative, and for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved.
In addition, functional modules of the embodiments in the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
In this document, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions.
The above description is only an alternative embodiment of the embodiments of the present application, but the scope of the embodiments of the present application is not limited thereto, and any person skilled in the art can easily conceive of changes or substitutions within the technical scope of the embodiments of the present application, and all the changes or substitutions should be covered by the scope of the embodiments of the present application.
Claims (10)
1. An automobile early warning method is characterized by comprising the following steps:
when an incoming vehicle is detected to be arranged at the side rear part of the automobile, the running track of the incoming vehicle is obtained;
correcting the driving track according to an included angle between the parking space corresponding to the automobile and the automobile to obtain a corrected driving track;
and acquiring a reversing track of the automobile, and carrying out early warning according to the reversing track and the corrected running track.
2. The method of claim 1, wherein the obtaining the driving track of the coming vehicle comprises:
detecting the position points of the coming vehicle by using a radar system of the automobile to obtain a plurality of position points;
and fitting the plurality of position points to obtain the driving track of the coming vehicle.
3. The method of claim 2, further comprising, prior to said fitting the plurality of location points:
judging whether each position point in the plurality of position points is a clutter point or not;
and if so, deleting the position point from the plurality of position points.
4. The method of claim 2, wherein said fitting the plurality of location points comprises:
performing straight line fitting on every two adjacent position points of the plurality of position points;
alternatively, a curve fit is performed to the plurality of location points.
5. The method according to claim 1, wherein the correcting the driving track according to the included angle between the corresponding parking space of the automobile and the automobile comprises:
and performing deflection correction on the running track by taking the included angle as a deflection angle value.
6. The method of claim 5, further comprising, after said yaw correcting said trajectory:
acquiring a historical track of a vehicle passing behind the automobile, wherein the historical track comprises: historical predicted trajectories and historical true trajectories;
and extracting a mapping relation between the historical predicted track and the historical real track, and correcting the running track according to the mapping relation.
7. The method according to any one of claims 1-6, wherein the performing an early warning according to the reverse trajectory and the modified travel trajectory comprises:
calculating the collision probability of the automobile and the coming automobile according to the backing track and the corrected running track;
and if the collision probability is greater than a preset threshold value, generating and outputting an early warning signal.
8. An automotive early warning device, comprising:
the driving track acquiring module is used for acquiring the driving track of an incoming vehicle when the situation that the incoming vehicle is located behind the automobile is detected;
the driving track correction module is used for correcting the driving track according to an included angle between a parking space corresponding to the automobile and the automobile to obtain a corrected driving track;
and the driving track early warning module is used for acquiring the backing track of the automobile and carrying out early warning according to the backing track and the corrected driving track.
9. An electronic device, comprising: a processor and a memory, the memory storing machine-readable instructions executable by the processor, the machine-readable instructions, when executed by the processor, performing the method of any of claims 1 to 7.
10. A storage medium, having stored thereon a computer program which, when executed by a processor, performs the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110227650.XA CN112950999A (en) | 2021-03-01 | 2021-03-01 | Automobile early warning method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110227650.XA CN112950999A (en) | 2021-03-01 | 2021-03-01 | Automobile early warning method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112950999A true CN112950999A (en) | 2021-06-11 |
Family
ID=76247032
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110227650.XA Pending CN112950999A (en) | 2021-03-01 | 2021-03-01 | Automobile early warning method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112950999A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113449648A (en) * | 2021-06-30 | 2021-09-28 | 北京纵目安驰智能科技有限公司 | Method, system, equipment and computer readable storage medium for detecting indicator line |
| CN113990052A (en) * | 2021-10-29 | 2022-01-28 | 南京慧尔视防务科技有限公司 | Incoming vehicle early warning method and device, storage medium and road protection vehicle |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104766084A (en) * | 2015-04-10 | 2015-07-08 | 南京大学 | Nearly copied image detection method based on multi-target matching |
| US20160161607A1 (en) * | 2014-12-08 | 2016-06-09 | Northrop Grumman Systems Corporation | Feature-based tracking of moving objects |
| CN106541945A (en) * | 2016-11-15 | 2017-03-29 | 广州大学 | A kind of unmanned vehicle automatic parking method based on ICP algorithm |
| CN107298100A (en) * | 2017-05-16 | 2017-10-27 | 开易（北京）科技有限公司 | A kind of track of vehicle Forecasting Methodology, system based on gauss hybrid models |
| US20170329332A1 (en) * | 2016-05-10 | 2017-11-16 | Uber Technologies, Inc. | Control system to adjust operation of an autonomous vehicle based on a probability of interference by a dynamic object |
| CN109080629A (en) * | 2017-06-14 | 2018-12-25 | 福特全球技术公司 | The method of cross traffic is considered while vehicle is driven out to and executes the vehicle of this method |
| CN109814115A (en) * | 2019-01-16 | 2019-05-28 | 杭州湘滨电子科技有限公司 | A kind of angle recognition bearing calibration vertically parked |
| CN109871599A (en) * | 2019-01-30 | 2019-06-11 | 西安理工大学 | A method for evaluating the safety index of unmanned vehicle operation |
| CN111062372A (en) * | 2020-03-13 | 2020-04-24 | 北京三快在线科技有限公司 | Method and device for predicting obstacle track |
| CN111079804A (en) * | 2019-12-02 | 2020-04-28 | 中南大学 | Vehicle motion track prediction method and system of improved Gaussian mixture model |
| CN111583718A (en) * | 2020-05-29 | 2020-08-25 | 江铃汽车股份有限公司 | Automobile reversing early warning method and system and vehicle-mounted terminal |
| CN111679256A (en) * | 2020-07-23 | 2020-09-18 | 杭州智波科技有限公司 | Angle calibration method, device and system of automobile millimeter wave radar and storage medium |
-
2021
- 2021-03-01 CN CN202110227650.XA patent/CN112950999A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160161607A1 (en) * | 2014-12-08 | 2016-06-09 | Northrop Grumman Systems Corporation | Feature-based tracking of moving objects |
| CN104766084A (en) * | 2015-04-10 | 2015-07-08 | 南京大学 | Nearly copied image detection method based on multi-target matching |
| US20170329332A1 (en) * | 2016-05-10 | 2017-11-16 | Uber Technologies, Inc. | Control system to adjust operation of an autonomous vehicle based on a probability of interference by a dynamic object |
| CN106541945A (en) * | 2016-11-15 | 2017-03-29 | 广州大学 | A kind of unmanned vehicle automatic parking method based on ICP algorithm |
| CN107298100A (en) * | 2017-05-16 | 2017-10-27 | 开易（北京）科技有限公司 | A kind of track of vehicle Forecasting Methodology, system based on gauss hybrid models |
| CN109080629A (en) * | 2017-06-14 | 2018-12-25 | 福特全球技术公司 | The method of cross traffic is considered while vehicle is driven out to and executes the vehicle of this method |
| CN109814115A (en) * | 2019-01-16 | 2019-05-28 | 杭州湘滨电子科技有限公司 | A kind of angle recognition bearing calibration vertically parked |
| CN109871599A (en) * | 2019-01-30 | 2019-06-11 | 西安理工大学 | A method for evaluating the safety index of unmanned vehicle operation |
| CN111079804A (en) * | 2019-12-02 | 2020-04-28 | 中南大学 | Vehicle motion track prediction method and system of improved Gaussian mixture model |
| CN111062372A (en) * | 2020-03-13 | 2020-04-24 | 北京三快在线科技有限公司 | Method and device for predicting obstacle track |
| CN111583718A (en) * | 2020-05-29 | 2020-08-25 | 江铃汽车股份有限公司 | Automobile reversing early warning method and system and vehicle-mounted terminal |
| CN111679256A (en) * | 2020-07-23 | 2020-09-18 | 杭州智波科技有限公司 | Angle calibration method, device and system of automobile millimeter wave radar and storage medium |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113449648A (en) * | 2021-06-30 | 2021-09-28 | 北京纵目安驰智能科技有限公司 | Method, system, equipment and computer readable storage medium for detecting indicator line |
| CN113990052A (en) * | 2021-10-29 | 2022-01-28 | 南京慧尔视防务科技有限公司 | Incoming vehicle early warning method and device, storage medium and road protection vehicle |
| CN113990052B (en) * | 2021-10-29 | 2023-08-15 | 南京慧尔视防务科技有限公司 | Method, device, storage medium and road protection vehicle for early warning of approaching vehicles |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112329552B (en) | Obstacle detection method and device based on automobile | |
| US9983306B2 (en) | System and method for providing target threat assessment in a collision avoidance system on a vehicle | |
| US8930063B2 (en) | Method for determining object sensor misalignment | |
| JP6005055B2 (en) | Method for continuously calculating, inspecting and / or adapting a parking trajectory in a vehicle parking assist system, a computer program and a parking assist system | |
| JP4420011B2 (en) | Object detection device | |
| CN106608261B (en) | Vehicle and method of controlling distance between running vehicles | |
| US11093761B2 (en) | Lane position sensing and tracking in a vehicle | |
| US8781688B2 (en) | Method and system for combining sensor data | |
| US20200216063A1 (en) | Vehicle and method for controlling the same | |
| CN111976598A (en) | Vehicle blind area monitoring method and system | |
| CN105799617A (en) | Method for determining misalignment of an object sensor | |
| US11433888B2 (en) | Driving support system | |
| US20200130683A1 (en) | Collision prediction apparatus and collision prediction method | |
| JP5680436B2 (en) | Foreign matter adhesion determination device for in-vehicle camera lens | |
| US20220234581A1 (en) | Vehicle control method, vehicle control device, and vehicle control system including same | |
| US11753002B2 (en) | Vehicular control system | |
| CN112950999A (en) | Automobile early warning method and device, electronic equipment and storage medium | |
| KR20210005439A (en) | Advanced Driver Assistance System, Vehicle having the same and method for controlling the vehicle | |
| US20240194077A1 (en) | Method for operating a driver assistance system, computer program product, driver assistance system, and vehicle | |
| JP7363062B2 (en) | Driving environment abnormality determination system | |
| JP7702036B2 (en) | Driving assistance device and driving assistance program | |
| US20230222813A1 (en) | Road surface marking detection device, notification system provided with the same, and road surface marking detection | |
| WO2024144436A1 (en) | Device and method for detecting objects | |
| WO2024144437A1 (en) | Autonomous vehicle and method for controlling the movement thereof | |
| CN115339440A (en) | Vehicle control method and apparatus |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210611 |
|
| RJ01 | Rejection of invention patent application after publication |