Static obstacle screening method, device and equipment and vehicle
By using millimeter-wave radar data to filter out target moving vehicle data and generate driving areas in low-speed driving scenarios, the problem of false obstacles when surround-view cameras and ultrasonic radar detect stationary obstacles is solved, achieving higher detection accuracy and safety.
Patent Information
- Application Number
- CN202511108335.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-08-08
- Publication Date
- 2025-10-28
AI Technical Summary
In existing technologies, surround-view cameras and ultrasonic radars are easily affected by the afterimages of moving vehicles when detecting stationary obstacles in low-speed driving scenarios, resulting in low accuracy in detecting stationary obstacles.
In low-speed driving scenarios, by acquiring the initial set of stationary obstacles and millimeter-wave radar data within a preset time period before the current moment, the target moving vehicle data is filtered out, and stationary obstacles are filtered out based on its driving area to remove false obstacles.
It improves the accuracy of detecting stationary obstacles, avoids false alarms caused by false obstacles, and enhances the driving experience and safety.
Smart Images
Figure CN120840561A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of vehicle technology, and specifically to a method, apparatus, equipment, and vehicle for screening stationary obstacles. Background Technology
[0002] With the continuous development of technology, vehicles are becoming increasingly feature-rich. The emergence of Automatic Emergency Braking (AEB) has improved vehicle safety. AEB can brake the vehicle when it detects an obstacle in front of it and a collision is imminent.
[0003] In existing technologies, the AEB (Autonomous Emergency Braking) function for vehicles in low-speed driving scenarios also uses data from surround-view cameras and ultrasonic radar to detect stationary obstacles and calculate the collision duration, braking when the collision duration is less than a threshold. However, due to the inherent performance limitations of surround-view cameras and ultrasonic radar, after other moving vehicles leave the detection area, afterimages appear, and the data from the surround-view cameras and ultrasonic radar still contain the data of that vehicle, thus detecting it as a stationary obstacle.
[0004] Therefore, there is an urgent need for a method to screen stationary obstacles that can be obtained from data obtained from surround-view cameras and ultrasonic radar. Summary of the Invention
[0005] One objective of this invention is to provide a method for screening stationary obstacles, thereby addressing the problem of low accuracy in identifying stationary obstacles based on data from surround-view cameras and ultrasonic radar in the prior art; a second objective is to provide a device for screening stationary obstacles; a third objective is to provide an electronic device; and a fourth objective is to provide a vehicle.
[0006] To achieve the above objectives, the technical solution adopted by the present invention is as follows:
[0007] In a first aspect, the present invention provides a method for screening stationary obstacles, comprising:
[0008] When the vehicle is traveling at low speed, it acquires an initial set of stationary obstacles and millimeter-wave radar data within a preset time period before the current moment.
[0009] If the millimeter-wave radar data includes moving vehicle data, then according to the preset collision area, all moving vehicle data is filtered to obtain the target moving vehicle data;
[0010] For each target moving vehicle data, the driving area of the target moving vehicle data is generated based on the target moving vehicle data;
[0011] Based on the driving area of each target moving vehicle, the stationary obstacles in the initial set of stationary obstacles are filtered to obtain the target obstacles.
[0012] Furthermore, the data for each moving vehicle includes multiple moments of movement, as well as the corresponding position of movement at each moment of movement;
[0013] The step of filtering all moving vehicle data according to the preset collision area to obtain target moving vehicle data includes:
[0014] For each moving vehicle data, if the movement position corresponding to each movement moment in the moving vehicle data belongs to the preset collision area, and the distance between the movement position corresponding to the latest movement moment in the moving vehicle data and the boundary of the preset collision area is less than the preset departure distance, then the moving vehicle data is taken as the target moving vehicle data.
[0015] Furthermore, generating the driving area of the target moving vehicle data based on the target moving vehicle data includes:
[0016] Based on the movement position corresponding to each movement moment in the target moving vehicle data, the driving area of the target moving vehicle data is generated; or...
[0017] The driving area of the target moving vehicle data is generated based on the earliest movement time and the latest movement time in the target moving vehicle data.
[0018] Furthermore, generating the driving area of the target moving vehicle data based on the movement position corresponding to each movement moment in the target moving vehicle data includes:
[0019] A driving trajectory is generated based on the movement position corresponding to each movement moment in the target moving vehicle data;
[0020] Based on the driving trajectory and preset width, the driving area of the target moving vehicle data is generated.
[0021] Furthermore, the step of filtering stationary obstacles in the initial set of stationary obstacles based on the driving area of each target moving vehicle data to obtain target obstacles includes:
[0022] For each stationary obstacle in the initial set of stationary obstacles, if the obstacle type of the stationary obstacle is a vehicle and the position of the stationary obstacle belongs to the driving area of at least one target moving vehicle data, then the stationary obstacle is regarded as a false obstacle.
[0023] Each stationary obstacle in the initial set of stationary obstacles, excluding false obstacles, is taken as the target obstacle.
[0024] Furthermore, each moving vehicle data includes a heading angle. Before filtering stationary obstacles in the initial set of stationary obstacles based on the driving area of each target moving vehicle data to obtain the target obstacle, the method further includes:
[0025] For each target moving vehicle data, if the heading angle in the target moving vehicle data belongs to a preset lateral travel angle range, then the target moving vehicle data is used as lateral moving vehicle data.
[0026] The step of filtering stationary obstacles in the initial set of stationary obstacles based on the driving area of each target moving vehicle data to obtain target obstacles includes:
[0027] Based on the driving area of each lateral moving vehicle, the stationary obstacles in the initial set of stationary obstacles are filtered to obtain the target obstacles.
[0028] Furthermore, the method also includes:
[0029] For each target obstacle, the collision distance and collision duration are calculated based on the position of the target obstacle, the current position of the vehicle, and the speed of the vehicle.
[0030] For each target obstacle, if the collision distance corresponding to the target obstacle is less than a preset collision distance threshold and the collision duration corresponding to the target obstacle is less than a preset collision duration threshold, then braking and an alarm will be triggered.
[0031] In a second aspect, the present invention provides a stationary obstacle screening device, comprising:
[0032] The acquisition module is used to acquire an initial set of stationary obstacles and millimeter-wave radar data within a preset time period before the current moment when the vehicle is traveling at low speed.
[0033] The filtering module is used to filter all moving vehicle data according to a preset collision area if the millimeter-wave radar data includes moving vehicle data, so as to obtain the target moving vehicle data.
[0034] The processing module is used to generate the driving area of each target moving vehicle data based on the target moving vehicle data.
[0035] The filtering module is also used to filter the stationary obstacles in the initial set of stationary obstacles according to the driving area of each target moving vehicle data, so as to obtain the target obstacles.
[0036] Thirdly, the present invention provides an electronic device, comprising:
[0037] Processor, memory, communication interface;
[0038] The memory is used to store the executable instructions of the processor;
[0039] The processor is configured to perform the static obstacle screening method according to any one of the first aspects by executing the executable instructions.
[0040] Fourthly, the present invention provides a readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the static obstacle screening method according to any one of the first aspects.
[0041] Fifthly, the present invention provides a computer program product, including a computer program, which, when executed by a processor, is used to implement the static obstacle screening method according to any one of the first aspects.
[0042] Sixthly, the present invention provides a vehicle, including a vehicle controller;
[0043] The vehicle controller is used to perform the stationary obstacle screening method described in any of the first aspects above.
[0044] The beneficial effects of this invention are:
[0045] (1) This application obtains an initial set of stationary obstacles and millimeter-wave radar data within a preset time period before the current moment when the vehicle is in a low-speed driving scenario. If the millimeter-wave radar data includes moving vehicle data, then all moving vehicle data is filtered according to a preset collision area to obtain target moving vehicle data. Then, a driving area for each target moving vehicle data is generated based on each target moving vehicle data. Then, based on the driving area of each target moving vehicle data, the stationary obstacles in the initial set of stationary obstacles are filtered to obtain the target obstacles, thus realizing the filtering of stationary obstacles obtained from the data of surround-view cameras and ultrasonic radar.
[0046] (2) This application can improve the accuracy of the target obstacles by filtering all moving vehicle data according to the preset collision area and filtering the stationary obstacles in the initial stationary obstacle set according to the driving area of each target moving vehicle data. Attached Figure Description
[0047] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0048] Figure 1a A flowchart illustrating an embodiment of the static obstacle screening method provided in this application;
[0049] Figure 1b A schematic diagram of the vehicle coordinate system provided in this application;
[0050] Figure 1c A schematic diagram of the driving area provided in this application;
[0051] Figure 2 A schematic flowchart of Embodiment 2 of the static obstacle screening method provided in this application;
[0052] Figure 3 A flowchart illustrating Embodiment 3 of the static obstacle screening method provided in this application;
[0053] Figure 4 A schematic diagram of the structure of an embodiment of the static obstacle screening device provided in this application;
[0054] Figure 5 This is a schematic diagram of the structure of an electronic device provided in this application.
[0055] The accompanying drawings have illustrated specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to specific embodiments. Detailed Implementation
[0056] The embodiments of the present invention will be described below with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention and not for limiting the scope of protection of the present invention.
[0057] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Therefore, the drawings only show the components related to the present invention and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.
[0058] With the development of technology, the Automatic Emergency Braking (AEB) function has emerged, which can greatly improve vehicle safety. The AEB function can brake when it detects an obstacle in front of the vehicle and a collision with the obstacle is imminent.
[0059] In existing technologies, AEB (Autonomous Emergency Braking) functions for vehicles in low-speed driving scenarios also use data from surround-view cameras and ultrasonic radar to detect stationary obstacles and calculate the collision duration, braking when the collision duration is less than a threshold. However, due to the performance limitations of surround-view cameras and ultrasonic radar, or environmental interference, afterimages of other moving vehicles may appear after they leave the detection area. The data from these cameras and radar still contains data about that vehicle, and these afterimages are detected as stationary obstacles. Therefore, there is an urgent need for a method to filter stationary obstacles obtained from data from surround-view cameras and ultrasonic radar.
[0060] To address the problems existing in the prior art, the inventors, during their research on static obstacle screening methods, discovered that, in order to achieve accurate screening of static obstacles, an initial set of static obstacles and millimeter-wave radar data within a preset time period prior to the current moment are acquired when the vehicle is traveling at low speed. If the millimeter-wave radar data includes moving vehicle data, all moving vehicle data is filtered according to a preset collision area to obtain target moving vehicle data. Then, a driving area is generated for each target moving vehicle data. Finally, based on the driving area of each target moving vehicle data, static obstacles in the initial set of static obstacles are filtered to obtain target obstacles. This achieves the screening of static obstacles obtained from data from surround-view cameras and ultrasonic radar. Based on the above inventive concept, the static obstacle screening scheme in this application was designed.
[0061] The executing entity of the static obstacle screening method in this application can be a vehicle control unit (VCU), or an on-board terminal, server, etc. This application does not limit it. The following explanation uses VCU as an example.
[0062] The following provides examples illustrating the application scenarios of the static obstacle screening method provided in this application.
[0063] A user parks their vehicle in a parking lot. The vehicle is equipped with millimeter-wave radar, a surround-view camera, and ultrasonic radar. The Vehicle Control Unit (VCU) detects obstacles based on data from the surround-view camera and ultrasonic radar, obtaining an initial set of stationary obstacles. The VCU detects that the vehicle is traveling at a low speed. To remove false obstacles from the initial set of stationary obstacles, the VCU filters the stationary obstacles within the initial set and acquires millimeter-wave radar data from a preset time period prior to the current moment.
[0064] It should be noted that the preset duration can be 10 seconds, 15 seconds, 20 seconds, 30 seconds, etc. This application embodiment does not limit the preset duration, and it can be determined according to the actual situation.
[0065] If the VCU determines that the millimeter-wave radar data includes moving vehicle data, it filters all moving vehicle data according to the preset collision area to obtain the target moving vehicle data.
[0066] Then, for each target moving vehicle data, the driving area of the target moving vehicle data is generated based on the target moving vehicle data.
[0067] The VCU then filters the stationary obstacles in the initial set of stationary obstacles based on the driving area of each target moving vehicle data, removing false obstacles to obtain the target obstacles.
[0068] Subsequently, the VCU can determine whether a collision is imminent based on the position of the target obstacle, the current position of the vehicle, and the vehicle speed. If a collision is determined to be imminent, it will brake and issue a warning.
[0069] It should be noted that the above scenario is only an example of an application scenario provided by the embodiments of this application. The embodiments of this application do not limit the actual form of the various devices included in the scenario, nor do they limit the interaction method between devices. In the specific application of the solution, it can be set according to actual needs.
[0070] The technical solution of the present application is described in detail below through specific embodiments. It should be noted that the following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.
[0071] Figure 1a This is a flowchart illustrating an embodiment of the stationary obstacle screening method provided in this application. This embodiment describes how the VCU, based on millimeter-wave radar data, filters stationary obstacles from an initial set of stationary obstacles within a driving area to obtain target obstacles. The method in this embodiment can be implemented through software, hardware, or a combination of both. Figure 1a As shown, the static obstacle screening method specifically includes the following steps:
[0072] S101: When the vehicle is traveling at low speed, acquire the initial set of stationary obstacles and the millimeter-wave radar data within a preset time period before the current moment.
[0073] The vehicle is equipped with millimeter-wave radar, surround-view camera, and ultrasonic radar. In order to realize the AEB function, the VCU detects based on the data from the surround-view camera and ultrasonic radar to obtain an initial set of stationary obstacles, which includes stationary obstacles.
[0074] In this step, in order to improve the accuracy of filtering stationary obstacles in low-speed driving scenarios, the VCU needs to acquire an initial set of stationary obstacles and millimeter-wave radar data within a preset time period before the current moment when the vehicle is in a low-speed driving scenario.
[0075] It should be noted that low-speed driving scenarios include parking lots, underground garages, and congested road sections. The VCU can determine whether the vehicle is in a low-speed driving scenario based on its own speed. If the vehicle speed is less than a preset low-speed scenario threshold, it is determined that the vehicle is in a low-speed driving scenario; if the vehicle speed is greater than or equal to the preset low-speed scenario threshold, it is determined that the vehicle is not in a low-speed driving scenario. The preset low-speed scenario threshold can be 10km / h, 15km / h, 20km / h, etc. This application embodiment does not limit the low-speed driving scenario or the preset low-speed scenario threshold, and it can be determined according to the actual situation.
[0076] It should be noted that the millimeter-wave radar data within the preset time period before the current moment includes target detection data. Each target detection data includes the target type and motion data within the preset time period before the current moment. The motion data within the preset time period before the current moment includes multiple motion moments and the motion position corresponding to each motion moment.
[0077] The target type can be pedestrians, railings, posts, moving vehicles, stationary vehicles, etc. If the target type in a detection target data is a moving vehicle, then the detected target vehicle is moving vehicle data.
[0078] S102: If the millimeter-wave radar data includes moving vehicle data, then based on the preset collision area, all moving vehicle data is filtered to obtain the target moving vehicle data.
[0079] In this step, after the VCU acquires millimeter-wave radar data within a preset time period prior to the current moment, it needs to determine whether there are any moving vehicles, since the false obstacles in the initial set of stationary obstacles are generated by moving vehicles. The VCU determines whether the millimeter-wave radar data includes moving vehicle data. If the millimeter-wave radar data includes detected target data of moving vehicle type, then it is determined that the meter-wave radar data includes moving vehicle data. If the millimeter-wave radar data does not include detected target data of moving vehicle type, then it is determined that the meter-wave radar data does not include moving vehicle data.
[0080] If the millimeter-wave radar data includes data on moving vehicles, it means that a moving vehicle passed near the vehicle within a preset time period before the current moment. Since a moving vehicle is only likely to be detected as a stationary obstacle when it is relatively close to the vehicle, it is necessary to filter all moving vehicle data according to the preset collision area to obtain the target moving vehicle data.
[0081] Specifically, the data for each moving vehicle includes multiple moments of movement and the corresponding position of movement at each moment of movement.
[0082] It should be noted that the position of motion can be represented using coordinates in the vehicle's vehicle coordinate system. For example, Figure 1b A schematic diagram of the vehicle coordinate system provided in this application, such as Figure 1b As shown, the vehicle coordinate system has the center of the rear axle of the vehicle as the origin, the direction of the vehicle's forward movement as the x-axis, and the positive direction as the direction of the vehicle's forward movement; the positive direction of the y-axis is perpendicular to the left side of the vehicle body.
[0083] For each moving vehicle data, if the movement position corresponding to each movement moment in the moving vehicle data belongs to the preset collision area, and the distance between the movement position corresponding to the latest movement moment in the moving vehicle data and the boundary of the preset collision area is less than the preset departure distance, then the moving vehicle data is taken as the target moving vehicle data.
[0084] It should be noted that the preset collision area is the area where the vehicle may collide, and it is also the area for detecting stationary obstacles. The preset collision area is generated based on the vehicle's current position and includes the vehicle's current area. The preset collision area can be: a circle centered on the vehicle's current position with a first preset detection distance as its radius; it can also be: a rectangle centered on the vehicle's current position with a second preset detection distance as its width and a third preset detection distance as its length; or it can be: a rectangle with a second preset detection distance as its width and a third preset detection distance as its length, with the vehicle's position at the midpoint of one side of the rectangle and the vehicle facing the opposite side. The first preset detection distance, the second preset detection distance, and the third preset detection distance can be 5 meters, 7.5 meters, 10 meters, 30 meters, etc. This application embodiment does not limit the size and shape of the first preset detection distance, the second preset detection distance, the third preset detection distance, or the preset collision area, and can be determined according to the actual situation.
[0085] In this data set of moving vehicles, the position corresponding to each movement moment falls within the preset collision zone, indicating that the vehicle corresponding to this data is traveling within the preset collision zone and is relatively close to the user. The distance between the position corresponding to the latest movement moment in this data set and the boundary of the preset collision zone is less than the preset departure distance, indicating that the vehicle left the preset collision zone but did not stop within it, which may result in afterimages.
[0086] It should be noted that the distance between the moving position and the boundary of the preset collision area refers to the minimum distance between the moving position and the boundary of the preset collision area.
[0087] It should be noted that the preset departure distance can be 1 meter, 0.5 meters, 0.3 meters, 0.1 meters, 0.01 meters, etc. This application embodiment does not limit the preset departure distance, and it can be determined according to the actual situation.
[0088] It should be noted that if the millimeter-wave radar data includes moving vehicle data, then the stationary obstacles in the initial set of stationary obstacles are not filtered. If each moving vehicle data point is not the target moving vehicle data, then the stationary obstacles in the initial set of stationary obstacles are not filtered.
[0089] S103: For each target moving vehicle data, generate the driving area of the target moving vehicle data based on the target moving vehicle data.
[0090] In this step, after the VCU obtains the target moving vehicle data, in order to filter stationary obstacles, it is necessary to generate the driving area of each target moving vehicle data based on that target moving vehicle data.
[0091] In one implementation, the driving area of the target moving vehicle data is generated based on the movement position corresponding to each movement moment in the target moving vehicle data.
[0092] The system can perform fitting processing based on the movement position corresponding to each movement moment in the target moving vehicle data to generate a driving trajectory. Then, based on the driving trajectory and a preset width, the driving area of the target moving vehicle data can be generated.
[0093] For example, Figure 1c A schematic diagram of the driving area provided in this application, such as Figure 1c As shown in the diagram, the dashed lines represent the driving trajectory, and the area enclosed by the solid lines is the driving area. The centerline of the driving area is the driving trajectory, and the minimum distance from each point on the driving trajectory to the boundary of the driving area is half the preset width.
[0094] It should be noted that the preset width can be 1 meter, 2 meters, 3 meters, etc. This application embodiment does not limit the preset width, and it can be determined according to the actual situation.
[0095] In another implementation, a driving area for the target moving vehicle data is generated based on the movement position corresponding to the earliest movement time and the movement position corresponding to the latest movement time in the target moving vehicle data. This driving area is rectangular, with one end of the rectangle representing the movement position corresponding to the earliest movement time in the target moving vehicle data and the other end representing the movement position corresponding to the latest movement time in the target moving vehicle data.
[0096] S104: Based on the driving area of each target moving vehicle data, filter the stationary obstacles in the initial set of stationary obstacles to obtain the target obstacles.
[0097] In this step, after the VCU obtains the driving area of each target moving vehicle, it filters the stationary obstacles in the initial set of stationary obstacles based on the driving area of each target moving vehicle to obtain the target obstacles.
[0098] Specifically, for each stationary obstacle in the initial set of stationary obstacles, if the obstacle type of the stationary obstacle is a vehicle and the position of the stationary obstacle belongs to the driving area of at least one target moving vehicle data, it means that the stationary obstacle is an obstacle obtained based on the afterimage detection of the moving vehicle, and then the stationary obstacle is regarded as a false obstacle.
[0099] Each stationary obstacle in the initial set of stationary obstacles, excluding false obstacles, is taken as the target obstacle.
[0100] The stationary obstacle screening method provided in this embodiment acquires an initial set of stationary obstacles and millimeter-wave radar data within a preset time period before the current moment when the vehicle is traveling at low speed. If the millimeter-wave radar data includes moving vehicle data, all moving vehicle data is filtered according to a preset collision area to obtain target moving vehicle data. Then, a driving area is generated for each target moving vehicle data. Based on the driving area of each target moving vehicle data, stationary obstacles in the initial stationary obstacle set are filtered to obtain target obstacles. This achieves the screening of stationary obstacles obtained from surround-view camera and ultrasonic radar data. By filtering all moving vehicle data and filtering stationary obstacles in the initial stationary obstacle set based on the driving area of each target moving vehicle data, false obstacles are removed, improving the accuracy of the obtained target obstacles. Simultaneously, braking based on false obstacles is avoided, improving the driving experience.
[0101] Figure 2 This is a flowchart illustrating a second embodiment of the stationary obstacle screening method provided in this application. Based on the above embodiments, this application embodiment describes the screening of target vehicle data after generating the driving area of each target vehicle data for each target vehicle data before the VCU filters stationary obstacles in the initial set of stationary obstacles according to the driving area of each target moving vehicle data. For example... Figure 2 As shown, the static obstacle screening method specifically includes the following steps:
[0102] S201: For each target moving vehicle data, if the heading angle in the target moving vehicle data is within the preset lateral travel angle range, then the target moving vehicle data is used as lateral moving vehicle data.
[0103] After the VCU obtains the driving area of each target moving vehicle, in order to improve the screening efficiency and accuracy, it can remove false obstacles that may collide with the vehicle. When a moving vehicle crosses the preset collision area laterally, the generated false obstacles may collide with the vehicle, so it is necessary to determine the lateral moving vehicle data.
[0104] In this step, after the VCU obtains the driving area of each target moving vehicle data, each moving vehicle data includes a heading angle. For each target moving vehicle data, if the heading angle in the target moving vehicle data belongs to the preset lateral driving angle range, then the target moving vehicle data is regarded as lateral moving vehicle data.
[0105] It should be noted that "lateral" refers to the direction perpendicular to the vehicle's direction of travel.
[0106] It should be noted that the heading angle in the moving vehicle data is the angle between the vehicle's direction of travel and the vehicle's own direction of travel.
[0107] It should be noted that the preset lateral driving angle range can be [60°, 120°], [45°, 135°], [80°, 110°], etc. This application embodiment does not limit the preset lateral driving angle range, and it can be determined according to the actual situation.
[0108] S202: Based on the driving area of each lateral moving vehicle data, filter the stationary obstacles in the initial set of stationary obstacles to obtain the target obstacle.
[0109] It should be noted that this step is similar to step S104 in Embodiment 1, and will not be described again here.
[0110] The stationary obstacle screening method provided in this embodiment filters target moving vehicle data based on heading angle to obtain lateral moving vehicle data, and then filters stationary obstacles based on the driving area of the lateral moving vehicle data to obtain target obstacles. This method can improve the screening efficiency and accuracy of stationary obstacle screening.
[0111] Figure 3 This is a flowchart illustrating a third embodiment of the stationary obstacle screening method provided in this application. Based on the above embodiments, this application describes how the VCU brakes and issues an alarm based on the target obstacle after obtaining it. Figure 3 As shown, the static obstacle screening method specifically includes the following steps:
[0112] S301: For each target obstacle, calculate the collision distance and collision duration based on the target obstacle's position, the vehicle's current position, and the vehicle's speed.
[0113] In this step, after the VCU obtains the target obstacle, in order to improve vehicle safety and brake when a collision is about to occur, it is necessary to calculate the corresponding collision distance and collision duration for each target obstacle based on the position of the target obstacle, the current position of the vehicle, and the speed of the vehicle.
[0114] The collision distance to the target obstacle can be calculated based on the location of the target obstacle and the current position of the vehicle. Then, the collision distance is divided by the vehicle's speed to obtain the collision duration to the target obstacle.
[0115] S302: For each target obstacle, if the collision distance corresponding to the target obstacle is less than the preset collision distance threshold and the collision duration corresponding to the target obstacle is less than the preset collision duration threshold, then braking and alarm will be triggered.
[0116] In this step, after the VCU obtains the collision distance and collision duration corresponding to each target obstacle, if the collision distance corresponding to the target obstacle is less than the preset collision distance threshold and the collision duration corresponding to the target obstacle is less than the preset collision duration threshold, it indicates that a collision is about to occur, so braking is performed and an alarm is issued.
[0117] It should be noted that the preset collision distance threshold can be 1 meter, 5 meters, 10 meters, etc., and the preset collision duration threshold can be 0.5 seconds, 1 second, 3 seconds, etc. This application embodiment does not limit the preset collision distance threshold and the preset collision duration threshold, which can be determined according to the actual situation.
[0118] It should be noted that the alarm method can be: playing a collision alarm message through a speaker; displaying a collision alarm message on the vehicle's in-vehicle terminal and flashing lights; or sending a collision alarm message to the user's terminal device. This application embodiment does not limit the alarm method and can determine it according to the actual situation.
[0119] It should be noted that for each piece of moving vehicle data, if the movement position corresponding to each movement moment in the moving vehicle data belongs to the preset collision area, and the distance between the movement position corresponding to the latest movement moment in the moving vehicle data and the boundary of the preset collision area is greater than or equal to the preset departure distance, then the moving vehicle data is considered as parking vehicle data in the collision area. For each piece of parking vehicle data in the collision area, if the distance between the movement position corresponding to the latest movement moment in the parking vehicle data and the current position of the own vehicle is less than the preset door opening distance, then adjacent vehicle door opening monitoring is performed to detect whether the adjacent vehicle will collide with the own vehicle when opening its door. The preset door opening distance can be 1 meter, 1.2 meters, 1.5 meters, 2 meters, etc. This application embodiment does not limit the preset door opening distance and can be determined according to the actual situation.
[0120] The stationary obstacle screening method provided in this embodiment determines whether a collision is about to occur based on the position of the target obstacle, the current position of the vehicle, and the vehicle speed. When a collision is about to occur, braking and warning are performed, thereby improving vehicle safety.
[0121] The following are device embodiments of the present application, which can be used to implement the method embodiments of the present application. For details not disclosed in the device embodiments of the present application, please refer to the method embodiments of the present application.
[0122] Figure 4This is a schematic diagram of the structure of an embodiment of the stationary obstacle screening device provided in this application. Figure 4 As shown, the stationary obstacle screening device 40 includes:
[0123] The acquisition module 41 is used to acquire an initial set of stationary obstacles and millimeter-wave radar data within a preset time period before the current moment when the vehicle is in a low-speed driving scenario.
[0124] The filtering module 42 is used to filter all moving vehicle data according to a preset collision area if the millimeter-wave radar data includes moving vehicle data, so as to obtain the target moving vehicle data.
[0125] Processing module 43 is used to generate the driving area of each target moving vehicle data based on the target moving vehicle data;
[0126] The filtering module 42 is also used to filter the stationary obstacles in the initial set of stationary obstacles according to the driving area of each target moving vehicle data, so as to obtain the target obstacles.
[0127] Furthermore, each moving vehicle data includes multiple movement moments and the corresponding movement position at each movement moment; the filtering module 42 is specifically used for:
[0128] For each moving vehicle data, if the movement position corresponding to each movement moment in the moving vehicle data belongs to the preset collision area, and the distance between the movement position corresponding to the latest movement moment in the moving vehicle data and the boundary of the preset collision area is less than the preset departure distance, then the moving vehicle data is taken as the target moving vehicle data.
[0129] Furthermore, the processing module 43 is specifically used for:
[0130] Based on the movement position corresponding to each movement moment in the target moving vehicle data, the driving area of the target moving vehicle data is generated; or...
[0131] The driving area of the target moving vehicle data is generated based on the earliest movement time and the latest movement time in the target moving vehicle data.
[0132] Furthermore, the processing module 43 is specifically used for:
[0133] A driving trajectory is generated based on the movement position corresponding to each movement moment in the target moving vehicle data;
[0134] Based on the driving trajectory and preset width, the driving area of the target moving vehicle data is generated.
[0135] Furthermore, the filtering module 42 is specifically used for:
[0136] For each stationary obstacle in the initial set of stationary obstacles, if the obstacle type of the stationary obstacle is a vehicle and the position of the stationary obstacle belongs to the driving area of at least one target moving vehicle data, then the stationary obstacle is regarded as a false obstacle.
[0137] Each stationary obstacle in the initial set of stationary obstacles, excluding false obstacles, is taken as the target obstacle.
[0138] Furthermore, each moving vehicle data includes a heading angle. Before filtering the stationary obstacles in the initial set of stationary obstacles according to the driving area of each target moving vehicle data to obtain the target obstacle, the processing module 43 is also used to, for each target moving vehicle data, if the heading angle in the target moving vehicle data belongs to a preset lateral driving angle range, then treat the target moving vehicle data as lateral moving vehicle data.
[0139] The filtering module 42 is further configured to filter the stationary obstacles in the initial set of stationary obstacles based on the driving area of each lateral moving vehicle data to obtain the target obstacle.
[0140] Furthermore, the processing module 43 is also used for:
[0141] For each target obstacle, the collision distance and collision duration are calculated based on the position of the target obstacle, the current position of the vehicle, and the speed of the vehicle.
[0142] For each target obstacle, if the collision distance corresponding to the target obstacle is less than a preset collision distance threshold and the collision duration corresponding to the target obstacle is less than a preset collision duration threshold, then braking and an alarm will be triggered.
[0143] The static obstacle screening device provided in this embodiment is used to execute the technical solution in any of the aforementioned method embodiments. Its implementation principle and technical effect are similar, and will not be described again here.
[0144] Figure 5 This is a schematic diagram of the structure of an electronic device provided in this application. Figure 5 As shown, the electronic device 50 includes:
[0145] Processor 51, memory 52, and communication interface 53;
[0146] The memory 52 is used to store the executable instructions of the processor 51;
[0147] The processor 51 is configured to execute the technical solutions in any of the foregoing method embodiments by executing the executable instructions.
[0148] Optionally, the memory 52 can be independent or integrated with the processor 51.
[0149] Optionally, when the memory 52 is a device independent of the processor 51, the electronic device 50 may further include:
[0150] Bus 54, memory 52 and communication interface 53 are connected to processor 51 through bus 54 and complete communication with each other. Communication interface 53 is used to communicate with other devices.
[0151] Optionally, the communication interface 53 can be implemented using a transceiver. The communication interface is used to enable communication between the database access device and other devices (e.g., clients, read-write databases, and read-only databases). The memory may include random access memory (RAM) and may also include non-volatile memory, such as at least one disk drive.
[0152] Bus 54 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, only one thick line is used in the diagram, but this does not indicate that there is only one bus or one type of bus.
[0153] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.
[0154] The electronic device is used to execute the technical solution in any of the aforementioned method embodiments, and its implementation principles and technical effects are similar and will not be repeated here.
[0155] This application also provides a vehicle, which includes a vehicle controller.
[0156] The vehicle controller is used to execute the technical solutions in any of the aforementioned method embodiments. Its implementation principle and technical effect are similar, and will not be described again here.
[0157] This application also provides a readable storage medium storing a computer program thereon, which, when executed by a processor, implements the technical solutions provided in any of the foregoing method embodiments.
[0158] This application also provides a computer program product, including a computer program, which, when executed by a processor, is used to implement the technical solutions provided in any of the foregoing method embodiments.
[0159] Those skilled in the art will appreciate that all or part of the steps in the above-described method embodiments can be implemented using hardware associated with program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.
[0160] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.
Claims
1. A method for screening stationary obstacles, characterized in that, include: When the vehicle is traveling at low speed, it acquires an initial set of stationary obstacles and millimeter-wave radar data within a preset time period before the current moment. If the millimeter-wave radar data includes moving vehicle data, then according to the preset collision area, all moving vehicle data is filtered to obtain the target moving vehicle data; For each target moving vehicle data, the driving area of the target moving vehicle data is generated based on the target moving vehicle data; Based on the driving area of each target moving vehicle, the stationary obstacles in the initial set of stationary obstacles are filtered to obtain the target obstacles.
2. The method according to claim 1, characterized in that, Each moving vehicle's data includes multiple moments of movement, as well as the corresponding movement position for each moment of movement; The step of filtering all moving vehicle data according to the preset collision area to obtain target moving vehicle data includes: For each moving vehicle data, if the movement position corresponding to each movement moment in the moving vehicle data belongs to the preset collision area, and the distance between the movement position corresponding to the latest movement moment in the moving vehicle data and the boundary of the preset collision area is less than the preset departure distance, then the moving vehicle data is taken as the target moving vehicle data.
3. The method according to claim 2, characterized in that, The step of generating the driving area of the target moving vehicle data based on the target moving vehicle data includes: Based on the movement position corresponding to each movement moment in the target moving vehicle data, the driving area of the target moving vehicle data is generated; or... The driving area of the target moving vehicle data is generated based on the earliest movement time and the latest movement time in the target moving vehicle data.
4. The method according to claim 3, characterized in that, The step of generating the driving area of the target moving vehicle data based on the movement position corresponding to each movement moment in the target moving vehicle data includes: A driving trajectory is generated based on the movement position corresponding to each movement moment in the target moving vehicle data; Based on the driving trajectory and preset width, the driving area of the target moving vehicle data is generated.
5. The method according to claim 1, characterized in that, The step of filtering stationary obstacles in the initial set of stationary obstacles based on the driving area of each target moving vehicle data to obtain target obstacles includes: For each stationary obstacle in the initial set of stationary obstacles, if the obstacle type of the stationary obstacle is a vehicle and the position of the stationary obstacle belongs to the driving area of at least one target moving vehicle data, then the stationary obstacle is regarded as a false obstacle. Each stationary obstacle in the initial set of stationary obstacles, excluding false obstacles, is taken as the target obstacle.
6. The method according to any one of claims 1 to 5, characterized in that, Each moving vehicle data includes a heading angle. Before filtering stationary obstacles in the initial set of stationary obstacles based on the driving area of each target moving vehicle data to obtain the target obstacle, the method further includes: For each target moving vehicle data, if the heading angle in the target moving vehicle data belongs to a preset lateral travel angle range, then the target moving vehicle data is used as lateral moving vehicle data. The step of filtering stationary obstacles in the initial set of stationary obstacles based on the driving area of each target moving vehicle data to obtain target obstacles includes: Based on the driving area of each lateral moving vehicle, the stationary obstacles in the initial set of stationary obstacles are filtered to obtain the target obstacles.
7. The method according to any one of claims 1 to 5, characterized in that, The method further includes: For each target obstacle, the collision distance and collision duration are calculated based on the position of the target obstacle, the current position of the vehicle, and the speed of the vehicle. For each target obstacle, if the collision distance corresponding to the target obstacle is less than a preset collision distance threshold and the collision duration corresponding to the target obstacle is less than a preset collision duration threshold, then braking and an alarm will be triggered.
8. A static obstacle screening device, characterized in that, include: The acquisition module is used to acquire an initial set of stationary obstacles and millimeter-wave radar data within a preset time period before the current moment when the vehicle is traveling at low speed. The filtering module is used to filter all moving vehicle data according to a preset collision area if the millimeter-wave radar data includes moving vehicle data, so as to obtain the target moving vehicle data. The processing module is used to generate the driving area of each target moving vehicle data based on the target moving vehicle data. The filtering module is also used to filter the stationary obstacles in the initial set of stationary obstacles according to the driving area of each target moving vehicle data, so as to obtain the target obstacles.
9. An electronic device, characterized in that, include: Processor, memory, communication interface; The memory is used to store the executable instructions of the processor; The processor is configured to execute the static obstacle screening method according to any one of claims 1 to 7 by executing the executable instructions.
10. A vehicle, characterized in that, Including the vehicle controller; The vehicle controller is used to execute the stationary obstacle screening method according to any one of claims 1 to 7.