Radar point filtering method and device, vehicle-mounted terminal, vehicle and storage medium

Abstract

The embodiment of the invention discloses a radar point filtering method and device, a vehicle-mounted terminal, a vehicle and a storage medium. The method comprises the steps of determining a driving scene of a target vehicle according to vehicle driving information collected by a plurality of sensors on the target vehicle; and filtering radar point data collected by the target vehicle according to a filtering strategy corresponding to the driving scene to obtain a target radar point. Therefore, the driving scene of the target vehicle can be determined according to the vehicle driving information acquired by the plurality of sensors on the target vehicle, so that the radar point data acquired by the target vehicle can be filtered in a targeted manner according to the filtering strategy corresponding to the driving scene, and the radar point data can be filtered stably and accurately; and the accuracy of radar point filtering is effectively improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a radar point filtering method, device, vehicle-mounted terminal, vehicle and storage medium. Background Art

[0002] In intelligent driving scenarios, in order to ensure vehicle safety and more intelligent driving, filtering invalid radar points in radar data is an important step to improve the accuracy and efficiency of target detection. In existing radar point filtering methods, threshold judgment methods are often used for filtering. By setting one or more thresholds based on certain characteristics of radar points in radar point data (such as distance, speed, acceleration, etc.), radar points that exceed these thresholds are regarded as invalid points and filtered.

[0003] However, due to the complex vehicle driving scenarios, existing radar point filtering methods cannot stably and accurately filter radar point data, resulting in low accuracy of radar point filtering. Summary of the invention

[0004] The embodiments of the present application provide a radar point filtering method, device, vehicle-mounted terminal, vehicle and storage medium, which can stably and accurately filter radar point data and improve the accuracy of radar point filtering.

[0005] In order to achieve the above object, according to a first aspect of the present application, a radar point filtering method is provided, the method comprising:

[0006] Determining a driving scene of the target vehicle based on vehicle driving information collected by multiple sensors on the target vehicle;

[0007] According to the filtering strategy corresponding to the driving scene, the radar point data collected by the target vehicle is filtered to obtain the target radar point.

[0008] In some embodiments, the vehicle driving information includes at least one of the driving speed information and driving road surface information of the target vehicle.

[0009] In some embodiments, determining the driving scene of the target vehicle based on the vehicle driving information collected by multiple sensors on the target vehicle includes: determining the driving scene of the target vehicle based on the driving speed information and / or driving road surface information in the vehicle driving information collected by multiple sensors on the target vehicle.

[0010] In some embodiments, determining the driving scene of the target vehicle based on the driving speed information and / or driving road surface information in the vehicle driving information collected by multiple sensors on the target vehicle includes: if the driving speed information in the vehicle driving information collected by multiple sensors on the target vehicle meets a preset speed condition, judging that the target vehicle is in a first driving scene.

[0011] In some embodiments, the driving scene of the target vehicle is determined based on the driving speed information and / or driving road surface information in the vehicle driving information collected by multiple sensors on the target vehicle, including: if the driving speed information in the vehicle driving information collected by multiple sensors on the target vehicle does not meet the preset speed condition, processing the driving road surface information in the vehicle driving information to determine whether there is a target edge on the driving road surface of the target vehicle; in the case where the target edge exists on the driving road surface, confirming that the target vehicle is in the second driving scene; in the case where the target edge does not exist on the driving road surface, confirming that the target vehicle is in the third driving scene.

[0012] In some embodiments, when the target vehicle is in a first driving scenario, filtering the radar point data collected by the target vehicle according to a filtering strategy corresponding to the driving scenario to obtain a target radar point includes: obtaining the target vehicle and a distance value between each radar point in the radar point data collected by the target vehicle; if the distance value is not less than a preset distance threshold, filtering the radar point; if the distance value is less than the preset distance threshold, determining the radar point as a target radar point.

[0013] In some embodiments, when the target vehicle is in a second driving scenario, filtering the radar point data collected from the target vehicle according to a filtering strategy corresponding to the driving scenario to obtain a target radar point includes: determining the type of target edges existing in the driving road surface, the target edges including a first target edge and a second target edge; if the first target edge exists in the driving road surface, obtaining a filtering boundary equation on both sides of the target vehicle determined based on the position information of the first target edge; if the first target edge does not exist in the driving road surface and the second target edge exists, determining a curve equation corresponding to an extended edge line of the second target edge based on the position information of the second target edge as the filtering boundary equation on both sides of the target vehicle; based on the filtering boundary equation on both sides of the target vehicle, filtering the radar point data collected from the target vehicle to obtain a target radar point.

[0014] In one embodiment, filtering the radar point data collected from the target vehicle based on the filtering boundary equations on both sides of the target vehicle to obtain the target radar point includes: obtaining the position coordinates of each radar point in the radar point data collected from the target vehicle, the position coordinates including the longitudinal position coordinates and the lateral position coordinates of the radar point relative to the target vehicle; calculating the values ​​of the filtering boundary equations on both sides of the target vehicle at the longitudinal position coordinates to obtain a first lateral position coordinate and a second lateral position coordinate; if the lateral position coordinate is between the first lateral position coordinate and the second lateral position coordinate, determining the radar point as the target radar point.

[0015] In some embodiments, the obtaining of filtering boundary equations on both sides of the target vehicle determined based on the position information of the first target edge includes: when there are first target edges on both sides of the target vehicle, obtaining curve equations calculated based on the position information of the first target edge as filtering boundary equations on both sides of the target vehicle; when the first target edge exists on only one side of the target vehicle, translating the curve equation corresponding to the first target edge based on a preset lane width, and determining the translated curve equations and the curve equation corresponding to the first target edge as filtering boundary equations on both sides of the target vehicle.

[0016] In some embodiments, the determining of the curve equation corresponding to the extended edge line of the second target edge based on the position information of the second target edge includes: when there are second target edges on both sides of the target vehicle, expanding the curve equations corresponding to each of the second target edges based on a preset lane width to obtain the curve equation corresponding to the extended edge line of the second target edge; when the second target edge exists only on one side of the target vehicle, expanding the curve equation corresponding to the second target edge based on the preset lane width, and translating the expanded curve equation based on the preset lane width to obtain the curve equations corresponding to the extended edge lines on both sides of the target vehicle.

[0017] In some embodiments, when the target vehicle is in a third driving scenario, filtering the radar point data collected from the target vehicle according to a filtering strategy corresponding to the driving scenario to obtain a target radar point includes: determining a predicted driving area of ​​the target vehicle according to driving speed information in the vehicle driving information; and determining, based on position information of each radar point in the radar point data, a radar point in the radar point data that is within the predicted driving area as a target radar point.

[0018] In some embodiments, the driving speed information includes the driving speed and yaw angular velocity of the target vehicle, and determining the predicted driving area of ​​the target vehicle based on the driving speed information in the vehicle driving information includes: calculating the circumferential radius and the center point of motion of the target vehicle in uniform circular motion based on the driving speed and the yaw angular velocity; determining the predicted driving path of the target vehicle based on the circumferential radius and the center point of motion; expanding the predicted driving path in the direction approaching and away from the center point of motion according to a preset lane width to obtain an expanded predicted driving path; and determining the predicted driving area of ​​the target vehicle based on the expanded predicted driving path.

[0019] In some embodiments, the method further includes: determining a dynamic target in the driving scene of the target vehicle through the vehicle driving information; and when the dynamic target meets a preset condition, controlling the radar point data corresponding to the dynamic target to be included in the target radar point.

[0020] In some embodiments, when the dynamic target meets a preset condition, controlling the radar point data corresponding to the dynamic target to be included in the target radar point includes: obtaining the lateral movement speed of the dynamic target relative to the target vehicle; when the lateral movement speed is greater than a preset speed threshold, controlling the radar point data that is on the same side of the target vehicle as the dynamic target and whose longitudinal distance to the dynamic target is within a preset distance to be included in the target radar point.

[0021] According to a second aspect of the present application, a radar point filtering device is provided, the device comprising:

[0022] A determination module, used to determine the driving scene of the target vehicle according to the vehicle driving information collected by multiple sensors on the target vehicle;

[0023] The filtering module is used to filter the radar point data collected by the target vehicle according to the filtering strategy corresponding to the driving scene to obtain the target radar point.

[0024] According to a third aspect of the present application, a vehicle-mounted terminal is provided, including a processor and a memory, wherein the memory stores an application program, and the processor is used to run the application program in the memory to implement the radar point filtering method provided in an embodiment of the present application.

[0025] According to a fourth aspect of the present application, a vehicle is provided, comprising the vehicle-mounted terminal provided by the third aspect of the present application.

[0026] According to a fifth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and the computer program is suitable for being loaded by a processor to execute the steps in any radar point filtering method provided in the embodiments of the present application.

[0027] According to the sixth aspect of the present application, a computer program product is provided, which includes a computer program, and the computer program is stored in a computer-readable storage medium; when the processor of a vehicle-mounted terminal reads the computer program from the computer-readable storage medium, the processor executes the computer program, so that the vehicle-mounted terminal performs the steps in the radar point filtering method provided in an embodiment of the present application.

[0028] In the radar point filtering method, device, vehicle-mounted terminal, vehicle and storage medium of the embodiment of the present application, the driving scene of the target vehicle is determined according to the vehicle driving information collected by multiple sensors on the target vehicle; according to the filtering strategy corresponding to the driving scene, the radar point data collected by the target vehicle is filtered to obtain the target radar point. In this way, the driving scene of the target vehicle can be determined according to the vehicle driving information collected by multiple sensors on the target vehicle, so that the radar point data collected by the target vehicle can be filtered in a targeted manner according to the filtering strategy corresponding to the driving scene, so as to achieve stable and accurate filtering of the radar point data in a variety of driving scenes, thereby effectively improving the accuracy of radar point filtering. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0030] Figure 1 This is a schematic diagram of an implementation scenario of a radar point filtering method provided in an embodiment of the present application;

[0031] Figure 2 It is a flow chart of a radar point filtering method provided in an embodiment of the present application;

[0032] Figure 3 It is a specific flow chart of a radar point filtering method provided in an embodiment of the present application;

[0033] Figure 4a It is a schematic diagram of a specific scenario of a radar point filtering method provided in an embodiment of the present application;

[0034] Figure 4bis another specific scenario schematic diagram of a radar point filtering method provided in an embodiment of the present application;

[0035] Figure 5 is a schematic diagram of the structure of a radar point filtering device provided in an embodiment of the present application;

[0036] Figure 6 It is a structural diagram of the vehicle-mounted terminal provided in an embodiment of the present application. DETAILED DESCRIPTION

[0037] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0038] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0039] The embodiment of the present application provides a radar point filtering method, device, vehicle-mounted terminal, vehicle and storage medium. The radar point filtering device can be integrated in an electronic device, which can be a server, a terminal or other device.

[0040] Among them, the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, network acceleration services (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms. Terminals may include but are not limited to mobile phones, computers, intelligent voice interaction devices, smart home appliances, vehicle-mounted terminals, aircraft, etc. Terminals and servers can be directly or indirectly connected via wired or wireless communications, and this application does not limit this.

[0041] Among them, the vehicle-mounted terminal can be integrated in a vehicle, and the vehicle can be a fuel vehicle, a plug-in hybrid vehicle or a new energy vehicle, etc. This application does not make specific limitations on this.

[0042] See also Figure 1, taking the radar point filtering device integrated into the vehicle terminal as an example, Figure 1 A schematic diagram of an implementation scenario of the radar point filtering method provided in an embodiment of the present application, wherein the vehicle-mounted terminal may be integrated on a vehicle, and the vehicle-mounted terminal may determine the driving scenario of the target vehicle based on the vehicle driving information collected by multiple sensors on the target vehicle; and filter the radar point data collected from the target vehicle according to a filtering strategy corresponding to the driving scenario to obtain a target radar point.

[0043] It should be noted that Figure 1 The implementation environment scenario diagram of the radar point filtering method shown is only an example. The implementation environment scenario of the radar point filtering method described in the embodiment of the present application is to more clearly illustrate the technical solution of the embodiment of the present application, and does not constitute a limitation on the technical solution provided by the embodiment of the present application. It is known to those skilled in the art that with the evolution of data processing and the emergence of new business scenarios, the technical solution provided by the present application is also applicable to similar technical problems.

[0044] The solutions provided in the embodiments of the present application are specifically described by the following embodiments. It should be noted that the description order of the following embodiments is not intended to limit the preferred order of the embodiments.

[0045] This embodiment will be described from the perspective of a radar point filtering device, which can be specifically integrated in a vehicle-mounted terminal.

[0046] See also Figure 2 , Figure 2 : is a flow chart of a radar point filtering method provided in an embodiment of the present application. The radar point filtering method comprises:

[0047] Step S101, determining a driving scene of a target vehicle according to vehicle driving information collected by multiple sensors on the target vehicle.

[0048] The target vehicle may be a vehicle currently being filtered by radar points, and the vehicle driving information may be information collected during the driving process of the target vehicle, which may be used to describe the driving state of the target vehicle, for example, it may include at least one of the driving speed information and the driving road surface information of the target vehicle. The driving speed information may include the driving speed, acceleration, heading angle and other information of the target vehicle, and the driving road surface information may be information collected based on visual perception technology, which is used to perceive the roadside line, lane line and other information of the driving road surface of the target vehicle. The driving scene may be a scene in which the target vehicle is located during the driving process, for example, it may include driving scenes such as low-speed driving scenes, non-low-speed driving scenes with edge lines, and non-low-speed driving scenes without edge lines. The low-speed driving scene may refer to a scene in which the driving speed of the target vehicle is less than a preset speed threshold, and the preset speed threshold may be a pre-set speed threshold. When the driving speed of the vehicle is less than the speed threshold, it may indicate that the vehicle is driving at a low speed, and when the driving speed of the vehicle is not less than the speed threshold, it may indicate that the vehicle is not driving at a low speed. The specific value of the preset speed threshold may be set according to actual conditions, for example, it may be 5km / h, 6km / h, 8km / h, etc. A non-low-speed driving scenario with edge lines may refer to a scenario in which the target vehicle is driving on a road with curb lines or lane lines, and the driving speed is not less than a preset speed threshold. A non-low-speed driving scenario without edge lines may refer to a scenario in which the target vehicle is driving on a road without curb lines and lane lines, and the driving speed is not less than a preset speed threshold.

[0049] Among them, there are many ways to determine the driving scene of the target vehicle based on the vehicle driving information collected by multiple sensors on the target vehicle. For example, the driving scene of the target vehicle can be determined based on the driving speed information and / or driving road surface information in the vehicle driving information collected by multiple sensors on the target vehicle.

[0050] Among them, there can be multiple ways to determine the driving scene of the target vehicle based on the driving speed information and / or driving road surface information in the vehicle driving information collected by multiple sensors on the target vehicle. For example, if the driving speed information in the vehicle driving information collected by multiple sensors on the target vehicle meets the preset speed condition, it is judged that the target vehicle is in the first driving scene.

[0051] Among them, the first driving scenario can be a low-speed driving scenario, and the preset speed condition can be that the driving speed is less than a preset speed threshold, so that the driving speed of the target vehicle can be determined based on the driving speed information in the vehicle driving information collected by multiple sensors on the target vehicle. When the driving speed of the target vehicle is less than the preset speed threshold, that is, when the driving speed information meets the preset speed condition, it is determined that the target vehicle is in the first driving scenario.

[0052] Optionally, there may be multiple ways to determine the driving scene of the target vehicle based on the driving speed information and / or driving road surface information in the vehicle driving information collected by multiple sensors on the target vehicle. For example, if the driving speed information in the vehicle driving information collected by multiple sensors on the target vehicle does not meet the preset speed condition, the driving road surface information in the vehicle driving information may be processed to determine whether there is a target edge on the driving road surface of the target vehicle. If there is a target edge on the driving road surface, it is confirmed that the target vehicle is in the second driving scene. If there is no target edge on the driving road surface, it is confirmed that the target vehicle is in the third driving scene.

[0053] Among them, the target edge can be an edge line on the road surface where the target vehicle is driving, the target edge can include a roadside line and a lane line, the second driving scene can be a non-low-speed driving scene with an edge line, and the third driving scene can be a non-low-speed driving scene without an edge line.

[0054] Step S102: filtering the radar point data collected by the target vehicle according to a filtering strategy corresponding to the driving scene to obtain the target radar point.

[0055] Among them, the filtering strategy can be a strategy for filtering the radar point data collected by the target vehicle. The radar point data can include multiple radar points, which can be a collection of radar points obtained by radar detection on the surface of the object around the target vehicle. The radar point can be a radar point corresponding to the radar point sampled on the surface of the object around the target vehicle based on the radar detection technology. Each radar point can contain information such as the position and speed of the object (i.e., the radar detection target). The target radar point can be the radar point data from which invalid points are filtered, i.e., the valid radar points in the radar point data. The invalid points in the radar point data can be radar points that have no effect on the normal driving and safety detection of the target vehicle. When collecting the radar point data corresponding to the object around the target vehicle, some radar points that have no effect or little effect on the driving of the target vehicle are often collected, i.e., the invalid points in the radar point data. In order to improve the analysis efficiency of the radar point data, the invalid radar points in the collected radar point data can be filtered, thereby improving the accuracy of the radar point data, and then improving the safety and reliability of the intelligent driving scene.

[0056] The coordinate system of the surrounding objects of the target vehicle (i.e., the detection target) can be a self-vehicle coordinate system with the self-vehicle position of the target vehicle as the origin, and the self-vehicle coordinate system of the target vehicle can be a self-vehicle coordinate system with the direction pointed by the front of the target vehicle (the driving direction of the self-vehicle) as the X-axis, and the direction pointing to the left side of the vehicle and perpendicular to the X-axis as the Y-axis. In the self-vehicle coordinate system, the coordinates on the X-axis are all called ordinates, and the coordinates on the Y-axis are all called abscissas. The position and speed of the radar point in the radar point data can be values ​​relative to the self-vehicle position and speed of the target vehicle.

[0057] Among them, according to the filtering strategy corresponding to the driving scene, the radar point data collected by the target vehicle is filtered, and there are many ways to obtain the target radar point. For example, when the target vehicle is in the first driving scene, the distance value between the target vehicle and each radar point in the radar point data collected by the target vehicle can be obtained; if the distance value is not less than the preset distance threshold, the radar point is filtered; if the distance value is less than the preset distance threshold, the radar point is determined as the target radar point.

[0058] Among them, the distance value may be information indicating the distance between each radar point in the radar point data collected by the target vehicle and the target vehicle, and the distance value may include a lateral distance value and a longitudinal distance value. For example, the position coordinates of each radar point in the radar point data in the self-vehicle coordinate system may be obtained, and the position coordinates may include a longitudinal position coordinate (XPos) and a lateral position coordinate (YPos). The longitudinal position coordinate may be the longitudinal distance from the radar point to the target vehicle, that is, the longitudinal distance value, and the lateral position coordinate may be the lateral distance from the radar point to the target vehicle. For the radar point detected by the radar, its corresponding position coordinate may be calculated by the relative position relationship between the target vehicle and the radar and the detection data of the radar. Thus, the distance value between each radar point in the radar point data and the target vehicle may be obtained according to the position coordinates of the radar point. The preset distance threshold may be a preset critical value of the distance. When the distance between the radar point and the target vehicle is greater than the critical value, the corresponding radar point may be regarded as an invalid point for filtering. Correspondingly, the preset distance threshold may include a preset lateral distance threshold and a preset longitudinal distance threshold.

[0059] When the speed of the target vehicle is lower than the preset speed threshold (e.g., 5km / h), the target vehicle can be considered to be in a low-speed driving state. When driving at a low speed, the sensor data far away from the vehicle has a relatively small impact on the vehicle's driving. Therefore, the radar point data far away from the vehicle can be filtered, so as to focus on the radar point data near the vehicle to analyze the vehicle-related data. In this case, there is no need to consider an overly complex filtering algorithm, and filtering can be performed based on the position of each radar point in the radar point data relative to the target vehicle. In this way, when the longitudinal distance value of the radar point in the radar point data relative to the target vehicle is not less than the preset longitudinal distance threshold, the radar point can be filtered as an invalid point, and when the absolute value of the lateral distance value of the radar point in the radar point data relative to the target vehicle is not less than the preset lateral distance threshold, the radar point can be filtered as an invalid point. In this way, the invalid radar points in the radar point data can be filtered to obtain the target radar point.

[0060] Among them, the preset longitudinal distance threshold can be a preset longitudinal distance threshold. When the longitudinal distance value between the radar point and the target vehicle is greater than the threshold, it can be indicated that the distance between the radar point and the target vehicle is relatively far, and the impact on the driving process of the target vehicle is relatively small. The preset lateral distance threshold can be a preset lateral distance threshold. When the lateral distance value between the radar point and the target vehicle is greater than the threshold, it can be indicated that the distance between the radar point and the target vehicle is relatively far, and the impact on the driving process of the target vehicle is relatively small. The specific values ​​of the preset longitudinal distance threshold and the preset lateral distance threshold can be set according to actual conditions. For example, the preset longitudinal distance threshold can be 20 meters, 25 meters, etc., and the preset lateral distance threshold can be 2.5 meters, 3 meters, etc.

[0061] In one embodiment, Figure 3 : This is a specific flow chart of a radar point filtering method provided by an embodiment of the present application. Taking the preset speed threshold of 5 km / h, the preset longitudinal distance threshold of 20 meters, and the preset lateral distance threshold of 2.5 meters as an example, when the self-vehicle speed of the target vehicle is lower than 5 km / h, it can be determined that the current scene is the first driving scene, so that the filtering conditions under the first driving scene can be determined as XPos>=20m, and |YPos|>=2.5m. Specifically, the position coordinates of each radar point can be obtained. When the longitudinal position XPos of the radar point is greater than 20 meters, it can be considered that the radar point is too far from the target vehicle and can be regarded as an invalid point for filtering. When the absolute value of the lateral position YPos of the radar point is greater than 2.5 meters, it can be considered that the radar point is too far from the target vehicle. For low-speed driving scenes, the radar point can also be regarded as an invalid point for filtering, so that the target radar point can be obtained.

[0062] Optionally, when the target vehicle is in the second driving scenario, the step of filtering the radar point data collected from the target vehicle according to the filtering strategy corresponding to the driving scenario to obtain the target radar point may include: determining the type of target edge existing in the driving road surface, the target edge including a first target edge and a second target edge; if there is a first target edge in the driving road surface, obtaining a filtering boundary equation on both sides of the target vehicle determined based on the position information of the first target edge; if there is no first target edge in the driving road surface and there is a second target edge, determining a curve equation corresponding to the extended edge line of the second target edge based on the position information of the second target edge as the filtering boundary equation on both sides of the target vehicle; based on the filtering boundary equation on both sides of the target vehicle, filtering the radar point data collected from the target vehicle to obtain the target radar point.

[0063] Among them, the first target edge can be a roadside line, a left-left lane line or a right-right lane line (i.e., LL\RR lane line), the left-left lane line can be the second lane line on the left side of the target vehicle, the right-right lane line can be the second lane line on the right side of the target vehicle, the second target edge can be a left lane line or a right lane line (i.e., L\R lane line), the left lane line can be the first lane line on the left side of the target vehicle, and the right lane line can be the first lane line on the right side of the target vehicle. The filtering boundary equation can be a curve equation of the boundary for filtering radar point data determined based on the target edge. The extended edge line can be an edge line after the second target edge is extended. The curve equation of the roadside line can be a roadside line equation, the curve equation of the lane line can be a lane line equation, the roadside line equation and the lane line equation can be a cubic curve equation, and the lane perception data of the target vehicle obtained by visual perception and other technologies can be used to construct the equation of the lane line or the roadside line, so as to obtain the curve equation of the roadside line or the lane line on both sides of the lane where the target vehicle is located. The position information of the target edge can be determined based on the sampling points on the target edge collected by the target vehicle through visual perception technology.

[0064] Among them, there can be multiple ways to obtain the filtering boundary equations on both sides of the target vehicle determined based on the position information of the first target edge. For example, when the first target edge exists on both sides of the target vehicle, the curve equation calculated based on the position information of the first target edge can be obtained as the filtering boundary equations on both sides of the target vehicle; when the first target edge exists on only one side of the target vehicle, the curve equation corresponding to the first target edge is translated based on the preset lane width, and the translated curve equation and the curve equation corresponding to the first target edge are determined as the filtering boundary equations on both sides of the target vehicle.

[0065] Among them, the preset lane width can be the width of a preset lane, which can be a value such as 3.5 meters, 4 meters, etc. The specific value can be set according to actual conditions.

[0066] There are multiple ways to translate the curve equation corresponding to the first target edge based on the preset lane width. For example, when the first target edge is a curb existing on one side, the curve equation corresponding to the existing first target edge (i.e., the curb equation) can be translated to the opposite side by two preset lane widths to obtain the translated curve equation. For example, when there is a curb on the left side, the curb equation of the left curb can be translated to the right by two preset lane widths relative to the target vehicle to obtain the translated curve equation of the virtual curb located on the right side of the target vehicle. When the first target edge is a left-left lane line or a right-right lane line existing on one side, the curve equation corresponding to the existing first target edge (i.e., the lane equation of the left-left lane line or the right-right lane line) can be translated to the opposite side by three preset lane widths to obtain the translated curve equation. For example, when there is a left-left lane line, the lane equation of the left-left lane line can be translated to the right by three preset lane widths relative to the target vehicle to obtain the translated curve equation of the virtual right-right lane line corresponding to the target vehicle.

[0067] Among them, based on the position information of the second target edge, there can be multiple ways to determine the curve equation corresponding to the extended edge line of the second target edge. For example, when there are second target edges on both sides of the target vehicle, the curve equations corresponding to the second target edges are expanded based on the preset lane width to obtain the curve equations corresponding to the extended edge lines of the second target edges; when the second target edge exists only on one side of the target vehicle, the curve equations corresponding to the second target edge are expanded based on the preset lane width, and the expanded curve equations are translated based on the preset lane width to obtain the curve equations corresponding to the extended edge lines on both sides of the target vehicle.

[0068] Among them, there are many ways to expand the curve equation corresponding to each second target edge based on the preset lane width to obtain the curve equation corresponding to the expanded edge line of the second target edge. For example, the curve equation corresponding to the second target edge on the left side of the target vehicle can be expanded to the left by a preset lane width, and the curve equation corresponding to the second target edge on the right side of the target vehicle can be expanded to the right by a preset lane width to obtain the curve equations corresponding to the expanded edge lines of the second target edges on both sides.

[0069] Among them, there are many ways to expand the curve equation corresponding to the second target edge based on the preset lane width, and translate the expanded curve equation based on the preset lane width to obtain the curve equation corresponding to the extended edge line on both sides of the target vehicle. For example, the curve equation corresponding to the second target edge on one side can be expanded to the side by a preset lane width to obtain the expanded curve equation, and then the expanded curve equation is translated to the opposite side by three preset lane widths, so that the expanded curve equation before and after the translation is used as the curve equation corresponding to the extended edge line on both sides of the target vehicle.

[0070] After obtaining the filtering boundary equations on both sides of the target vehicle, the radar point data collected by the target vehicle can be filtered based on the filtering boundary equations on both sides of the target vehicle to obtain the target radar point. There are multiple ways to filter the radar point data collected by the target vehicle based on the filtering boundary equations on both sides of the target vehicle to obtain the target radar point. For example, the position coordinates of each radar point in the radar point data collected by the target vehicle can be obtained, and the position coordinates include the longitudinal position coordinates and the lateral position coordinates of the radar point relative to the target vehicle. The values ​​of the filtering boundary equations on both sides of the target vehicle are calculated at the longitudinal position coordinates to obtain the first lateral position coordinate and the second lateral position coordinate. If the lateral position coordinate is between the first lateral position coordinate and the second lateral position coordinate, the radar point is determined as the target radar point.

[0071] The position coordinates may be expressed as (XPos, YPos), wherein XPos may be expressed as the longitudinal position coordinate of the radar point relative to the target vehicle, and YPos may be expressed as the lateral position coordinate of the radar point relative to the target vehicle. The first lateral position coordinate may be the value of the filter boundary equation on the left side of the target vehicle at the longitudinal position coordinate XPos of the radar point, and the second lateral position coordinate may be the value of the filter boundary equation on the right side of the target vehicle at the longitudinal position coordinate XPos of the radar point.

[0072] For example, based on the filtering boundary equations on both sides of the target vehicle, the filtering condition for filtering the radar point data collected from the target vehicle can be expressed as YPos>=LE(XPos)||YPos<=RE(XPos), wherein LE() can represent the filtering boundary equation on the left side of the target vehicle, LE(XPos) can be expressed as the first lateral position coordinate, RE() can represent the filtering boundary equation on the right side of the target vehicle, and RE(XPos) can be expressed as the second lateral position coordinate, so that when the lateral position coordinate of the radar point YPos>=LE(XPos), the radar point can be filtered out as an invalid point, or, when the lateral position coordinate of the radar point YPos<=RE(XPos), the radar point can be filtered out as an invalid point, so that the radar point with a lateral position coordinate between the first lateral position coordinate and the second lateral position coordinate can be determined as a target radar point for retention.

[0073] Specifically, when there is a first target edge on the road surface where the target vehicle is traveling, that is, when there is a roadside line on the road surface where the target vehicle is traveling, the filtering conditions for the radar points in the radar point data may include:

[0074] YPos>=LeftRoadEdge(XPos)||YPos<=RightRoadEdge(XPos)

[0075] Among them, LeftRoadEdge() can be the roadside equation on the left side of the target vehicle, that is, the filtering boundary equation on the left side of the target vehicle, and RightRoadEdge() can be the roadside equation on the right side of the target vehicle, that is, the filtering boundary equation on the right side of the target vehicle.

[0076] When there is no roadside line but a lane line on the road surface where the target vehicle is traveling, the filtering conditions for the radar points in the radar point data may include:

[0077] YPos>=LLEdge(XPos)||YPos<=RREdge(XPos)

[0078] Among them, LLEdge() can be the curve equation of the left lane line of the target vehicle, that is, the filtering boundary equation on the left side of the target vehicle, and RREdge() can be the curve equation of the right lane line of the target vehicle, that is, the filtering boundary equation on the right side of the target vehicle.

[0079] When the first target edge does not exist on the driving road of the target vehicle, but the second target edge exists, the filtering conditions for the radar points in the radar point data may include:

[0080] YPos>=LEdge(XPos)+LaneWidth||YPos<=REdge(XPos)-LaneWidth

[0081] Among them, LaneWidth can be the preset lane width, LEdge(XPos) can be the curve equation of the left lane line of the target vehicle, LEdge()+LaneWidth is the filtering boundary equation on the left side of the target vehicle, REdge() can be the curve equation of the right lane line of the target vehicle, and REdge(XPos)-LaneWidth is the filtering boundary equation on the right side of the target vehicle.

[0082] For example, please refer to Figure 3 ,Since the curb usually represents the edge of the road, objects beyond these boundaries usually do not enter the lane, thus not affecting the normal driving of the target vehicle. Therefore, when the target vehicle is driving in a scene with a curb and not at a low speed, the curb information can be an important basis for judging the validity of the radar point in the radar point data. In this case, the curb has the highest filtering priority. Therefore, when there is a curb on the road surface where the target vehicle is driving, the curve equation constructed based on the position of the curb can be set as the filtering boundary equation. First, it is necessary to obtain the curve equations of the curbs on the left and right sides of the target vehicle, that is, the curb equations. These equations can be obtained through image processing and data analysis methods of the visual sensor. Then, the longitudinal position XPos of the radar point can be substituted into the curb equation to calculate the corresponding lateral position. If the lateral position YPos of a radar point exceeds the calculated lateral position, the radar point can be filtered as an invalid point. When there is only a roadside line on one side, the curve equation of the existing roadside line on one side can be translated by two preset lane widths as the filtering boundary equation on the other side, so as to ensure that the radar points far away from the edge of the road where the target vehicle is located are filtered out to avoid them from interfering with the subsequent data processing and analysis. When the roadside line information does not exist, the LL / RR lane line will be used as the second priority filtering boundary. If the LL / RR lane lines on both sides exist, the curve equations using the LL lane line and the RR lane line can be used as the filtering boundary equations on both sides. If there is only a LL lane line or a RR lane line on one side, the curve equation of the existing lane line can be translated by three lane widths to the other side as the filtering boundary equation on the other side. If there are only L / R lane lines in the driving scene, the L / R lane line equations can be extended outward by a preset lane width to form a virtual LL / RR lane line, which can be used as the filtering boundary equations on both sides of the target vehicle. When there is only a single-side L / R lane line, the filtering boundary equation on the other side can be calculated according to the processing method when there is a single-side LL / RR lane line.

[0083] Optionally, when the target vehicle is in a third driving scenario, for the step of filtering the radar point data collected from the target vehicle according to the filtering strategy corresponding to the driving scenario to obtain the target radar point, the predicted driving area of ​​the target vehicle can be determined according to the driving speed information in the vehicle driving information, and based on the position information of each radar point in the radar point data, the radar point in the radar point data that is within the predicted driving area can be determined as the target radar point.

[0084] The preset driving area may be a predicted possible driving area of ​​the target vehicle, or an area that affects the normal driving of the target vehicle. The position information of the radar point may be information indicating the position of the radar point relative to the target vehicle, for example, it may include the position coordinates of the radar point in the self-vehicle coordinate system of the target vehicle, so that it can be determined whether each radar point is in the preset driving area based on the position coordinates, so that the radar points that are not in the preset driving area can be filtered out as invalid radar points, and the radar points in the preset driving area can be retained as target radar points.

[0085] There are many ways to determine the predicted driving area of ​​the target vehicle based on the driving speed information in the vehicle driving information. For example, the driving speed information includes the driving speed and yaw angular velocity of the target vehicle. The radius of the circle and the center point of the uniform circular motion of the target vehicle can be calculated based on the driving speed and the yaw angular velocity. The predicted driving path of the target vehicle is determined based on the radius of the circle and the center point of the motion. The predicted driving path is extended along the direction approaching and away from the center point of the motion according to the preset lane width to obtain the extended predicted driving path. The predicted driving area of ​​the target vehicle is determined based on the extended predicted driving path.

[0086] Among them, in the third driving scenario, it can be assumed that the target vehicle performs uniform circular motion, so that the driving speed (Speed) of the target vehicle can represent the linear speed of the target vehicle performing circular motion, and the driving yaw rate (YawRate) can represent the angular velocity of the target vehicle performing circular motion. The circumference radius can be the radius of the target vehicle performing uniform circular motion, the center point of motion can be the center of the target vehicle performing uniform circular motion, and the predicted driving path can be the trajectory curve of the target vehicle performing uniform circular motion.

[0087] In the third driving scenario, the target vehicle is driving in a scene without lane lines. Due to the lack of clear lane boundary information, the target vehicle's driving state information can be relied on to predict the vehicle's future driving area, and the radar points can be filtered accordingly. In this case, the vehicle's driving state information, especially the vehicle speed (Speed) and the driving yaw rate (YawRate), become key parameters. Therefore, it can be assumed that the target vehicle's driving yaw rate and driving speed remain relatively stable within a single calculation cycle, and do not change significantly. In most cases, the vehicle's driving state is relatively stable in a short period of time and will not undergo drastic mutations. Therefore, this assumption is reasonable. Based on this assumption, it can be considered that the vehicle is traveling in uniform circular motion.

[0088] There are many ways to calculate the radius of the circle and the center point of the uniform circular motion of the target vehicle based on the vehicle speed and the yaw rate. For example, the radius of the circular motion can be calculated using the following formula:

[0089]

[0090] Among them, R can be the radius of the circle, (Speed) can represent the linear speed of the target vehicle in circular motion, and the yaw rate (YawRate) can represent the angular velocity of the target vehicle in circular motion, so that the center point of the circular motion can be determined based on the radius of the circle. Based on the geometric relationship, the distance between the future driving path of the target vehicle and the center point of motion is always maintained as the radius of the circle R, which represents the future driving range of the vehicle. However, since this path prediction method is relatively simple, it may not be able to fully cover all situations that the target vehicle may encounter in actual driving. Therefore, in order to prevent the filtering out of valid radar points, the predicted driving path can be expanded to a certain extent.

[0091] There are many ways to expand the predicted driving path according to the preset lane width in the direction close to and away from the center of motion to obtain the expanded predicted driving path. For example, the predicted driving path can be expanded outward by two preset lane widths to obtain the expanded predicted driving path. The two expanded predicted driving paths can form a circular area. For example, please refer to Figure 4a , Figure 4aIt is a schematic diagram of a specific scenario of a radar point filtering method provided by an embodiment of the present application. Among them, the solid arc is the predicted driving path S, whose circumferential radius is R. The extended predicted driving path includes S1 and S2. Among them, the circumferential radius of S1 is the inner radius of this circular ring area, that is, R - 2×LaneWidth, and the circumferential radius of S2 is the outer radius of the circular ring area, that is, R + 2×LaneWidth. In this way, the circular ring area formed by the two extended predicted driving paths can be determined as the predicted driving area, so that the radar point data outside the predicted driving area can be filtered to ensure that the radar points that are offset from the preset driving path but still within the safe range will not be wrongly filtered out, thereby effectively improving the accuracy of radar point data filtering. Thus, the radar points within the predicted driving area in the radar point data can be retained as valid target radar points. For example, assuming the preset vehicle width is 3.5 meters, the following formula can be used to filter the radar point data based on the predicted driving area:

[0092] R - 7DD ≥ R + 7

[0093]

[0094] Among them, R is the circumferential radius of the preset driving path, D is the distance between the radar point and the moving center point of the target vehicle, and XPos and YPos can be the position information of the radar point. Among them, XPos can be expressed as the longitudinal position coordinate of the radar point relative to the target vehicle, and YPos can be expressed as the lateral position coordinate of the radar point relative to the target vehicle. In this way, when D <= R - 7 or D >= R + 7, it indicates that the radar point is not within the predicted driving area, and the radar point can be filtered. When (R - 7) < D < (R + 7), it indicates that the radar point is within the predicted driving area and can be retained as a target radar point.

[0095] Correspondingly, please continue to refer to Figure 3 , and the filtering condition for filtering the radar point data based on the predicted driving area can also be expressed as:

[0096] Sqrt(XPos^2 + YPos^2) >= (YawRate / Speed) + 2 * LaneWidth || Sqrt(XPos^2 + YPos^2) <= (YawRate / Speed) - 2 * LaneWidth

[0098] In this way, based on the filtering condition, the circular area formed by the two expanded predicted driving paths can be determined as the predicted driving area, so that the radar point data outside the predicted driving area can be filtered to ensure that those radar points that are deviated from the preset driving path but still within the safe range will not be mistakenly filtered out, thereby effectively improving the accuracy of radar point data filtering.

[0099] In the process of filtering radar points, it is necessary to ensure that the normal ADAS (Advanced Driving Assistance System) function of the vehicle is not affected, especially the performance of AEB (Autonomous Emergency Braking). Among them, the AEB system is crucial for emergency braking scenarios of targets crossing the road (such as pedestrians, bicycles or motorcycles). Since the filtering strategy in various driving scenarios is mainly based on lateral distance to exclude radar points far away from the driving path of the target vehicle, this may cause the radar point data of targets that may cross the road to be filtered. Therefore, when a crossing target crossing the road appears, the radar point data of the crossing target is misjudged as invalid, resulting in the AEB function being unable to respond in time, resulting in a dangerous situation. To this end, special processing logic can be set for targets with higher lateral speeds to release the radar point data corresponding to targets with higher lateral speeds from the filtering strategy of each driving scenario to avoid affecting the timely response of the AEB function, thereby improving the accuracy of radar point data filtering.

[0100] Specifically, the dynamic target in the driving scene of the target vehicle can be determined through the vehicle driving information, and when the dynamic target meets the preset conditions, the radar point data corresponding to the dynamic target is controlled to be included in the target radar point.

[0101] Among them, the dynamic target can be a target with a faster lateral speed around the target vehicle, the preset condition can be that the lateral movement speed of the dynamic target is greater than a preset speed threshold, the lateral movement speed can be a lateral component of the movement speed of the dynamic target relative to the target vehicle, and the preset speed threshold can be a preset lateral speed threshold. When the lateral movement speed of the dynamic target is greater than the threshold, it can be indicated that the dynamic target meets the preset condition.

[0102] Among them, controlling the radar point data corresponding to the dynamic target to be included in the target radar point may include, when the radar point corresponding to the dynamic target is filtered out as an invalid point in the filtering strategy of the driving scene, releasing it from the filtering strategy and adding the radar point corresponding to the dynamic target to the target radar point, and when the radar point data corresponding to the dynamic target is not filtered out in the filtering strategy of the driving scene, not processing is performed to keep the radar point corresponding to the dynamic target included in the target radar point.

[0103] Among them, when the dynamic target meets the preset conditions, there can be multiple ways to control the radar point data corresponding to the dynamic target to be included in the target radar point. For example, the lateral movement speed of the dynamic target relative to the target vehicle can be obtained. When the lateral movement speed is greater than the preset speed threshold, the radar point data that is on the same side of the target vehicle as the dynamic target and has a longitudinal distance with the dynamic target within a preset distance is controlled to be included in the target radar point.

[0104] The preset distance may be a preset threshold of a longitudinal distance, and the longitudinal distance to the dynamic target may be expressed as the distance between the radar point and the dynamic target in the longitudinal direction in the coordinate system of the target vehicle.

[0105] When the lateral movement speed is greater than the preset speed threshold, the dynamic target can be determined as a crossing target, that is, a target that may cross the driving area of ​​the target vehicle. Since the crossing target has a faster moving speed and may soon enter the driving area of ​​the target vehicle, they cannot be simply filtered out based on the lateral distance. In addition, the accuracy of directly obtaining the lateral movement speed of the dynamic target from the radar data is often low. Therefore, the visual sensor of the target vehicle can be combined to provide more accurate target type and speed information. For example, when the radar senses a crossing target with a lateral movement speed greater than the preset speed threshold, for example, for a pedestrian-type dynamic target, the corresponding preset speed threshold can be 2km / h, and for a two-wheeled vehicle-type dynamic target, the corresponding preset speed threshold can be 5km / h. The data sensed by the visual system can be used to verify and confirm the status of these crossing targets.

[0106] For details, please continue to refer to Figure 3 , when the visual system identifies a crossing visual target (i.e., a crossing target identified by the visual system), it can determine whether it is crossing to the left or right and record it based on the lateral movement speed and lateral position of the crossing visual target. Radar points that are on the same side as the lateral position of the crossing visual target and whose longitudinal position XPos is within a preset distance (e.g., ±6m) of the visual target can be exempted from filtering, and they can be released from the filtering strategy of the driving scene, i.e., they will no longer be filtered out because the lateral distance is too far. Therefore, even if the lateral speed information of the radar target is not accurate enough, it can be combined with the data of the visual system to ensure that the AEB system can respond to the target crossing the road in a timely manner, thereby improving the safety performance of the vehicle.

[0107] For example, see Figure 4b , Figure 4bThis is another specific scenario schematic diagram of a radar point filtering method provided in an embodiment of the present application, wherein the circular mark is a radar target, i.e., a radar point, and the square mark is a visual target, i.e., a target perceived by a visual system. When a crossing target is identified, a radar point that is on the same side of the target vehicle as the crossing target and whose longitudinal distance to the crossing target is within a preset distance can be added to the target radar points.

[0108] In intelligent driving scenarios, in order to ensure vehicle safety and more intelligent driving, invalid point filtering of radar point data is an important step to improve the accuracy and efficiency of target detection. Radar sensors play an important role in intelligent driving scenarios. They can detect various objects in the surrounding environment, including dynamic and static obstacles. However, radar point data often contains a large number of invalid points, which may be caused by internal noise of the radar equipment, external interference, or errors in the data acquisition process. In order to ensure the stability and safety of the intelligent driving system, radar point data must be filtered. In existing filtering methods, threshold judgment methods are often used for filtering. However, due to the complex vehicle driving scenarios, existing filtering methods cannot stably and accurately filter invalid radar points, resulting in low accuracy of radar point filtering. To this end, an embodiment of the present application provides a radar point filtering method based on the driving area and the vehicle status. For common vehicle driving scenarios, the effective target area and the invalid target area when the ADAS function is running are analyzed, so that the radar points in the invalid target area are filtered, and the invalid radar point filtering of most scenarios is completed with a method with a small amount of calculation. The filtering is not performed based on the attributes of the radar points themselves, but the radar points are filtered according to the driving interactive environment area of ​​the vehicle and the future trajectory prediction of the vehicle in combination with the lane line information and the vehicle motion information obtained by the visual sensor. In addition, for objects that may cross the road, they can be identified based on the visual system and the radar points around them can be protected from filtering to avoid affecting the timely response of the vehicle's AEB function, so as to filter most of the invalid radar points with a small computational burden, and effectively improve the accuracy of radar point filtering.

[0109] From the above, it can be seen that the embodiment of the present application determines the driving scene of the target vehicle according to the vehicle driving information collected by multiple sensors on the target vehicle; according to the filtering strategy corresponding to the driving scene, the radar point data collected by the target vehicle is filtered to obtain the target radar point. In this way, the driving scene of the target vehicle can be determined according to the vehicle driving information collected by multiple sensors on the target vehicle, so that the radar point data collected by the target vehicle can be filtered in a targeted manner according to the filtering strategy corresponding to the driving scene, so as to achieve stable and accurate filtering of the radar point data in a variety of driving scenes, thereby effectively improving the accuracy of radar point filtering.

[0110] In order to facilitate better implementation of the radar point filtering method provided in the embodiment of the present application, the embodiment of the present application also provides a device based on the above radar point filtering method. The meanings of the terms are the same as those in the above radar point filtering method, and the specific implementation details can refer to the description in the method embodiment.

[0111] For example, Figure 5 As shown, it is a schematic diagram of the structure of the radar point filtering device provided in an embodiment of the present application. The radar point filtering device may include a determination module 201 and a filtering module 202, which are specifically as follows:

[0112] A determination module 201 is used to determine a driving scene of a target vehicle based on vehicle driving information collected by multiple sensors on the target vehicle;

[0113] The filtering module 202 is used to filter the radar point data collected by the target vehicle according to the filtering strategy corresponding to the driving scene to obtain the target radar point.

[0114] In one embodiment, the vehicle driving information includes at least one of driving speed information and driving road surface information of the target vehicle.

[0115] In one embodiment, the determination module 201 includes:

[0116] The determination submodule is used to determine the driving scene of the target vehicle based on the driving speed information and / or driving road surface information in the vehicle driving information collected by multiple sensors on the target vehicle.

[0117] In one embodiment, the determination submodule includes a first determination unit configured to:

[0118] If the driving speed information in the vehicle driving information collected by multiple sensors on the target vehicle meets the preset speed condition, it is determined that the target vehicle is in the first driving scenario.

[0119] In one embodiment, the determination submodule includes a second determination unit configured to:

[0120] If the driving speed information in the vehicle driving information collected by multiple sensors on the target vehicle does not meet the preset speed condition, the driving road surface information in the vehicle driving information is processed to determine whether there is a target edge on the driving road surface of the target vehicle;

[0121] In the case where there is a target edge on the driving road, confirming that the target vehicle is in a second driving scene;

[0122] When there is no target edge on the driving road, it is confirmed that the target vehicle is in the third driving scenario.

[0123] In one embodiment, when the target vehicle is in the first driving scenario, the filtering module 202 includes a first filtering submodule, which is used to:

[0124] Obtain the target vehicle and the distance value between each radar point in the radar point data collected by the target vehicle;

[0125] If the distance value is not less than the preset distance threshold, the radar point is filtered;

[0126] If the distance value is less than the preset distance threshold, the radar point is determined as a target radar point.

[0127] In one embodiment, when the target vehicle is in the second driving scenario, the filtering module 202 includes:

[0128] An edge determination submodule, used to determine the type of target edge existing in the driving road surface, the target edge including a first target edge and a second target edge;

[0129] A first boundary determination submodule, for obtaining, if a first target edge exists in the driving road surface, filtering boundary equations on both sides of the target vehicle determined based on the position information of the first target edge;

[0130] A second boundary determination submodule is used to determine, if the first target edge does not exist in the driving road surface and the second target edge exists, based on the position information of the second target edge, a curve equation corresponding to the extended edge line of the second target edge as a filtering boundary equation on both sides of the target vehicle;

[0131] The second filtering submodule is used to filter the radar point data collected from the target vehicle based on the filtering boundary equations on both sides of the target vehicle to obtain the target radar point.

[0132] In one embodiment, the second filtering submodule is used to:

[0133] Obtaining the position coordinates of each radar point in the radar point data collected by the target vehicle, the position coordinates including the longitudinal position coordinates and the lateral position coordinates of the radar point relative to the target vehicle;

[0134] Calculating values ​​of filtering boundary equations on both sides of the target vehicle at the longitudinal position coordinate to obtain a first lateral position coordinate and a second lateral position coordinate;

[0135] If the lateral position coordinate is between the first lateral position coordinate and the second lateral position coordinate, the radar point is determined as a target radar point.

[0136] In one embodiment, the first boundary determination submodule is used to:

[0137] When there are first target edges on both sides of the target vehicle, obtaining a curve equation calculated based on the position information of the first target edge as a filtering boundary equation on both sides of the target vehicle;

[0138] When the first target edge exists only on one side of the target vehicle, the curve equation corresponding to the first target edge is translated based on the preset lane width, and the translated curve equation and the curve equation corresponding to the first target edge are determined as the filtering boundary equations on both sides of the target vehicle.

[0139] In one embodiment, the second boundary determination submodule is used to:

[0140] When there are second target edges on both sides of the target vehicle, the curve equations corresponding to the second target edges are expanded based on the preset lane width to obtain the curve equations corresponding to the expanded edge lines of the second target edges;

[0141] When the second target edge exists only on one side of the target vehicle, the curve equation corresponding to the second target edge is expanded based on the preset lane width, and the expanded curve equation is translated based on the preset lane width to obtain the curve equations corresponding to the expanded edge lines on both sides of the target vehicle.

[0142] In one embodiment, when the target vehicle is in the third driving scenario, the filtering module 202 includes:

[0143] The area determination submodule is used to determine the predicted driving area of ​​the target vehicle according to the driving speed information in the vehicle driving information;

[0144] The third filtering submodule is used to determine the radar points in the radar point data that are within the predicted driving area as target radar points based on the position information of each radar point in the radar point data.

[0145] In one embodiment, the driving speed information includes the driving speed and the driving yaw rate of the target vehicle, and the area determination submodule is used to:

[0146] Based on the vehicle speed and yaw rate, the radius of the circle and the center point of the uniform circular motion of the target vehicle are calculated;

[0147] Determine the predicted driving path of the target vehicle based on the circle radius and the center point of motion;

[0148] The predicted driving path is expanded along the direction approaching and away from the moving center point according to the preset lane width to obtain the expanded predicted driving path;

[0149] The predicted driving area of ​​the target vehicle is determined based on the expanded predicted driving path.

[0150] In one embodiment, the radar point filtering device further includes:

[0151] A dynamic target determination module, used to determine a dynamic target in a driving scene of a target vehicle through vehicle driving information;

[0152] The filtering control module is used to control the radar point data corresponding to the dynamic target to be included in the target radar point when the dynamic target meets the preset conditions.

[0153] In one embodiment, the filtering control module is used to:

[0154] Obtain the lateral moving speed of the dynamic target relative to the target vehicle;

[0155] When the lateral movement speed is greater than a preset speed threshold, radar point data that is located at the same side of the target vehicle as the dynamic target and has a longitudinal distance to the dynamic target within a preset distance is controlled to be included in the target radar points.

[0156] As can be seen from the above, the embodiment of the present application determines the driving scene of the target vehicle according to the vehicle driving information collected by multiple sensors on the target vehicle through the determination module 201; the filtering module 202 filters the radar point data collected by the target vehicle according to the filtering strategy corresponding to the driving scene to obtain the target radar point. In this way, the driving scene of the target vehicle can be determined according to the vehicle driving information collected by multiple sensors on the target vehicle, so that the radar point data collected by the target vehicle can be filtered in a targeted manner according to the filtering strategy corresponding to the driving scene, so as to achieve stable and accurate filtering of the radar point data in a variety of driving scenes, thereby effectively improving the accuracy of radar point filtering.

[0157] Accordingly, the embodiment of the present application also provides a vehicle-mounted terminal, such as Figure 6 As shown, Figure 6 A schematic diagram of the structure of the vehicle-mounted terminal provided in an embodiment of the present application. The vehicle-mounted terminal 300 includes a processor 301 having one or more processing cores, a memory 302 having one or more computer-readable storage media, and a computer program stored in the memory 302 and executable on the processor. The processor 301 is electrically connected to the memory 302. Those skilled in the art will appreciate that the vehicle-mounted terminal structure shown in the figure does not constitute a limitation on the vehicle-mounted terminal, and may include more or fewer components than shown in the figure, or combine certain components, or arrange components differently.

[0158] The processor 301 is the control center of the vehicle terminal 300, and uses various interfaces and lines to connect various parts of the entire vehicle terminal 300. It executes various functions and processes data of the vehicle terminal 300 by running or loading software programs and / or units stored in the memory 302, and calling data stored in the memory 302. The processor 301 can be a processor CPU, a graphics processor GPU, a network processor (Network Processor, NP), etc., and can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present application.

[0159] In the embodiment of the present application, the processor 301 in the vehicle terminal 300 will load instructions corresponding to the processes of one or more application programs into the memory 302 according to the following steps, and the processor 301 will run the application programs stored in the memory 302 to implement various functions, such as:

[0160] The driving scene of the target vehicle is determined based on the vehicle driving information collected by multiple sensors on the target vehicle; the radar point data collected by the target vehicle is filtered according to the filtering strategy corresponding to the driving scene to obtain the target radar point.

[0161] Furthermore, various functions implemented by running the application program stored in the memory 302 can also be found in the description of the aforementioned embodiment, which will not be repeated here.

[0162] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0163] Optional, such as Figure 6 As shown, the vehicle terminal 300 also includes: a touch screen 303, a radio frequency circuit 304, an audio circuit 305, an input unit 306 and a power supply 307. Among them, the processor 301 is electrically connected to the touch screen 303, the radio frequency circuit 304, the audio circuit 305, the input unit 306 and the power supply 307 respectively. Those skilled in the art can understand that Figure 6 The vehicle-mounted terminal structure shown in the figure does not constitute a limitation on the vehicle-mounted terminal, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0164] The touch display screen 303 can be used to display a graphical user interface and receive operation instructions generated by the user acting on the graphical user interface. The touch display screen 303 may include a display panel and a touch panel. Among them, the display panel can be used to display information input by the user or information provided to the user and various graphical user interfaces of the vehicle terminal, which can be composed of graphics, text, icons, videos and any combination thereof. Optionally, the display panel can be configured in the form of a liquid crystal display (LCD, Liquid Crystal Display), an organic light-emitting diode (OLED, Organic Light-Emitting Diode), etc. The touch panel can be used to collect the user's touch operation on or near it (such as the user uses any suitable object or accessory such as a finger, stylus, etc. on the touch panel or near the touch panel), and generate corresponding operation instructions, and the operation instructions execute the corresponding program. Optionally, the touch panel may include two parts: a touch detection device and a touch controller. Among them, the touch detection device detects the user's touch direction, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into the touch point coordinates, and then sends it to the processor 301, and can receive the command sent by the processor 301 and execute it. The touch panel can cover the display panel. When the touch panel detects a touch operation on or near it, it is transmitted to the processor 301 to determine the type of touch event, and then the processor 301 provides a corresponding visual output on the display panel according to the type of touch event. In an embodiment of the present application, the touch panel and the display panel can be integrated into the touch display screen 303 to realize the input and output functions. However, in some embodiments, the touch panel and the touch panel can be used as two independent components to realize the input and output functions. That is, the touch display screen 303 can also be used as a part of the input unit 306 to realize the input function.

[0165] The RF circuit 304 may be used to send and receive RF signals, so as to establish wireless communication with a network device or other vehicle-mounted terminals through wireless communication, and to send and receive signals with the network device or other vehicle-mounted terminals.

[0166] The audio circuit 305 can be used to provide an audio interface between the user and the vehicle-mounted terminal through a speaker and a microphone. The audio circuit 305 can transmit the electrical signal converted from the received audio data to the speaker, which is converted into a sound signal for output; on the other hand, the microphone converts the collected sound signal into an electrical signal, which is received by the audio circuit 305 and converted into audio data, and then the audio data is output to the processor 301 for processing, and then sent to another vehicle-mounted terminal through the radio frequency circuit 304, or the audio data is output to the memory 302 for further processing. The audio circuit 305 may also include an earplug jack to provide communication between an external headset and the vehicle-mounted terminal.

[0167] The input unit 306 may be used to receive input target video and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.

[0168] The power supply 307 is used to supply power to various components of the vehicle-mounted terminal 300. Optionally, the power supply 307 can be logically connected to the processor 301 through a power management system, so as to manage charging, discharging, and power consumption through the power management system. The power supply 307 can also include one or more DC or AC power supplies, recharging systems, power failure detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0169] although Figure 6 Not shown, the vehicle terminal 300 may also include a camera, a sensor, a wireless fidelity module, a Bluetooth module, etc., which will not be described in detail here.

[0170] In the above embodiments, the description of each embodiment has its own emphasis. For the part not described in detail in a certain embodiment, please refer to the relevant description of other embodiments. It should be noted that the vehicle-mounted terminal provided in the embodiment of the present application and the radar point filtering method in the above embodiment belong to the same concept. The specific implementation process is detailed in the above method embodiment and will not be repeated here.

[0171] As can be seen from the above, the vehicle-mounted terminal provided in the embodiment of the present application can determine the driving scene of the target vehicle according to the vehicle driving information collected by multiple sensors on the target vehicle; according to the filtering strategy corresponding to the driving scene, the radar point data collected by the target vehicle is filtered to obtain the target radar point. In this way, the driving scene of the target vehicle can be determined according to the vehicle driving information collected by multiple sensors on the target vehicle, so that the radar point data collected by the target vehicle can be filtered in a targeted manner according to the filtering strategy corresponding to the driving scene, so as to achieve stable and accurate filtering of the radar point data in a variety of driving scenes, thereby effectively improving the accuracy of radar point filtering.

[0172] A person of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0173] To this end, an embodiment of the present application provides a computer-readable storage medium, which includes a computer program. When the computer program is run on a vehicle-mounted terminal, the computer program is used to enable the vehicle-mounted terminal to perform any radar point filtering method provided in the embodiment of the present application. For example, the computer program can perform the following steps of the radar point filtering method:

[0174] The driving scene of the target vehicle is determined based on the vehicle driving information collected by multiple sensors on the target vehicle; the radar point data collected by the target vehicle is filtered according to the filtering strategy corresponding to the driving scene to obtain the target radar point.

[0175] Furthermore, for the detailed steps of the above method steps, reference can be made to the description in the above embodiments, which will not be repeated here.

[0176] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0177] The computer-readable storage medium may include: a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0178] Since the computer program stored in the computer-readable storage medium can execute any radar point filtering method provided in the embodiments of the present application, the beneficial effects that can be achieved by any radar point filtering method provided in the embodiments of the present application can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0179] According to one aspect of the present application, a computer program product is also provided, including a computer program, which is stored in a computer-readable storage medium; when the processor of a vehicle-mounted terminal reads the computer program from the computer-readable storage medium, the processor executes the computer program, so that the vehicle-mounted terminal executes the methods provided in the various optional implementation methods in the above-mentioned embodiments.

[0180] In the above radar point filtering device, computer readable storage medium, vehicle-mounted terminal, and computer program product embodiments, the description of each embodiment has its own emphasis. For parts not described in detail in a certain embodiment, reference can be made to the relevant description of other embodiments. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process and beneficial effects of the above-described radar point filtering device, computer readable storage medium, computer program product, vehicle-mounted terminal and its corresponding units can refer to the description of the radar point filtering method in the above embodiment, and will not be repeated here.

[0181] The above is a detailed introduction to a radar point filtering method, device, vehicle-mounted terminal, vehicle, computer-readable storage medium and computer program product provided in the embodiments of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, according to the ideas of the present application, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as limiting the present application.

Claims

1. A radar point filtering method, characterized in that: include: Determining a driving scene of the target vehicle based on vehicle driving information collected by multiple sensors on the target vehicle; According to the filtering strategy corresponding to the driving scene, the radar point data collected by the target vehicle is filtered to obtain the target radar point.

2. The radar point filtering method according to claim 1, characterized in that: The vehicle driving information includes at least one of driving speed information and driving road surface information of the target vehicle.

3. The radar point filtering method according to claim 2, characterized in that: Determining the driving scene of the target vehicle according to the vehicle driving information collected by multiple sensors on the target vehicle includes: The driving scene of the target vehicle is determined based on the driving speed information and / or the driving road surface information in the vehicle driving information collected by multiple sensors on the target vehicle.

4. The radar point filtering method according to claim 3, characterized in that: The determining of the driving scene of the target vehicle according to the driving speed information and / or the driving road surface information in the vehicle driving information collected by multiple sensors on the target vehicle includes: If the driving speed information in the vehicle driving information collected by multiple sensors on the target vehicle meets the preset speed condition, it is determined that the target vehicle is in the first driving scene.

5. The radar point filtering method according to claim 3, characterized in that: The determining of the driving scene of the target vehicle according to the driving speed information and / or the driving road surface information in the vehicle driving information collected by multiple sensors on the target vehicle includes: If the driving speed information in the vehicle driving information collected by multiple sensors on the target vehicle does not meet the preset speed condition, the driving road surface information in the vehicle driving information is processed to determine whether there is a target edge on the driving road surface of the target vehicle; In a case where the target edge exists in the driving road surface, confirming that the target vehicle is in a second driving scene; When the target edge does not exist in the driving road surface, it is confirmed that the target vehicle is in a third driving scenario.

6. The radar point filtering method according to claim 4, characterized in that: When the target vehicle is in a first driving scene, filtering the radar point data collected by the target vehicle according to a filtering strategy corresponding to the driving scene to obtain a target radar point includes: Obtaining the target vehicle and the distance value between each radar point in the radar point data collected by the target vehicle; If the distance value is not less than a preset distance threshold, filtering the radar point; If the distance value is less than a preset distance threshold, the radar point is determined as a target radar point.

7. The radar point filtering method according to claim 5, characterized in that: When the target vehicle is in the second driving scene, filtering the radar point data collected by the target vehicle according to the filtering strategy corresponding to the driving scene to obtain the target radar point includes: Determining a type of a target edge existing in the driving road surface, the target edge comprising a first target edge and a second target edge; If the first target edge exists in the driving road surface, obtaining filtering boundary equations on both sides of the target vehicle determined based on the position information of the first target edge; If the first target edge does not exist in the driving road surface and the second target edge exists, based on the position information of the second target edge, determining a curve equation corresponding to the extended edge line of the second target edge as a filtering boundary equation on both sides of the target vehicle; Based on the filtering boundary equations on both sides of the target vehicle, the radar point data collected from the target vehicle is filtered to obtain the target radar point.

8. The radar point filtering method according to claim 7, characterized in that: The filtering boundary equations on both sides of the target vehicle are used to filter the radar point data collected from the target vehicle to obtain the target radar point, including: Acquire the position coordinates of each radar point in the radar point data collected by the target vehicle, wherein the position coordinates include the longitudinal position coordinates and the lateral position coordinates of the radar point relative to the target vehicle; Calculating values ​​of filtering boundary equations on both sides of the target vehicle at the longitudinal position coordinate to obtain a first lateral position coordinate and a second lateral position coordinate; If the lateral position coordinate is between the first lateral position coordinate and the second lateral position coordinate, the radar point is determined as a target radar point.

9. The radar point filtering method according to claim 7, characterized in that: The obtaining of filtering boundary equations on both sides of the target vehicle determined based on the position information of the first target edge includes: When there are first target edges on both sides of the target vehicle, obtaining a curve equation calculated based on the position information of the first target edge as a filtering boundary equation on both sides of the target vehicle; When the first target edge exists on only one side of the target vehicle, the curve equation corresponding to the first target edge is translated based on the preset lane width, and the translated curve equation and the curve equation corresponding to the first target edge are determined as filtering boundary equations on both sides of the target vehicle.

10. The radar point filtering method according to claim 7, characterized in that: The step of determining the curve equation corresponding to the extended edge line of the second target edge based on the position information of the second target edge includes: When there are second target edges on both sides of the target vehicle, the curve equations corresponding to the second target edges are expanded based on the preset lane width to obtain the curve equations corresponding to the expanded edge lines of the second target edges; When the second target edge exists only on one side of the target vehicle, the curve equation corresponding to the second target edge is expanded based on the preset lane width, and the expanded curve equation is translated based on the preset lane width to obtain the curve equations corresponding to the expanded edge lines on both sides of the target vehicle.

11. The radar point filtering method according to claim 5, characterized in that: When the target vehicle is in a third driving scene, filtering the radar point data collected by the target vehicle according to a filtering strategy corresponding to the driving scene to obtain a target radar point includes: Determining a predicted driving area of ​​the target vehicle according to driving speed information in the vehicle driving information; Based on the position information of each radar point in the radar point data, a radar point in the radar point data that is within the predicted driving area is determined as a target radar point.

12. The radar point filtering method according to claim 11, characterized in that: The driving speed information includes the driving speed and the driving yaw rate of the target vehicle, and determining the predicted driving area of ​​the target vehicle according to the driving speed information in the vehicle driving information includes: Based on the driving speed and the driving yaw angular velocity, calculating the radius of a circle and a center point of the uniform circular motion of the target vehicle; Determining a predicted driving path of the target vehicle based on the circle radius and the motion center point; Expanding the predicted driving path along directions approaching and away from the motion center point according to a preset lane width to obtain an expanded predicted driving path; The predicted driving area of ​​the target vehicle is determined based on the expanded predicted driving path.

13. The radar point filtering method according to any one of claims 1 to 12, characterized in that: The method further comprises: Determining a dynamic target in a driving scene of the target vehicle through the vehicle driving information; When the dynamic target meets a preset condition, the radar point data corresponding to the dynamic target is controlled to be included in the target radar point.

14. The radar point filtering method according to claim 13, characterized in that: When the dynamic target meets a preset condition, controlling the radar point data corresponding to the dynamic target to be included in the target radar point comprises: Acquiring a lateral motion speed of the dynamic target relative to the target vehicle; When the lateral movement speed is greater than a preset speed threshold, radar point data that is on the same side of the target vehicle as the dynamic target and has a longitudinal distance to the dynamic target within a preset distance is controlled to be included in the target radar points.

15. A radar point filtering device, characterized in that: include: A determination module, used to determine the driving scene of the target vehicle according to the vehicle driving information collected by multiple sensors on the target vehicle; The filtering module is used to filter the radar point data collected by the target vehicle according to the filtering strategy corresponding to the driving scene to obtain the target radar point.

16. A vehicle-mounted terminal, characterized in that: It comprises a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of any one of the methods of claims 1 to 14.

17. A vehicle, characterized in that: The vehicle includes the vehicle-mounted terminal as claimed in claim 16.

18. A computer-readable storage medium, characterized in that: The method comprises a computer program. When the computer program is run on a vehicle-mounted terminal, the computer program is used to enable the vehicle-mounted terminal to execute the steps of any method described in claims 1 to 14.

Images