Obstacle filtering method and system based on ultrasonic real-time detection range

Abstract

The present invention provides a method and system for obstacle filtering based on the real-time ultrasonic detection range. The method includes: calibrating the installation position data of each radar around the vehicle body according to the vehicle coordinate system, and setting a radar parameter table based on the installation position data and specification parameters of each radar; obtaining the real-time detection range of each radar to the obstacle, and determining the clearance zone of each radar based on the real-time detection range and the radar parameter table; obtaining an obstacle list from other modules after camera and ultrasonic fusion; traversing the obstacle list and determining whether the obstacle is within the radar's clearance zone based on the obstacle's coordinates; updating the obstacle confidence level based on the determination result, and updating the obstacle list based on the obstacle confidence level. The present invention filters out falsely detected obstacles based on the ultrasonic radar detection range, resolving the problem of false detection in obstacle fusion in parking systems and optimizing the reliability and safety of parking systems.

Description

Technical Field

[0001] The present invention relates to the field of automatic parking technology, and more specifically, to an obstacle filtering method, system, electronic device and storage medium based on ultrasonic real-time detection range. Background Art

[0002] The core functions of automated parking include sensor data perception, fusion, positioning, decision-making, planning, and control. Perception fusion involves integrating, tracking, and filtering obstacles detected by multiple sensors before outputting them to the decision-making, planning, and control modules. The accuracy and reliability of obstacle detection directly determine the safety and reliability of the parking system.

[0003] During the parking space search and parking process, the parking system uses visual sensors to identify and track obstacles around the vehicle (including SOD and MOD). Due to the limitations of visual sensor calibration, algorithm performance, and computing power, there will be a certain degree of false detection and missed detection, such as detecting patterns or designs on the ground as SOD.

[0004] If these falsely detected obstacles are not filtered, the parking space will be excessively restricted due to these falsely detected obstacles, making it impossible to plan a parking trajectory or identify available parking spaces, reducing the reliability of the parking system. Furthermore, due to the limitations of the visual sensor's output image frame rate, the recognition accuracy of visual obstacle coordinates is low. Furthermore, missed detections can lead to the false triggering of emergency braking or a crash, compromising the safety of the parking system.

[0005] The traditional parking obstacle fusion method is to directly fuse the obstacle coordinates output by the visual sensor and the obstacle coordinates output by the ultrasonic radar. Although this method can improve the situation of missed obstacle detection and the accuracy of the fused obstacle coordinates, it does not significantly improve the situation of false detection. Summary of the Invention

[0006] In response to the technical problems existing in the prior art, the present invention provides an obstacle filtering method and system based on the real-time ultrasonic detection range. The method filters out falsely detected obstacles based on the ultrasonic radar detection distance, thereby resolving the problem of false detection of obstacle fusion in the parking system and optimizing the reliability and safety of the parking system.

[0007] According to a first aspect of the present invention, there is provided a method for filtering obstacles based on a real-time ultrasonic detection range, comprising:

[0008] Calibrate the installation position data of each radar around the vehicle body according to the vehicle coordinate system, and set the radar parameter table according to the installation position data and specification parameters of each radar;

[0009] Obtain the real-time detection distance of each radar to obstacles, and obtain the clearance zone of each radar based on the real-time detection distance and radar parameter table; obtain the obstacle list after the camera and ultrasonic fusion from other modules;

[0010] Traverse the obstacle list and determine whether the obstacle is in the radar's clear area based on the obstacle's coordinates; update the obstacle confidence based on the judgment result, and update the obstacle list based on the obstacle confidence.

[0011] On the basis of the above technical solution, the present invention can also make the following improvements.

[0012] Optionally, calibrating the coordinates of each radar according to the vehicle coordinate system includes:

[0013] The vehicle coordinate system is established with the X-axis positive direction forward along the vehicle's front, and the Y-axis positive direction perpendicular to the vehicle body and pointing leftward.

[0014] The installation position data of all ultrasonic radars are measured and calibrated based on the vehicle coordinate system. The installation position data at least includes the coordinate points of the radars and the installation angles of the radars.

[0015] Optionally, the parameters of the radar parameter table include at least:

[0016] The numbers, x-coordinate values, y-coordinate values, installation angles, field of view angles, and detection distances of all radars.

[0017] Optionally, obtaining the clearance area of ​​each radar according to the real-time detection distance dist and the radar parameter table includes:

[0018] Obtain the field of view and minimum detection distance of any radar through the radar parameter table;

[0019] Taking the minimum detection range of the current radar as the radius, intercepting the first sector within the field of view of the current radar;

[0020] Taking the real-time detection distance dist of the current radar as the radius, intercept the second sector surface within the field of view of the current radar;

[0021] The overlapping area between the second sector and the first sector is removed, and the remaining area is used as the clearance area of ​​the current radar;

[0022] Traverse all radars in the radar parameter table and obtain the clearance areas of all radars.

[0023] Optionally, judging whether the obstacle is located in the radar's clear zone based on the obstacle's coordinates includes:

[0024] Determine whether an obstacle is an obstacle frame or an obstacle point:

[0025] If the obstacle is an obstacle frame, the coordinates of each vertex of the obstacle frame are converted from the world coordinate system to the ego vehicle coordinate system. Based on the coordinates of the vertex in the ego vehicle coordinate system, it is determined whether the vertex is within the clear zone of any radar. The coordinates of all vertices of the current obstacle are traversed. If at least one vertex is within the clear zone, the current obstacle frame is determined to be within the clear zone.

[0026] If it is determined that all vertices of the current obstacle frame are not within the clear area, then further determine whether the current obstacle frame and the clear area have an intersection. If there is an intersection, then determine that the current obstacle frame is within the clear area. If there is no intersection, then determine that the current obstacle frame is not within the clear area.

[0027] If the obstacle is an obstacle point, converting the coordinates of the obstacle point from the world coordinate system to the ego vehicle coordinate system, and determining whether the obstacle point is within the clearance zone of any radar based on the coordinates of the obstacle point based on the ego vehicle coordinate system;

[0028] Iterate over all obstacles in the obstacle list.

[0029] Optionally, updating the obstacle confidence level according to the judgment result includes:

[0030] If the current obstacle is determined to be within the clearance zone of any radar, the confidence level of the current obstacle is lowered; if the current obstacle is determined not to be within the clearance zone of any radar, the confidence level of the current obstacle is not changed.

[0031] Optionally, updating the obstacle list according to the obstacle confidence level includes:

[0032] Cyclic determination is made whether all obstacles in the obstacle list are within the clear zone of each radar. The value by which the obstacle confidence is reduced in a single cycle is k, where k is a constant value.

[0033] The confidence values ​​of all obstacles are updated in each cycle, and obstacles with a confidence value of 0 are removed from the obstacle list.

[0034] According to a second aspect of the present invention, there is provided an obstacle filtering system based on ultrasonic real-time detection range, comprising:

[0035] The pre-processing module is used to calibrate the installation position data of each radar around the vehicle body according to the vehicle coordinate system, and is also used to set the radar parameter table according to the installation position data and specification parameters of each radar;

[0036] The obstacle detection module is used to obtain the real-time detection distance of each radar to obstacles, and obtain the clearance zone of each radar based on the real-time detection distance and radar parameter table. It is also used to obtain the obstacle list after the camera and ultrasonic wave fusion from other modules;

[0037] The obstacle filtering module is used to traverse the obstacle list and determine whether the obstacle is located in the radar's clear area based on its coordinates. It is also used to update the obstacle confidence level based on the judgment result and update the obstacle list based on the obstacle confidence level.

[0038] According to a third aspect of the present invention, an electronic device is provided, comprising a memory and a processor, wherein the processor is configured to implement the steps of the above-mentioned obstacle filtering method based on the real-time ultrasonic detection range when executing a computer management program stored in the memory.

[0039] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, on which a computer management program is stored. When the computer management program is executed by a processor, the steps of the above-mentioned obstacle filtering method based on the real-time ultrasonic detection range are implemented.

[0040] The present invention provides an obstacle filtering method, system, electronic device, and storage medium based on the real-time ultrasonic detection range. These methods can reduce the false detection rate of obstacles, ensure that the parking planning module can obtain a reliable parking area for trajectory planning, and that the control module obtains accurate obstacle information for obstacle avoidance control, thereby improving the reliability and safety of the parking system. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 A schematic diagram of multiple ultrasonic radars installed circumferentially around a vehicle body in the present invention;

[0042] Figure 2 A schematic diagram of the clearance area of ​​the radar mentioned in the present invention;

[0043] Figure 3 A flow chart of an obstacle filtering method based on ultrasonic real-time detection range provided by the present invention;

[0044] Figure 4 A schematic diagram of the radar clearance zone calculation process provided by the present invention;

[0045] Figure 5 A schematic diagram of the obstacle filtering process provided by the present invention;

[0046] Figure 6 A block diagram of an obstacle filtering system based on ultrasonic real-time detection range provided by the present invention;

[0047] Figure 7 A schematic diagram of the hardware structure of a possible electronic device provided by the present invention;

[0048] Figure 8 A schematic diagram of the hardware structure of a possible computer-readable storage medium provided by the present invention. DETAILED DESCRIPTION

[0049] The following embodiments of the present invention are described in further detail with reference to the accompanying drawings and examples. The following examples are used to illustrate the present invention but are not intended to limit the scope of the present invention.

[0050] Figure 1 This is a schematic diagram of multiple ultrasonic radars installed around the circumference of the vehicle body. Figure 2 Schematic diagram of the clearance area of ​​a single ultrasonic radar.

[0051] like Figure 1 As shown, in this embodiment, twelve ultrasonic radars are provided as an example. The twelve ultrasonic radars are symmetrically arranged around the vehicle body with respect to the X axis of the vehicle coordinate system to complete a wide range of obstacle detection around the vehicle body.

[0052] Figure 3 The present invention provides a flow chart of an obstacle filtering method based on ultrasonic real-time detection range, such as Figure 3 As shown, the method includes:

[0053] S1. Calibrate the installation position data of each radar around the vehicle body according to the vehicle coordinate system, and set the radar parameter table according to the installation position data and specification parameters of each radar;

[0054] S2. Obtain the real-time detection distance of each radar to obstacles, and obtain the clearance zone of each radar based on the real-time detection distance and radar parameter table; obtain the obstacle list after the camera and ultrasonic fusion from other modules;

[0055] S3. Traverse the obstacle list and determine whether the obstacle is located in the radar clearance area based on the coordinates of the obstacle; update the obstacle confidence based on the judgment result, and update the obstacle list based on the obstacle confidence.

[0056] As will be appreciated, addressing the shortcomings of the background art, the present invention proposes an obstacle filtering method based on the real-time ultrasonic detection range. This embodiment considers obstacles detected by radar that are located within the radar's clear zone as falsely detected obstacles and can be filtered out. Therefore, the coordinates of each obstacle detected by each radar are calculated based on the vehicle's coordinate system. Based on the obstacle's coordinate position in the vehicle's coordinate system, the obstacle's location is determined to be within the clear zone of any radar. If the determination is positive, the confidence level of the obstacle is lowered. Each time the judgment process repeats, the confidence level of the obstacle within the clear zone is lowered. When the confidence level of an obstacle reaches a preset confidence threshold (e.g., a confidence threshold of 0), the obstacle is removed from the obstacle list, thereby updating the obstacle list and obtaining a more accurate obstacle list for parking trajectory planning. This method reduces the false detection rate of obstacles, ensures that the parking planning module obtains a reliable parking area for trajectory planning, and that the control module obtains accurate obstacle information for obstacle avoidance control, thereby improving the reliability and safety of the parking system.

[0057] In a possible embodiment, calibrating the coordinates of each radar according to the vehicle coordinate system includes:

[0058] like Figure 1 As shown, the vehicle coordinate system is established with the center of the rear wheel axle of the vehicle forward along the front of the vehicle as the positive direction of the X axis and the left direction perpendicular to the vehicle body as the positive direction of the Y axis;

[0059] The installation position data of all ultrasonic radars are measured and calibrated based on the vehicle coordinate system. The installation position data at least includes the coordinate points of the radars and the installation angles of the radars.

[0060] It is understood that in this embodiment, a vehicle coordinate system is constructed, and the installation positions and installation angles (orientations) of all ultrasonic radars can be calculated using the vehicle coordinate system. The radar coordinate positions can be converted between the vehicle coordinate system and the world coordinate system by converting between the vehicle coordinate system and the world coordinate system.

[0061] In a possible embodiment, the parameters of the radar parameter table include at least:

[0062] The numbers, x-coordinate values, y-coordinate values, installation angles, field of view angles, and detection distances of all radars.

[0063] Table 1 shows an example of the radar parameter table obtained.

[0064] Table 1 Radar parameters based on the vehicle coordinate system

[0065]

[0066]

[0067] The field of view of each ultrasonic radar can be calculated using its installation coordinates (m, n), installation angle yaw deg, field of view angle alpha deg, minimum field of view angle beta_min deg, maximum field of view angle beta_max deg, minimum detection distance min_lenm, and maximum detection distance max_lenm. It is understood that when an ultrasonic radar detects an obstacle, its actual detection distance dist is between the minimum detection distance min_lenm and the maximum detection distance max_lenm.

[0068] In one possible embodiment, Figure 4 As shown in the flowchart, the clearance area of ​​each radar is obtained according to the real-time detection distance dist and the radar parameter table, including:

[0069] Obtain the field of view and minimum detection distance min_lenm of any radar through the radar parameter table;

[0070] Take the minimum detection range min_len m of the current radar as the radius and intercept the first sector within the field of view of the current radar;

[0071] Taking the real-time detection distance dist of the current radar as the radius, intercept the second sector surface within the field of view of the current radar;

[0072] Removing the overlapping area of ​​the second sector surface and the first sector surface (for example, subtracting the second sector surface from the first sector surface), and the remaining area is used as the clearance area of ​​the current radar;

[0073] Traverse all radars in the radar parameter table and obtain the clearance areas of all radars.

[0074] It is understandable that this embodiment records the steps of calculating the radar clearance area, and the clearance area obtained is as follows: Figure 2 As shown in FIG, it is a fan-shaped arc area. After calculating the range of the entire radar clear area, it can be used as a criterion for determining whether an obstacle is falsely detected.

[0075] In one possible embodiment, Figure 5 As shown, judging whether the obstacle is located in the radar's clear area based on the obstacle's coordinates includes:

[0076] Determine whether the current obstacle is an obstacle box or an obstacle point based on the parameters of the current obstacle in the obstacle list:

[0077] If the current obstacle is an obstacle frame, the obstacle is an area. This embodiment uses a rectangular frame as an example. The coordinates of the obstacle frame are converted from the world coordinate system to the ego vehicle coordinate system. This includes converting the coordinates of the four vertices of the obstacle frame from the world coordinate system to the ego vehicle coordinate system. Based on the coordinates of any vertex in the ego vehicle coordinate system, it is determined whether the vertex is within the clear zone of a radar. The coordinates of all vertices of the current obstacle are traversed. If at least one vertex is within the clear zone, the current obstacle frame is determined to be within the clear zone.

[0078] If it is determined that all vertices of the obstacle frame are not within the clear area, then further determine whether the obstacle frame has an intersection with the clear area. If there is an intersection, then determine that the current obstacle frame is within the clear area. If there is no intersection, then determine that the current obstacle frame is not within the clear area. Traverse the clear areas of all ultrasonic radars to determine whether the current obstacle has an intersection with all clear areas.

[0079] If the current obstacle is an obstacle point, the coordinates of the current obstacle point are converted from the world coordinate system to the ego vehicle coordinate system. Based on the coordinates of the obstacle point in the ego vehicle coordinate system, the current obstacle point is determined to be within the clearance zone of any radar. The clearance zones of all ultrasonic radars are traversed to determine whether the coordinates of the current obstacle point are included in any clearance zone.

[0080] Traverse all obstacles in the obstacle list and obtain the positional relationship between all obstacles and each clear area.

[0081] It can be understood that, through the method of this embodiment, regardless of the size of the detected obstacle, it is possible to determine whether there is an intersection (or inclusion relationship) between the obstacle and each radar clearance zone, thereby determining whether the obstacle is a false detection, thereby improving the accuracy of detection.

[0082] In one possible embodiment, Figure 5 As shown, updating the obstacle confidence according to the judgment result includes:

[0083] If the current obstacle is determined to be within the clearance zone of any radar, the confidence level of the current obstacle is lowered; if the current obstacle is determined not to be within the clearance zone of any radar, the confidence level of the current obstacle is not changed.

[0084] It is understandable that when it is confirmed that the current obstacle is contained or intersected with the clearance zone of any radar, the obstacle is considered to be a false detection, and the confidence level of the obstacle can be lowered to ensure that the parking planning module can obtain a reliable parking area for trajectory planning, and the control module obtains accurate obstacle information for obstacle avoidance control, thereby improving the reliability and safety of the parking system.

[0085] In a possible embodiment, updating the obstacle list according to the obstacle confidence level includes:

[0086] Cyclic determination is made to determine whether all obstacles in the obstacle list are within the clear zone of each radar. The confidence level of obstacles is reduced by k in a single cycle, where k is a fixed value. For example, the confidence level of obstacles within the clear zone of any radar is reduced by 25% in each cycle.

[0087] The confidence values ​​of all obstacles are updated in each cycle, and obstacles with a confidence value of 0 are removed from the obstacle list. For example, if an obstacle is determined to be within the clear zone of a radar, its confidence value is reduced by 25% in a single cycle. After four cycles, its confidence value drops to 0, and the obstacle can be removed from the obstacle list, thus achieving the purpose of updating the obstacle list.

[0088] More specifically, the calculation process for a certain obstacle is described as an example.

[0089] First, the obstacle type is determined by the parameters of the obstacle in the obstacle list, which is an obstacle box or an obstacle point. To simplify the description of the calculation process, the obstacle box is taken as a rectangular box for example.

[0090] Assuming the current obstacle is an obstacle point, the coordinates of the obstacle point in the ego-vehicle coordinate system are calculated. The distance L between the obstacle point coordinates and the ultrasonic radar installation location is calculated. The obstacle point coordinates are based on the angle theta of the ego-vehicle coordinate system. The system then checks whether L∈[min_len,dist] and L∈[beta_min,beta_max] satisfy the following conditions: Specifically, the straight-line distance L between the obstacle point and the radar is within the radar's minimum detection range min_len and the radar's real-time detection range dist, and whether the obstacle's angle theta based on the ego-vehicle coordinate system is within the radar's field of view. If both conditions are met, the obstacle point is considered within the radar's clear zone, and the confidence level of the obstacle decreases by k (k can be a preset value, such as 25%). The system then iterates through all 12 radars, confirming the relationship between the current obstacle point and the clear zones of all radars. This process repeats, accumulating the confidence level decreases with each cycle. After four cycles, the confidence level of the obstacle point drops to 0, at which point the obstacle point is removed from the obstacle list.

[0091] Assume the current obstacle is a rectangular obstacle box containing four vertices. The four vertices of the obstacle box are calculated based on the coordinates of the ego-vehicle coordinate system. The above calculation and judgment are performed for each vertex in turn to determine whether the four vertices are within the clearance zone of the current radar. If none of the four vertices are within the clearance zone of the current radar, the sector boundary formed by the clearance zone [min_len, dist] and [beta_min, beta_max] is calculated to determine whether it intersects with the current obstacle's rectangular box. If there is an intersection, it means that part of the obstacle's rectangular box is within (or spans) the clearance zone. The confidence score of the obstacle is decreased by k, and the obstacle is processed by traversing 12 radars in turn. This process is repeated, and as the confidence score of the obstacle box decreases with each cycle, after multiple cycles, the confidence score of the obstacle point drops to 0, at which point the obstacle point is removed from the obstacle list.

[0092] Figure 6 The present invention provides an embodiment of an obstacle filtering system based on ultrasonic real-time detection range, such as Figure 6 As shown, an obstacle filtering system based on ultrasonic real-time detection range includes a pre-processing module, an obstacle detection module and an obstacle filtering module, wherein:

[0093] The pre-processing module is used to calibrate the installation position data of each radar around the vehicle body according to the vehicle coordinate system, and is also used to set the radar parameter table according to the installation position data and specification parameters of each radar;

[0094] The obstacle detection module is used to obtain the real-time detection distance of each radar to obstacles, and obtain the clearance zone of each radar based on the real-time detection distance and radar parameter table. It is also used to obtain the obstacle list after the camera and ultrasonic wave fusion from other modules;

[0095] The obstacle filtering module is used to traverse the obstacle list and determine whether the obstacle is located in the radar's clear area based on its coordinates. It is also used to update the obstacle confidence level based on the judgment result and update the obstacle list based on the obstacle confidence level.

[0096] It can be understood that the obstacle filtering system based on the ultrasonic real-time detection range provided by the present invention corresponds to the obstacle filtering method based on the ultrasonic real-time detection range provided in the aforementioned embodiments. The relevant technical features of the obstacle filtering system based on the ultrasonic real-time detection range can refer to the relevant technical features of the obstacle filtering method based on the ultrasonic real-time detection range, and will not be repeated here.

[0097] See also Figure 7 , Figure 7 Schematic diagram of an embodiment of an electronic device provided by an embodiment of the present invention. Figure 7As shown, an embodiment of the present invention provides an electronic device, including a memory 710, a processor 720, and a computer program 711 stored in the memory 710 and executable on the processor 720. When the processor 720 executes the computer program 711, the following steps are implemented:

[0098] Calibrate the installation position data of each radar around the vehicle body according to the vehicle coordinate system, and set the radar parameter table according to the installation position data and specification parameters of each radar;

[0099] Obtain the real-time detection distance of each radar to obstacles, and obtain the clearance zone of each radar based on the real-time detection distance and radar parameter table; obtain the obstacle list after the camera and ultrasonic fusion from other modules;

[0100] Traverse the obstacle list and determine whether the obstacle is in the radar's clear area based on the obstacle's coordinates; update the obstacle confidence based on the judgment result, and update the obstacle list based on the obstacle confidence.

[0101] See also Figure 8 , Figure 8 Schematic diagram of an embodiment of a computer-readable storage medium provided by the present invention. Figure 8 As shown, this embodiment provides a computer-readable storage medium 800 on which a computer program 811 is stored. When the computer program 811 is executed by a processor, the following steps are implemented:

[0102] Calibrate the installation position data of each radar around the vehicle body according to the vehicle coordinate system, and set the radar parameter table according to the installation position data and specification parameters of each radar;

[0103] Obtain the real-time detection distance of each radar to obstacles, and obtain the clearance zone of each radar based on the real-time detection distance and radar parameter table; obtain the obstacle list after the camera and ultrasonic fusion from other modules;

[0104] Traverse the obstacle list and determine whether the obstacle is in the radar's clear area based on the obstacle's coordinates; update the obstacle confidence based on the judgment result, and update the obstacle list based on the obstacle confidence.

[0105] Embodiments of the present invention provide an obstacle filtering method, system, and storage medium based on ultrasonic real-time detection range. These methods consider obstacles detected by radar that are located within the radar's clear zone as falsely detected obstacles and can be filtered out. Therefore, the coordinates of each obstacle detected by each radar are calculated based on the vehicle's coordinate system. Based on the obstacle's coordinate position in the vehicle's coordinate system, the system determines whether it is located within the clear zone of any radar. If the determination is positive, the confidence level of the obstacle is lowered. The confidence level of obstacles within the clear zone is lowered each time the judgment process repeats. When the confidence level of an obstacle reaches a preset confidence threshold (e.g., a confidence threshold of 0), the obstacle is removed from the obstacle list, thereby updating the obstacle list and obtaining a more accurate obstacle list for parking trajectory planning. This method reduces the false detection rate of obstacles, ensures that the parking planning module obtains reliable parking areas for trajectory planning, and that the control module obtains accurate obstacle information for obstacle avoidance control, thereby improving the reliability and safety of the parking system.

[0106] It should be noted that, in the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0107] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0108] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0109] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0110] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0111] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0112] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. An obstacle filtering method based on ultrasonic real-time detection range, characterized in that: include: Calibrate the installation position data of each radar around the vehicle body according to the vehicle coordinate system, and set the radar parameter table according to the installation position data and specification parameters of each radar; Obtain the real-time detection distance of each radar to obstacles, and obtain the clearance zone of each radar based on the real-time detection distance and radar parameter table; obtain the obstacle list after the camera and ultrasonic fusion from other modules; Traverse the obstacle list and determine whether the obstacle is in the radar's clear area based on the obstacle's coordinates; update the obstacle confidence based on the judgment result, and update the obstacle list based on the obstacle confidence.

2. The obstacle filtering method based on ultrasonic real-time detection range according to claim 1, characterized in that: The coordinates of each radar are calibrated according to the vehicle coordinate system, including: The vehicle coordinate system is established with the X-axis positive direction forward along the vehicle's front, and the Y-axis positive direction perpendicular to the vehicle body and pointing leftward. The installation position data of all ultrasonic radars are measured and calibrated based on the vehicle coordinate system. The installation position data at least includes the coordinate points of the radars and the installation angles of the radars.

3. The obstacle filtering method based on ultrasonic real-time detection range according to claim 1, characterized in that: The parameters of the radar parameter table include at least: The numbers, x-coordinate values, y-coordinate values, installation angles, field of view angles, and detection distances of all radars.

4. The obstacle filtering method based on ultrasonic real-time detection range according to claim 1 or 3, characterized in that: The method of obtaining the clearance area of ​​each radar according to the real-time detection distance dist and the radar parameter table includes: Obtain the field of view and minimum detection distance of any radar through the radar parameter table; Taking the minimum detection range of the current radar as the radius, intercepting the first sector within the field of view of the current radar; Using the real-time detection distance dist of the current radar as the radius, intercept the second sector within the field of view of the current radar; The overlapping area between the second sector and the first sector is removed, and the remaining area is used as the clearance area of ​​the current radar; Traverse all radars in the radar parameter table and obtain the clearance areas of all radars.

5. The obstacle filtering method based on ultrasonic real-time detection range according to claim 1, characterized in that: Determine whether the obstacle is located in the radar's clear area based on the obstacle's coordinates, including: Determine whether an obstacle is an obstacle frame or an obstacle point: If the obstacle is an obstacle frame, the coordinates of each vertex of the obstacle frame are converted from the world coordinate system to the ego vehicle coordinate system. Based on the coordinates of the vertex in the ego vehicle coordinate system, it is determined whether the vertex is within the clear zone of any radar. The coordinates of all vertices of the current obstacle are traversed. If at least one vertex is within the clear zone, the current obstacle frame is determined to be within the clear zone. If it is determined that all vertices of the current obstacle frame are not within the clear area, then further determine whether the current obstacle frame and the clear area have an intersection. If there is an intersection, then determine that the current obstacle frame is within the clear area. If there is no intersection, then determine that the current obstacle frame is not within the clear area. If the obstacle is an obstacle point, converting the coordinates of the obstacle point from the world coordinate system to the ego vehicle coordinate system, and determining whether the obstacle point is within the clearance zone of any radar based on the coordinates of the obstacle point based on the ego vehicle coordinate system; Iterate over all obstacles in the obstacle list.

6. The obstacle filtering method based on ultrasonic real-time detection range according to claim 1 or 5, characterized in that: Updating the obstacle confidence level according to the judgment result includes: If the current obstacle is determined to be within the clearance zone of any radar, the confidence level of the current obstacle is lowered; if the current obstacle is determined not to be within the clearance zone of any radar, the confidence level of the current obstacle is not changed.

7. The obstacle filtering method based on ultrasonic real-time detection range according to claim 6, characterized in that: The updating of the obstacle list according to the obstacle confidence level includes: Cyclic determination is made whether all obstacles in the obstacle list are within the clear zone of each radar. The value by which the obstacle confidence is reduced in a single cycle is k, where k is a constant value. The confidence values ​​of all obstacles are updated in each cycle, and obstacles with a confidence value of 0 are removed from the obstacle list.

8. An obstacle filtering system based on ultrasonic real-time detection range, characterized in that: include: The pre-processing module is used to calibrate the installation position data of each radar around the vehicle body according to the vehicle coordinate system, and is also used to set the radar parameter table according to the installation position data and specification parameters of each radar; The obstacle detection module is used to obtain the real-time detection distance of each radar to obstacles, and obtain the clearance zone of each radar based on the real-time detection distance and radar parameter table. It is also used to obtain the obstacle list after the camera and ultrasonic wave fusion from other modules; The obstacle filtering module is used to traverse the obstacle list and determine whether the obstacle is in the radar's clear area based on the obstacle's coordinates; It is also used to update the obstacle confidence level based on the judgment result and update the obstacle list based on the obstacle confidence level.

9. An electronic device, characterized in that: The system comprises a memory and a processor, wherein the processor is used to implement the steps of the obstacle filtering method based on the ultrasonic real-time detection range as described in any one of claims 1 to 7 when executing the computer management program stored in the memory.

10. A computer-readable storage medium, characterized in that A computer management program is stored thereon, and when the computer management program is executed by the processor, the steps of the obstacle filtering method based on the ultrasonic real-time detection range as described in any one of claims 1 to 7 are implemented.

Images