Blind area detection method and apparatus, computer device and readable storage medium
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- VANJEE TECHNOLOGY CO LTD
- Filing Date
- 2021-07-29
- Publication Date
- 2026-05-29
AI Technical Summary
Blind spots caused by obstacles in the field of view of lidar are difficult to detect effectively, affecting the target detection and tracking performance.
By acquiring radar point cloud data from lidar scanning, the actual optical path length of the laser beam is determined and compared with the theoretical optical path length in a preset blind zone detection database. If the actual optical path length is less than the theoretical optical path length, the blind zone area of the lidar is determined according to the database.
It enables rapid and effective detection of blind spots in the lidar field of view, improving the accuracy and efficiency of detection and reducing the dependence on the quality of lidar target detection.
Smart Images
Figure CN115687842B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of radar technology, and in particular to a blind zone detection method, apparatus, computer equipment, and readable storage medium. Background Technology
[0002] LiDAR can emit low-power, eye-safe laser beams to detect, track, and identify targets, thereby obtaining parameters such as the target's distance, orientation, altitude, speed, attitude, and even shape.
[0003] Normally, when a lidar is in operation, if the laser beam encounters an obstacle during transmission, the obstacle will block the target behind it, resulting in a blind spot in the lidar's field of view. This will affect the detection and tracking of the target.
[0004] Therefore, how to effectively detect blind spots in the field of view of lidar so as to take timely measures to reduce the adverse effects caused by blind spots has become an urgent problem to be solved. Summary of the Invention
[0005] Therefore, it is necessary to provide a blind spot detection method, device, computer equipment, and readable storage medium that can effectively detect blind spots in the field of view of a lidar, in order to address the above-mentioned technical problems.
[0006] In a first aspect, embodiments of this application provide a blind zone detection method, the method comprising:
[0007] Acquire radar point cloud data scanned by lidar, and determine the actual optical path length corresponding to the laser beam of lidar based on the radar point cloud data;
[0008] The theoretical optical path length corresponding to the laser beam is obtained from the preset blind zone detection database, and it is detected whether the actual optical path length is less than the theoretical optical path length. The theoretical optical path length is the optical path length of the laser beam in the optical path when there are no obstacles in the optical path of the laser beam.
[0009] If the actual optical path length is less than the theoretical optical path length, the blind zone of the lidar is determined according to the blind zone detection database.
[0010] In one embodiment, determining the blind zone region of the lidar based on the blind zone detection database includes:
[0011] Obtain the landing point position of the theoretical landing point corresponding to the theoretical optical path length of the laser beam from the blind zone detection database;
[0012] The blind zone area is determined based on the location of the landing point.
[0013] In one embodiment, the number of laser beams is multiple, and determining the blind zone region based on the landing point position includes:
[0014] The target region is obtained by performing envelope fitting on the landing point position corresponding to each laser beam, and the target region is used as the blind zone region.
[0015] In one embodiment, the number of laser beams is one, and determining the blind zone region based on the landing point position includes:
[0016] The area within a preset distance range around the landing point is defined as the blind zone.
[0017] In one embodiment, the method further includes:
[0018] Determine the horizontal and vertical angles corresponding to the laser beam, wherein the horizontal angle is used to characterize the rotation angle of the laser beam along the horizontal direction, and the vertical angle is used to characterize the angle between the laser beam and the horizontal direction;
[0019] Based on the horizontal angle and the vertical angle, the vertical height of the target between the radar position of the lidar and the landing point position is determined;
[0020] Based on the target's vertical height and the vertical angle, the theoretical optical path length is obtained, and the theoretical optical path length is stored in the blind zone detection database corresponding to the laser beam.
[0021] In one embodiment, determining the target vertical height between the lidar position and the impact point position based on the horizontal angle and the vertical angle includes:
[0022] Based on the rotation angle range to which the horizontal angle belongs, the sector area information corresponding to the rotation angle range is determined. The sector area information is used to characterize the position range of the sector scanning area of the lidar and the rotation angle range.
[0023] Based on the sector area information, determine the candidate vertical height corresponding to each sector area in the sector scan area;
[0024] The target vertical height is determined from the candidate vertical heights based on the vertical angle.
[0025] In one embodiment, determining the target vertical height from the candidate vertical heights based on the vertical angle includes:
[0026] For each candidate vertical height, the horizontal distance between the radar position and the landing point position is obtained based on the vertical angle and the candidate vertical height;
[0027] If the horizontal distance is within the horizontal distance range between the target sector region corresponding to the candidate vertical height and the radar position, then the candidate vertical height is taken as the target vertical height.
[0028] In one embodiment, the method further includes:
[0029] Based on the horizontal distance and the vertical angle, the landing point position of the theoretical landing point corresponding to the theoretical optical path length of the laser beam is obtained;
[0030] The location of the impact point, corresponding to the laser beam, is stored in the blind zone detection database.
[0031] Secondly, embodiments of this application provide a blind spot detection device, the device comprising:
[0032] The first acquisition module is used to acquire radar point cloud data scanned by the lidar, and determine the actual optical path length corresponding to the laser beam of the lidar based on the radar point cloud data.
[0033] The detection module is used to obtain the theoretical optical path length corresponding to the laser beam from a preset blind zone detection database, and to detect whether the actual optical path length is less than the theoretical optical path length, wherein the theoretical optical path length is the optical path length of the laser beam in the optical path when there are no obstacles in the optical path of the laser beam;
[0034] The first determining module is used to determine the blind zone region of the lidar based on the blind zone detection database if the actual optical path length is less than the theoretical optical path length.
[0035] Thirdly, embodiments of this application provide a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method described in the first aspect above.
[0036] Fourthly, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method described in the first aspect above.
[0037] The beneficial effects of the technical solutions provided in this application include at least the following:
[0038] The aforementioned blind zone detection method, apparatus, computer equipment, and readable storage medium acquire radar point cloud data scanned by a lidar, determine the actual optical path length corresponding to the lidar's laser beam based on the radar point cloud data, then retrieve the theoretical optical path length corresponding to the laser beam from a preset blind zone detection database, and detect whether the actual optical path length is less than the theoretical optical path length. The theoretical optical path length is the optical path length of the laser beam in the optical path when there are no obstacles in the laser beam's optical path. Thus, if the actual optical path length is less than the theoretical optical path length, the blind zone area of the lidar is determined according to the blind zone detection database. Since the optical path length of the laser beam is shortened when there are obstacles in the laser beam's optical path compared to when there are no obstacles, by comparing the actual optical path length with the theoretical optical path length, the existence of a blind zone in the lidar's field of view can be quickly and effectively determined, thereby identifying the blind zone area of the lidar and achieving effective detection of blind zones in the lidar's field of view. Attached Figure Description
[0039] Figure 1-a This is a schematic diagram of the implementation environment of the blind zone detection method in one embodiment;
[0040] Figure 1-b This is a schematic diagram of the implementation environment for the blind zone detection method in another embodiment;
[0041] Figure 2 This is a flowchart illustrating a blind zone detection method in one embodiment;
[0042] Figure 3 This is a schematic diagram illustrating the optical path length corresponding to an exemplary laser beam;
[0043] Figure 4 This is a schematic diagram illustrating the optical path length corresponding to another exemplary laser beam.
[0044] Figure 5 This is a flowchart illustrating the process of determining the blind zone area of a lidar in another embodiment;
[0045] Figure 6 This is a schematic diagram of the process for obtaining the theoretical optical path length in another embodiment;
[0046] Figure 7 This is a schematic diagram illustrating an exemplary sector division of the area surrounding a lidar.
[0047] Figure 8 This is a flowchart illustrating step 602 in another embodiment;
[0048] Figure 9 This is a flowchart illustrating step 803 in another embodiment;
[0049] Figure 10 This is a schematic diagram illustrating the division of sectors within an exemplary sector-shaped scanning area;
[0050] Figure 11 This is a flowchart illustrating the process of obtaining the landing point location of the theoretical landing point in another embodiment;
[0051] Figure 12 This is a structural block diagram of a blind zone detection device in one embodiment;
[0052] Figure 13 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation
[0053] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.
[0054] The blind zone detection method, apparatus, computer equipment, and readable storage medium provided in this application can effectively detect blind zones in the field of view of a lidar. The technical solutions of this application will be described in detail below through embodiments, in conjunction with the accompanying drawings and implementation environment. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.
[0055] Figure 1-a This is a schematic diagram of an implementation environment involved in the blind zone detection method provided in the embodiments of this application, such as... Figure 1-a As shown, the implementation environment may include lidar 101.
[0056] exist Figure 1-a In the implementation environment shown, the lidar 101 can acquire radar point cloud data scanned by the lidar 101, and determine the actual optical path length corresponding to the laser beam of the lidar 101 based on the radar point cloud data; the lidar 101 can obtain the theoretical optical path length corresponding to the laser beam from a preset blind zone detection database, and detect whether the actual optical path length is less than the theoretical optical path length, where the theoretical optical path length is the optical path length of the laser beam in the optical path when there are no obstacles in the optical path of the laser beam; if the actual optical path length is less than the theoretical optical path length, the lidar 101 determines the blind zone area of the lidar 101 based on the blind zone detection database.
[0057] Figure 1-b A schematic diagram illustrating another implementation environment involved in the blind zone detection method provided in the embodiments of this application, as shown below. Figure 1-bAs shown, the implementation environment may include a lidar 101 and a computer device 102, which can communicate with each other via a wired network or a wireless network.
[0058] The computer device 102 can be a roadside computing unit / terminal / edge server. Optionally, the computer device 102 can also be a cloud server, a vehicle-mounted computing unit / terminal, etc. The type of computer device 102 is not specifically limited here.
[0059] exist Figure 1-b In the implementation environment shown, the lidar 101 can acquire radar point cloud data scanned by the lidar 101 and send the radar point cloud data to the computer device 102. After acquiring the radar point cloud data scanned by the lidar 101, the computer device 102 can determine the actual optical path length corresponding to the laser beam of the lidar 101 based on the radar point cloud data. The computer device 102 can obtain the theoretical optical path length corresponding to the laser beam from a preset blind zone detection database and detect whether the actual optical path length is less than the theoretical optical path length. The theoretical optical path length is the optical path length of the laser beam in the optical path when there are no obstacles in the optical path of the laser beam. If the actual optical path length is less than the theoretical optical path length, the computer device 102 determines the blind zone area of the lidar 101 based on the blind zone detection database.
[0060] In one embodiment, such as Figure 2 As shown, a blind zone detection method is provided, which is applied to... Figure 1-b The method described in this application will be illustrated using a computer device as an example. It should be noted that the method described in this embodiment can also be applied to… Figure 1-a The method can be implemented by a combination of vehicle-mounted, cloud-based, and roadside computing devices, or by a LiDAR system. The specific task allocation in this method can be flexibly set based on requirements, and this application does not limit it.
[0061] The method includes steps 201, 202, and 203:
[0062] Step 201: The computer device acquires the radar point cloud data scanned by the lidar and determines the actual optical path length corresponding to the laser beam of the lidar based on the radar point cloud data.
[0063] In this embodiment of the application, the lidar can be a roadside lidar, which can be installed on any marker, such as tree trunks, lampposts, etc.; of course, the lidar can also be other types of lidar, and the type of lidar is not limited here.
[0064] During operation, a lidar system emits a laser beam to scan its surroundings, outputting lidar point cloud data which is then sent to a computer. This point cloud data contains a wealth of information, including the optical path length of the laser beam, as well as coordinates, color, reflection intensity, echo count, and more.
[0065] Optical path length refers to the length of the optical path that a laser beam travels from the laser of a lidar to a target (or obstacle) in the surrounding environment.
[0066] See Figure 3 , Figure 3 This is a schematic diagram illustrating the optical path length corresponding to an exemplary laser beam. For example... Figure 3 As shown, the optical path length L is the length of the optical path that the laser beam travels from the laser of the lidar to the target (ground) in the surrounding environment.
[0067] See Figure 4 , Figure 4 This is another exemplary schematic diagram of the optical path length corresponding to a laser beam. For example... Figure 4 As shown, the optical path length L′ is the length of the optical path that the laser beam travels from the laser of the lidar to an obstacle in the surrounding environment.
[0068] After the computer equipment obtains the radar point cloud data sent by the lidar, it can parse the optical path length corresponding to the laser beam from the radar point cloud data. This optical path length is the actual optical path length of the laser beam during the current working process.
[0069] Step 202: The computer device obtains the theoretical optical path length corresponding to the laser beam from the preset blind zone detection database and detects whether the actual optical path length is less than the theoretical optical path length.
[0070] In this embodiment, the blind spot detection database can pre-set the theoretical optical path length corresponding to the laser beam. This theoretical optical path length is the optical path length of the laser beam in the optical path when there are no obstacles in the optical path of the laser beam. As described above. Figure 3 As shown, when there are no obstacles in the optical path of the laser beam, the laser beam will hit the target (ground) directly without being blocked by obstacles. Thus, the length L of the optical path from the laser of the lidar to the target is the theoretical optical path length.
[0071] It's understandable that, since light travels in a straight line, the optical path length of a laser beam is shorter than that of a lidar beam if there are obstacles in its path—that is, if there is an obstacle between the lidar and the target. Please refer to... Figure 3and Figure 4 It is understandable that the optical path length L′ measured when there is an obstacle in the optical path of the laser beam will be less than the optical path length L measured when there is no obstacle in the optical path.
[0072] Based on the aforementioned characteristics of optical path length, in this embodiment of the application, the computer device can detect whether the actual optical path length corresponding to the laser beam during the current working process is less than the theoretical optical path length corresponding to the laser beam, and determine whether there is an obstacle in the optical path of the laser beam based on the detection result.
[0073] Step 203: If the actual optical path length is less than the theoretical optical path length, the computer device determines the blind zone area of the lidar based on the blind zone detection database.
[0074] If the actual optical path length is less than the theoretical optical path length, the computer equipment determines that there is an obstacle in the optical path of the laser beam, that is, there is an obstacle between the lidar and the target. The computer equipment then determines the blind zone area of the lidar based on the blind zone detection database.
[0075] As one implementation method, the blind zone detection database can also store the range of the blind zone area corresponding to the theoretical optical path length. In this way, the computer device can determine the range of the blind zone area corresponding to the theoretical optical path length based on the blind zone detection database and use this range as the blind zone area of the lidar. The range of the blind zone area corresponding to the theoretical optical path length can be a preset distance range around the landing point of the laser beam at that theoretical optical path length.
[0076] If the actual optical path length is equal to the theoretical optical path length, since the theoretical optical path length is the optical path length of the laser beam in the optical path when there are no obstacles in the optical path of the laser beam, the computer device will determine that there are no obstacles in the optical path of the laser beam.
[0077] The above embodiment acquires radar point cloud data scanned by the lidar and determines the actual optical path length corresponding to the lidar's laser beam based on the radar point cloud data. Then, it obtains the theoretical optical path length corresponding to the laser beam from a preset blind zone detection database and detects whether the actual optical path length is less than the theoretical optical path length. The theoretical optical path length is the optical path length of the laser beam in the optical path when there are no obstacles in the laser beam's optical path. If the actual optical path length is less than the theoretical optical path length, the blind zone area of the lidar is determined according to the blind zone detection database. In this way, since the optical path length of the laser beam is shortened when there are obstacles in the laser beam's optical path compared to when there are no obstacles, by comparing the size of the actual optical path length and the theoretical optical path length, it is possible to quickly and effectively determine whether there is a blind zone in the lidar's field of view, thereby determining the blind zone area of the lidar and achieving effective detection of blind zones in the lidar's field of view.
[0078] It should be noted that while some related technologies employ blind zone detection methods based on LiDAR target detection results, these methods rely heavily on the quality of LiDAR target detection. Poor LiDAR target detection quality significantly reduces the accuracy of blind zone detection. This application's embodiment starts from the perspective of the original point cloud, thus eliminating reliance on the quality of LiDAR target detection and improving the accuracy of blind zone detection.
[0079] In one embodiment, based on Figure 2 The illustrated embodiment can be found in [reference]. Figure 5 This embodiment describes the process by which a computer device determines the blind zone area of a lidar based on a blind zone detection database. For example... Figure 5 As shown, the process includes steps 501 and 502:
[0080] Step 501: The computer device obtains the landing point position of the theoretical landing point corresponding to the theoretical optical path length of the laser beam from the blind spot detection database.
[0081] In this embodiment of the application, the blind spot detection database can preset the landing point position of the theoretical landing point corresponding to the theoretical optical path length. The theoretical landing point is the landing point where the laser beam reaches the target when there are no obstacles in the optical path of the laser beam. The landing point position can be the position coordinates of the theoretical landing point.
[0082] Step 502: The computer device determines the blind zone area based on the landing point location.
[0083] In one possible implementation of step 502, there are multiple laser beams. For each laser beam, the computer device obtains the theoretical landing point position corresponding to the laser beam from the blind zone detection database. Then, the computer device performs envelope fitting processing on the landing point positions corresponding to each laser beam to obtain the target area, and uses the target area as the blind zone area.
[0084] In another possible implementation of step 502, the number of laser beams is one. After the computer device obtains the theoretical landing point location of the laser beam from the blind spot detection database, the computer device uses the area within a preset distance range around the landing point location as the blind spot area. The preset distance can be set by the user during implementation, for example, it can be set to one meter, two meters, etc.
[0085] In this way, the above embodiment compares the actual optical path length with the theoretical optical path length, and when the actual optical path length is less than the theoretical optical path length, obtains the theoretical landing point of the laser beam from the blind zone detection database, and obtains the blind zone area by performing simple processing based on the landing point position. The computer equipment does not need to perform complex calculations in the entire blind zone detection process, and the amount of calculation and complexity are low, which helps to improve the efficiency of blind zone detection.
[0086] In one embodiment, based on Figure 5 The illustrated embodiment can be found in [reference]. Figure 6 This embodiment relates to the process by which a computer device calculates the theoretical optical path length. For example... Figure 6 As shown, the process includes steps 601, 602, and 603:
[0087] Step 601: The computer device determines the horizontal and vertical angles corresponding to the laser beam.
[0088] The horizontal angle is used to characterize the rotation angle of the laser beam along the horizontal direction. For example, if the laser beam of the lidar rotates at a horizontal angle of 30° during the current operation, then the corresponding horizontal angle of the laser beam is 30°. The vertical angle is used to characterize the angle between the laser beam and the horizontal direction. For example, if the angle between the laser beam and the horizontal direction is 45° during the current operation, then the corresponding vertical angle of the laser beam is 45°.
[0089] Step 602: The computer device determines the vertical height of the target between the radar position and the landing point position of the lidar based on the horizontal and vertical angles.
[0090] In this embodiment of the application, the area around the lidar can be divided into sectors in advance to facilitate the calculation of the theoretical optical path length of the laser beam at each different horizontal angle of the lidar.
[0091] For example, see Figure 7 , Figure 7 This is an exemplary schematic diagram of sector division of the area surrounding a lidar, such as... Figure 7 As shown, the area around the lidar can first be divided into several sector scanning areas according to the rotation angle range (e.g., 0°~45°, 45°~90°, etc.), with each rotation angle range corresponding to a sector scanning area. Then, according to the horizontal distance from the center (i.e., the lidar), each sector scanning area can be divided into multiple sector areas.
[0092] It should be noted that in other embodiments, the number of fan-shaped scanning areas and sector areas can be adjusted according to the actual terrain and topography of the area surrounding the lidar.
[0093] After dividing the area surrounding the lidar into sectors, the computer equipment can store the sector division results and the candidate vertical heights corresponding to each sector in the blind zone detection database. These candidate vertical heights are the pre-measured vertical distances between the lidar and the sector. In this way, the computer equipment can determine the target's vertical height between the lidar's position and its impact point based on the horizontal angle, vertical angle, and the blind zone detection database.
[0094] In one possible implementation of step 602, see [link to step 602] Figure 8 Step 602 may include steps 801, 802 and 803:
[0095] Step 801: The computer device determines the sector area information corresponding to the rotation angle range based on the rotation angle range to which the horizontal angle belongs.
[0096] The computer device can pre-set a first mapping relationship between each horizontal angle and each rotation angle range, and a second mapping relationship between each rotation angle range and each sector area information. Based on this first mapping relationship, the computer device can determine the rotation angle range to which a horizontal angle belongs; for example, it can determine that the rotation angle range to which a horizontal angle of 30° belongs is 0° to 45°.
[0097] Next, the computer device determines the sector area information corresponding to the rotation angle range based on the second mapping relationship.
[0098] Step 802: The computer device determines the candidate vertical height corresponding to each sector in the sector scanning area based on the sector area information.
[0099] In this embodiment, the sector area information is used to characterize the position range of the sector scanning area corresponding to the rotation angle interval of the lidar. This sector area information may include the position range of each sector within the sector scanning area and the candidate vertical height corresponding to each sector. Thus, the computer device can determine the candidate vertical height corresponding to each sector within the sector scanning area.
[0100] Step 803: The computer device determines the target vertical height from the candidate vertical heights based on the vertical angle.
[0101] In one possible implementation of step 803, see [link to step 803]. Figure 9 Step 803 may include steps 8031 and 8032:
[0102] Step 8031: For each candidate vertical height, the computer device obtains the horizontal distance between the radar position and the landing point position based on the vertical angle and the candidate vertical height.
[0103] Step 8032: If the horizontal distance is within the horizontal distance range between the target sector area corresponding to the candidate vertical height and the radar position, the computer device will use the candidate vertical height as the target vertical height.
[0104] The following, combined with Figure 10 The implementation method of step 803 will be briefly described below. Figure 10 This is an exemplary schematic diagram illustrating the division of sectors within a sector-shaped scanning area.
[0105] like Figure 10 As shown, assuming the vertical angle is θ, the sector regions in this sector scanning area include sector region 1, sector region 2, sector region 3, sector region 4, sector region 5, sector region 6, and sector region 7. The position range of sector region 1 is d0-d1, the position range of sector region 2 is d1-d2, ..., and the position range of sector region 7 is d6-d7. The candidate vertical height of sector region 1 is h1, the candidate vertical height of sector region 2 is h2, ..., and the candidate vertical height of sector region 7 is h7.
[0106] For each candidate vertical height, for example, for the candidate vertical height h7 of sector region 7, the computer device substitutes the vertical angle θ and the candidate vertical height h7 into the following formula 1 to obtain the horizontal distance d between the radar position and the impact point position:
[0107] d = h / tanθ (Formula 1)
[0108] After obtaining the horizontal distance d, the computer device detects whether the horizontal distance d is within the horizontal distance range between the target sector area (sector area 7) corresponding to the candidate vertical height h7 and the radar position, that is, whether the horizontal distance d is within [d6, d7]. If it is, the computer device takes the candidate vertical height h7 as the target vertical height.
[0109] Step 603: The computer device obtains the theoretical optical path length based on the target's vertical height and vertical angle, and stores the theoretical optical path length corresponding to the laser beam in the blind zone detection database.
[0110] The computer equipment substitutes the vertical angle θ and the target vertical height h7 into the following formula 2 to obtain the theoretical optical path length L:
[0111] L=h / sinθ Formula 2
[0112] The computer equipment stores the calculated theoretical optical path length, corresponding to the laser beam, in the blind zone detection database.
[0113] Therefore, by dividing the area around the lidar into sectors and storing the sector division results and the candidate vertical heights corresponding to each sector, the target vertical height between the lidar position and the landing point is determined from each candidate vertical height based on the horizontal and vertical angles. Then, the theoretical optical path length can be obtained based on the target vertical height and vertical angle. The computer equipment does not need to perform complex calculations during the entire blind zone detection process, resulting in low computational load and complexity, which helps to improve the efficiency of blind zone detection.
[0114] The following is a brief introduction to how computer equipment obtains the theoretical landing point's location.
[0115] based on Figure 9 The illustrated embodiment can be found in [reference]. Figure 11 The process may include steps 1101 and 1102:
[0116] Step 1101: The computer device obtains the theoretical landing point position of the laser beam corresponding to the theoretical optical path length based on the horizontal distance and vertical angle.
[0117] The horizontal distance is the distance between the theoretical landing point and the origin of the coordinate system. Based on the horizontal distance, the vertical angle, and trigonometric relationships, the computer can calculate the landing position of the theoretical landing point.
[0118] Specifically, the computer equipment can calculate the x-coordinate of the theoretical landing point according to Formula 3, and the y-coordinate of the theoretical landing point according to Formula 4:
[0119] x = d * cosθ (Formula 3)
[0120] y=d*sinθ Formula 4
[0121] The computer equipment uses the calculated (x,y) as the theoretical landing point position.
[0122] Step 1102: The computer device stores the landing point location corresponding to the laser beam in the blind zone detection database.
[0123] After the computer equipment calculates the theoretical landing point position corresponding to the theoretical optical path length of the laser beam, it stores the landing point position corresponding to the laser beam in the blind zone detection database. In this way, during the blind zone detection process, if the computer equipment determines that the actual optical path length of the laser beam is less than the theoretical optical path length, it retrieves the landing point position corresponding to the theoretical optical path length of the laser beam from the blind zone detection database, and quickly determines the blind zone area based on the landing point position, thereby realizing the effective detection of blind zones in the field of view of the lidar.
[0124] In one embodiment, a blind zone detection method is provided, which is applied to... Figure 1-b Taking computer devices as an example, the method includes:
[0125] Step a: The computer equipment determines the horizontal and vertical angles corresponding to the laser beam.
[0126] The horizontal angle is used to characterize the rotation angle of the laser beam along the horizontal direction, and the vertical angle is used to characterize the angle between the laser beam and the horizontal direction.
[0127] Step b: The computer device determines the sector area information corresponding to the rotation angle range based on the rotation angle range to which the horizontal angle belongs.
[0128] Among them, the sector area information is used to characterize the position range of the sector scanning area corresponding to the rotation angle interval of the lidar.
[0129] Step c: The computer device determines the candidate vertical height corresponding to each sector in the sector scanning area based on the sector area information.
[0130] Step d: For each candidate vertical height, the computer device obtains the horizontal distance between the radar position and the landing point position based on the vertical angle and the candidate vertical height.
[0131] Step e: If the horizontal distance is within the horizontal distance range between the target sector area corresponding to the candidate vertical height and the radar position, the computer device will use the candidate vertical height as the target vertical height.
[0132] Step f: The computer device obtains the theoretical optical path length based on the target's vertical height and vertical angle, and stores the theoretical optical path length corresponding to the laser beam in the blind zone detection database.
[0133] Step g: The computer device obtains the theoretical landing point position of the laser beam corresponding to the theoretical optical path length based on the horizontal distance and vertical angle.
[0134] In step h, the computer device stores the location of the laser beam corresponding to the landing point in the blind zone detection database.
[0135] Step i: The computer device acquires the radar point cloud data scanned by the lidar and determines the actual optical path length corresponding to the laser beam of the lidar based on the radar point cloud data.
[0136] Step j: The computer device obtains the theoretical optical path length corresponding to the laser beam from the blind spot detection database and detects whether the actual optical path length is less than the theoretical optical path length.
[0137] The theoretical optical path length is the optical path length of the laser beam in the optical path when there are no obstacles in the optical path of the laser beam.
[0138] In step k, if the actual optical path length is less than the theoretical optical path length, the computer device obtains the landing point position of the theoretical landing point corresponding to the theoretical optical path length from the blind zone detection database, and determines the blind zone area based on the landing point position.
[0139] In one possible implementation, there are multiple laser beams, and the blind zone is determined based on the landing point position, including: performing envelope fitting processing on the landing point position corresponding to each laser beam to obtain the target area, and using the target area as the blind zone.
[0140] In another possible implementation, the number of laser beams is one, and the blind zone area is determined according to the landing point position, including: taking the area within a preset distance range around the landing point position as the blind zone area.
[0141] It should be understood that although the steps in the flowchart above are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowchart above may include multiple steps or stages, which are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps.
[0142] In one embodiment, such as Figure 12 As shown, a blind spot detection device is provided, comprising:
[0143] The first acquisition module 100 is used to acquire radar point cloud data scanned by the lidar and determine the actual optical path length corresponding to the laser beam of the lidar based on the radar point cloud data.
[0144] The detection module 200 is used to obtain the theoretical optical path length corresponding to the laser beam from a preset blind zone detection database, and to detect whether the actual optical path length is less than the theoretical optical path length, wherein the theoretical optical path length is the optical path length of the laser beam in the optical path when there are no obstacles in the optical path of the laser beam;
[0145] The first determining module 300 is used to determine the blind zone region of the lidar based on the blind zone detection database if the actual optical path length is less than the theoretical optical path length.
[0146] In one embodiment, the first determining module 300 includes:
[0147] The first acquisition unit is used to acquire the landing position of the theoretical landing point corresponding to the theoretical optical path length of the laser beam from the blind zone detection database.
[0148] The first determining unit is used to determine the blind zone area based on the landing point location.
[0149] In one embodiment, there are multiple laser beams, and the first determining unit is specifically used to perform envelope fitting processing on the landing position corresponding to each laser beam to obtain the target area, and to use the target area as the blind area.
[0150] In one embodiment, the number of laser beams is one, and the first determining unit is specifically used to define the area within a preset distance range around the landing point as the blind zone area.
[0151] In one embodiment, the apparatus further includes:
[0152] The second determining module is used to determine the horizontal angle and vertical angle corresponding to the laser beam, wherein the horizontal angle is used to characterize the rotation angle of the laser beam along the horizontal direction, and the vertical angle is used to characterize the angle between the laser beam and the horizontal direction.
[0153] The third determining module is used to determine the vertical height of the target between the radar position of the lidar and the landing point position based on the horizontal angle and the vertical angle.
[0154] The second acquisition module is used to acquire the theoretical optical path length based on the target's vertical height and the vertical angle, and store the theoretical optical path length corresponding to the laser beam in the blind zone detection database.
[0155] In one embodiment, the third determining module includes:
[0156] The second determining unit is used to determine the sector area information corresponding to the rotation angle interval according to the rotation angle interval to which the horizontal angle belongs. The sector area information is used to characterize the position range of the sector scanning area of the lidar and the rotation angle interval.
[0157] The third determining unit is used to determine the candidate vertical height corresponding to each sector in the sector scanning area based on the sector area information.
[0158] The fourth determining unit is used to determine the target vertical height from the candidate vertical heights based on the vertical angle.
[0159] In one embodiment, the fourth determining unit is specifically used to obtain the horizontal distance between the radar position and the landing point position based on the vertical angle and the candidate vertical height for each candidate vertical height; if the horizontal distance is within the range of the horizontal distance between the target sector area corresponding to the candidate vertical height and the radar position, then the candidate vertical height is used as the target vertical height.
[0160] In one embodiment, the third determining module further includes:
[0161] The second acquisition unit is used to acquire the landing point position of the theoretical landing point corresponding to the theoretical optical path length of the laser beam based on the horizontal distance and the vertical angle.
[0162] A storage unit is used to store the landing point position corresponding to the laser beam in the blind zone detection database.
[0163] Specific limitations regarding the blind spot detection device can be found in the limitations of the blind spot detection method described above, and will not be repeated here. Each module in the aforementioned blind spot detection device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.
[0164] In one embodiment, a computer device is provided, the internal structure of which can be shown as follows: Figure 13As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores data related to the blind zone detection method. The network interface communicates with external terminals via a network connection. When the computer program is executed by the processor, it implements a blind zone detection method.
[0165] Those skilled in the art will understand that Figure 13 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.
[0166] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:
[0167] Acquire radar point cloud data scanned by lidar, and determine the actual optical path length corresponding to the laser beam of lidar based on the radar point cloud data;
[0168] The theoretical optical path length corresponding to the laser beam is obtained from the preset blind zone detection database, and it is detected whether the actual optical path length is less than the theoretical optical path length. The theoretical optical path length is the optical path length of the laser beam in the optical path when there are no obstacles in the optical path of the laser beam.
[0169] If the actual optical path length is less than the theoretical optical path length, the blind zone of the lidar is determined according to the blind zone detection database.
[0170] In one embodiment, the processor, when executing a computer program, also performs the following steps:
[0171] Obtain the landing point position of the theoretical landing point corresponding to the theoretical optical path length of the laser beam from the blind zone detection database;
[0172] The blind zone area is determined based on the location of the landing point.
[0173] In one embodiment, the number of laser beams is multiple, and the processor, when executing the computer program, further performs the following steps:
[0174] The target region is obtained by performing envelope fitting on the landing point position corresponding to each laser beam, and the target region is used as the blind zone region.
[0175] In one embodiment, the number of laser beams is one, and the processor, when executing the computer program, further performs the following steps:
[0176] The area within a preset distance range around the landing point is defined as the blind zone.
[0177] In one embodiment, the processor, when executing a computer program, also performs the following steps:
[0178] Determine the horizontal and vertical angles corresponding to the laser beam, wherein the horizontal angle is used to characterize the rotation angle of the laser beam along the horizontal direction, and the vertical angle is used to characterize the angle between the laser beam and the horizontal direction;
[0179] Based on the horizontal angle and the vertical angle, the vertical height of the target between the radar position of the lidar and the landing point position is determined;
[0180] Based on the target's vertical height and the vertical angle, the theoretical optical path length is obtained, and the theoretical optical path length corresponding to the laser beam is stored in the blind zone detection database.
[0181] In one embodiment, the processor, when executing a computer program, also performs the following steps:
[0182] Based on the rotation angle range to which the horizontal angle belongs, the sector area information corresponding to the rotation angle range is determined. The sector area information is used to characterize the position range of the sector scanning area of the lidar and the rotation angle range.
[0183] Based on the sector area information, determine the candidate vertical height corresponding to each sector area in the sector scan area;
[0184] The target vertical height is determined from the candidate vertical heights based on the vertical angle.
[0185] In one embodiment, the processor, when executing a computer program, also performs the following steps:
[0186] For each candidate vertical height, the horizontal distance between the radar position and the landing point position is obtained based on the vertical angle and the candidate vertical height;
[0187] If the horizontal distance is within the horizontal distance range between the target sector region corresponding to the candidate vertical height and the radar position, then the candidate vertical height is taken as the target vertical height.
[0188] In one embodiment, the processor, when executing a computer program, also performs the following steps:
[0189] Based on the horizontal distance and the vertical angle, the landing point position of the theoretical landing point corresponding to the theoretical optical path length of the laser beam is obtained;
[0190] The location of the impact point, corresponding to the laser beam, is stored in the blind zone detection database.
[0191] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:
[0192] Acquire radar point cloud data scanned by lidar, and determine the actual optical path length corresponding to the laser beam of lidar based on the radar point cloud data;
[0193] The theoretical optical path length corresponding to the laser beam is obtained from the preset blind zone detection database, and it is detected whether the actual optical path length is less than the theoretical optical path length. The theoretical optical path length is the optical path length of the laser beam in the optical path when there are no obstacles in the optical path of the laser beam.
[0194] If the actual optical path length is less than the theoretical optical path length, the blind zone of the lidar is determined according to the blind zone detection database.
[0195] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:
[0196] Obtain the landing point position of the theoretical landing point corresponding to the theoretical optical path length of the laser beam from the blind zone detection database;
[0197] The blind zone area is determined based on the location of the landing point.
[0198] In one embodiment, the number of laser beams is multiple, and the computer program, when executed by a processor, further performs the following steps:
[0199] The target region is obtained by performing envelope fitting on the landing point position corresponding to each laser beam, and the target region is used as the blind zone region.
[0200] In one embodiment, the number of laser beams is one, and the computer program, when executed by a processor, further performs the following steps:
[0201] The area within a preset distance range around the landing point is defined as the blind zone.
[0202] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:
[0203] Determine the horizontal and vertical angles corresponding to the laser beam, wherein the horizontal angle is used to characterize the rotation angle of the laser beam along the horizontal direction, and the vertical angle is used to characterize the angle between the laser beam and the horizontal direction;
[0204] Based on the horizontal angle and the vertical angle, the vertical height of the target between the radar position of the lidar and the landing point position is determined;
[0205] Based on the target's vertical height and the vertical angle, the theoretical optical path length is obtained, and the theoretical optical path length corresponding to the laser beam is stored in the blind zone detection database.
[0206] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:
[0207] Based on the rotation angle range to which the horizontal angle belongs, the sector area information corresponding to the rotation angle range is determined. The sector area information is used to characterize the position range of the sector scanning area of the lidar and the rotation angle range.
[0208] Based on the sector area information, determine the candidate vertical height corresponding to each sector area in the sector scan area;
[0209] The target vertical height is determined from the candidate vertical heights based on the vertical angle.
[0210] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:
[0211] For each candidate vertical height, the horizontal distance between the radar position and the landing point position is obtained based on the vertical angle and the candidate vertical height;
[0212] If the horizontal distance is within the horizontal distance range between the target sector region corresponding to the candidate vertical height and the radar position, then the candidate vertical height is taken as the target vertical height.
[0213] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:
[0214] Based on the horizontal distance and the vertical angle, the landing point position of the theoretical landing point corresponding to the theoretical optical path length of the laser beam is obtained;
[0215] The location of the impact point, corresponding to the laser beam, is stored in the blind zone detection database.
[0216] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical storage, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.
[0217] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0218] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.
Claims
1. A blind zone detection method, characterized in that, The method includes: Acquire radar point cloud data scanned by lidar, and determine the actual optical path length corresponding to the laser beam of lidar based on the radar point cloud data; The theoretical optical path length corresponding to the laser beam is obtained from the preset blind zone detection database, and it is detected whether the actual optical path length is less than the theoretical optical path length. The theoretical optical path length is the optical path length of the laser beam in the optical path when there are no obstacles in the optical path of the laser beam. If the actual optical path length is less than the theoretical optical path length, then the blind zone region of the lidar is determined according to the blind zone detection database; The method further includes: Determine the horizontal and vertical angles corresponding to the laser beam, wherein the horizontal angle is used to characterize the rotation angle of the laser beam along the horizontal direction, and the vertical angle is used to characterize the angle between the laser beam and the horizontal direction; Based on the rotation angle range to which the horizontal angle belongs, the sector area information corresponding to the rotation angle range is determined. The sector area information is used to characterize the position range of the sector scanning area of the lidar and the rotation angle range. Based on the sector area information, determine the candidate vertical height corresponding to each sector area in the sector scan area; For each candidate vertical height, the horizontal distance between the radar position and the landing point of the lidar is obtained based on the vertical angle and the candidate vertical height; If the horizontal distance is within the horizontal distance range between the target sector region corresponding to the candidate vertical height and the radar position, then the candidate vertical height is taken as the target vertical height; Based on the target's vertical height and the vertical angle, the theoretical optical path length is obtained, and the theoretical optical path length corresponding to the laser beam is stored in the blind zone detection database.
2. The method according to claim 1, characterized in that, Determining the blind zone region of the lidar based on the blind zone detection database includes: Obtain the landing point position of the theoretical landing point corresponding to the theoretical optical path length of the laser beam from the blind zone detection database; The blind zone area is determined based on the location of the landing point.
3. The method according to claim 2, characterized in that, The number of laser beams is multiple, and determining the blind zone region based on the landing point position includes: The target region is obtained by performing envelope fitting on the landing point position corresponding to each laser beam, and the target region is used as the blind zone region.
4. The method according to claim 2, characterized in that, The number of laser beams is one, and determining the blind zone region based on the landing point position includes: The area within a preset distance range around the landing point is defined as the blind zone.
5. The method according to claim 1, characterized in that, The method further includes: Based on the horizontal distance and the vertical angle, the landing point position of the theoretical landing point corresponding to the theoretical optical path length of the laser beam is obtained; The location of the impact point, corresponding to the laser beam, is stored in the blind zone detection database.
6. A blind spot detection device, characterized in that, The device includes: The first acquisition module is used to acquire radar point cloud data scanned by the lidar, and determine the actual optical path length corresponding to the laser beam of the lidar based on the radar point cloud data. The detection module is used to obtain the theoretical optical path length corresponding to the laser beam from a preset blind zone detection database, and to detect whether the actual optical path length is less than the theoretical optical path length, wherein the theoretical optical path length is the optical path length of the laser beam in the optical path when there are no obstacles in the optical path of the laser beam; The first determining module is used to determine the blind zone region of the lidar based on the blind zone detection database if the actual optical path length is less than the theoretical optical path length. The device further includes: The second determining module is used to determine the horizontal angle and vertical angle corresponding to the laser beam, wherein the horizontal angle is used to characterize the rotation angle of the laser beam along the horizontal direction, and the vertical angle is used to characterize the angle between the laser beam and the horizontal direction. The second determining unit is used to determine the sector area information corresponding to the rotation angle interval according to the rotation angle interval to which the horizontal angle belongs. The sector area information is used to characterize the position range of the sector scanning area of the lidar and the rotation angle interval. The third determining unit is used to determine the candidate vertical height corresponding to each sector in the sector scanning area based on the sector area information. The fourth determining unit is used to obtain, for each candidate vertical height, the horizontal distance between the radar position and the landing point position of the lidar based on the vertical angle and the candidate vertical height; if the horizontal distance is within the range of the horizontal distance between the target sector area corresponding to the candidate vertical height and the radar position, then the candidate vertical height is taken as the target vertical height; The third determining module is used to obtain the theoretical optical path length based on the target's vertical height and the vertical angle, and store the theoretical optical path length corresponding to the laser beam in the blind zone detection database.
7. The apparatus according to claim 6, characterized in that, The first determining module includes: The first acquisition unit is used to acquire the landing position of the theoretical landing point corresponding to the theoretical optical path length of the laser beam from the blind zone detection database. The first determining unit is used to determine the blind zone area based on the landing point location.
8. The apparatus according to claim 7, characterized in that, The number of laser beams is multiple. The first determining unit is specifically used to perform envelope fitting processing on the landing position corresponding to each laser beam to obtain the target area, and to use the target area as the blind area.
9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 5.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.