Trailer pose detection method and device, target trailer and storage medium

Abstract

The present application relates to the technical field of intelligent driving, in particular to a trailer pose detection method and device, a target tow truck and a storage medium. The method comprises: scanning a feature area of a target trailer by using a preset sensor installed on the target tow truck to obtain initial point cloud data corresponding to the feature area; filtering the initial point cloud data by using a laser reflection detection method and a laser edge detection method to obtain first target point cloud data and / or second target point cloud data; determining first position information of a first target center point corresponding to a left feature area and second position information of a second target center point corresponding to a right feature area according to the first target point cloud data and / or the second target point cloud data; and determining a pose of the target trailer according to the relationship between the first position information and the second position information. The accuracy of the determined pose of the target trailer is ensured, and the safety of driving is ensured, thereby avoiding accidents.

Description

Technical Field

[0001] This invention relates to the field of intelligent driving technology, specifically to a trailer position detection method, device, target trailer, and storage medium. Background Technology

[0002] Unmanned trailers are widely used in closed parks, long-haul logistics, ports, and other scenarios. Coordinated alignment and attitude detection between the unmanned trailer and the trailer are one of the core scenarios for achieving fully unmanned operation of unmanned trailers.

[0003] Autonomous trailer-trailer alignment requires the vehicle to travel to a specific area, such as a parking lot or loading / unloading yard. Parking detection of the trailer is performed; by detecting the trailer's position and attitude, the vehicle is controlled to park and move to the trailer's position for alignment. Simultaneously, during the trailer-trailer's movement, due to the vehicle's considerable length, the trailer's attitude (heading) needs to be monitored in real time. The perception, planning, and decision-making modules perform vehicle path planning and obstacle detection around the vehicle. The control module then performs smooth and safe vehicle control based on the planned path and the trailer's position and attitude.

[0004] Therefore, how to accurately and quickly detect the position and orientation of the trailer by an unmanned trailer has become an urgent problem to be solved. Summary of the Invention

[0005] In view of this, embodiments of the present invention provide a trailer position detection method, device, target trailer, and storage medium, aiming to solve the urgent problem of how to accurately and quickly detect the position of a trailer.

[0006] According to a first aspect, embodiments of the present invention provide a trailer position detection method, applied to a target trailer, the target trailer being used to tow the target trailer, comprising:

[0007] The feature area of ​​the target trailer is scanned by a preset sensor installed on the target trailer to obtain the initial point cloud data corresponding to the feature area. The feature area refers to the area on the left and right sides of the target trailer near the target trailer where a reflective strip is pasted.

[0008] The initial point cloud data is filtered using laser reflection detection and laser edge detection methods to obtain the first target point cloud data and / or the second target point cloud data.

[0009] Based on the first target point cloud data and / or the second target point cloud data, determine the first position information of the first target center point corresponding to the left feature region and the second position information of the second target center point corresponding to the right feature region;

[0010] The position of the target trailer is determined based on the relationship between the first position information and the second position information.

[0011] The trailer pose detection method provided in this invention utilizes a preset sensor installed on the target trailer to scan the feature areas of the target trailer, obtaining initial point cloud data corresponding to the feature areas, ensuring the accuracy of the obtained initial point cloud data. Then, a laser reflection detection method and a laser edge detection method are used to filter the initial point cloud data to obtain first target point cloud data and / or second target point cloud data, ensuring the accuracy of the obtained first target point cloud data and / or second target point cloud data. Based on the first target point cloud data and / or second target point cloud data, the first position information of the first target center point corresponding to the left feature area and the second position information of the second target center point corresponding to the right feature area are determined, ensuring the accuracy of the determined first target center point information and second target center point information. Then, based on the relationship between the first position information and the second position information, the pose of the target trailer is determined, ensuring the accuracy of the determined target trailer pose. Therefore, during the alignment process between the target trailer and the target trailer, alignment can be achieved quickly and accurately. Furthermore, when the target trailer is towing the target trailer, the target trailer can accurately and safely tow the target trailer according to its position, ensuring driving safety and avoiding accidents.

[0012] In conjunction with the first aspect, in the first embodiment of the first aspect, the initial point cloud data is filtered using a laser reflection detection method and a laser edge detection method to obtain first target point cloud data, including: acquiring a first preset range corresponding to the initial point cloud data; removing point cloud data outside the first preset range from the initial point cloud data to obtain first candidate point cloud data; acquiring a reflectivity threshold corresponding to the first candidate point cloud data; removing point cloud data with reflectivity less than the reflectivity threshold from the first candidate point cloud data to obtain second candidate point cloud data; performing cluster analysis on the second candidate point cloud data to obtain two clusters of third candidate point cloud data, and calculating the initial position information of the initial center point corresponding to each cluster of third candidate point cloud data; acquiring a second preset range corresponding to each initial center point; retaining point cloud data within the second preset range corresponding to each initial center point as the center to obtain fourth candidate point cloud data; and obtaining the first target point cloud data based on the fourth candidate point cloud data.

[0013] The trailer pose detection method provided in this embodiment of the invention obtains a first preset range corresponding to initial point cloud data. Then, point cloud data outside the first preset range is removed from the initial point cloud data to obtain first candidate point cloud data, ensuring the accuracy of the obtained first candidate point cloud data and avoiding the first candidate point cloud data range being too large. Next, a reflectance threshold corresponding to the first candidate point cloud data is obtained, and point cloud data with reflectance less than the reflectance threshold is removed from the first candidate point cloud data to obtain second candidate point cloud data, ensuring the accuracy of the obtained second candidate point cloud data and removing point cloud data outside the left and right feature regions. Cluster analysis is performed on the second candidate point cloud data to obtain two clusters of third candidate point cloud data, ensuring the accuracy of the obtained two clusters of third candidate point cloud data, so that the two clusters of third candidate point cloud data respectively represent the left and right feature regions. Then, the initial position information of the initial center point corresponding to each cluster of third candidate point cloud data is calculated, ensuring the accuracy of the calculated initial center point position information. Then, a second preset range corresponding to each initial center point is obtained. Using each initial center point as the center, point cloud data within the second preset range corresponding to each initial center point is retained to obtain fourth candidate point cloud data, ensuring the accuracy of the obtained fourth candidate point cloud data. Based on the fourth candidate point cloud data, the first target point cloud data is obtained, ensuring the accuracy of the obtained first target point cloud data.

[0014] In conjunction with the first embodiment of the first aspect, in the second embodiment of the first aspect, obtaining the first target point cloud data based on the fourth candidate point cloud data includes: performing edge detection on the fourth candidate point cloud data using normal estimation and grid occupancy methods to obtain the first edge point cloud data; identifying the first edge point cloud data and extracting the point cloud data of the left and right edges from the first edge point cloud data to obtain the first target point cloud data.

[0015] The trailer pose detection method provided in this embodiment of the invention uses normal estimation and mesh occupancy methods to perform edge detection on the fourth candidate point cloud data to obtain the first edge point cloud data, ensuring the accuracy of the obtained first edge point cloud data. Then, the first edge point cloud data is identified, and the point cloud data of the left and right edges in the first edge point cloud data are extracted to obtain the first target point cloud data, ensuring the accuracy of the obtained first target point cloud data, and also enabling the first target point cloud data to more accurately represent the point cloud data corresponding to the left and right feature regions.

[0016] In conjunction with the first aspect, in the third embodiment of the first aspect, the initial point cloud data is filtered using a laser reflection detection method and a laser edge detection method to obtain the second target point cloud data. The method further includes: acquiring a first preset range corresponding to the initial point cloud data; removing point cloud data outside the first preset range from the initial point cloud data to obtain first candidate point cloud data; performing edge detection on the first candidate point cloud data using normal estimation and grid occupancy methods to obtain second edge point cloud data; identifying the second edge point cloud data and extracting the contours of the X-axis, Y-axis, and Z-axis corresponding to the second edge point cloud data to obtain the contour range corresponding to the second edge point cloud data; acquiring a third preset range for the Z-axis corresponding to the second edge point cloud data; removing point cloud data whose Z-axis range is outside the third preset range from the second edge point cloud data to obtain third edge point cloud data; performing cluster analysis on the third edge point cloud data to obtain two clusters of fourth edge point cloud data; and identifying the two clusters of fourth edge point cloud data as the second target point cloud data.

[0017] The trailer pose detection method provided in this embodiment of the invention obtains a first preset range corresponding to initial point cloud data; point cloud data outside the first preset range is removed from the initial point cloud data to obtain first candidate point cloud data, ensuring the accuracy of the obtained first candidate point cloud data. Edge detection is performed on the first candidate point cloud data using normal estimation and mesh occupancy methods to obtain second edge point cloud data, ensuring the accuracy of the obtained second edge point cloud data. The second edge point cloud data is identified, and the contours of the X-axis, Y-axis, and Z-axis corresponding to the second edge point cloud data are extracted to obtain the contour range corresponding to the second edge point cloud data, ensuring the accuracy of the obtained contour range corresponding to the second edge point cloud data. Then, a third preset range of the Z-axis corresponding to the second edge point cloud data is obtained; point cloud data outside the third preset range of the Z-axis range are removed from the second edge point cloud data to obtain third edge point cloud data, ensuring the accuracy of the obtained third edge point cloud data. Cluster analysis is performed on the third edge point cloud data to obtain two clusters of fourth edge point cloud data, ensuring the accuracy of the obtained two clusters of fourth edge point cloud data. By identifying the two clusters of fourth-edge point cloud data as the second target point cloud data, the accuracy of the obtained second target point cloud data is ensured. This also allows the second target point cloud data to more accurately represent the point cloud data corresponding to the left and right feature regions.

[0018] In conjunction with the first aspect, in the fourth embodiment of the first aspect, determining the first position information of the first target center point corresponding to the left feature region and the second position information of the second target center point corresponding to the right feature region based on the first target point cloud data and the second target point cloud data includes: extracting the left first backup position information of the left first backup center point corresponding to the left feature region and the right first backup position information of the right first backup center point corresponding to the right feature region from the first target point cloud data; extracting the left second backup position information of the left second backup center point corresponding to the left feature region and the right second backup center point corresponding to the right feature region from the second target point cloud data; obtaining the first weight information corresponding to the left first backup position information and the right first backup position information, and the second weight information corresponding to the left second backup position information and the right second backup position information; and performing a weighted calculation on the left first backup position information, the right first backup position information, the left second backup position information, and the right second backup position information based on the first weight information and the second weight information to obtain the first position information of the first target center point and the second position information of the second target center point.

[0019] The trailer pose detection method provided in this embodiment of the invention extracts the left first backup position information of the left first backup center point corresponding to the left feature region and the right first backup position information of the right first backup center point corresponding to the right feature region from the first target point cloud data, ensuring the accuracy of the extracted left first backup position information and right first backup position information. Then, it extracts the left second backup position information of the left second backup center point corresponding to the left feature region and the right second backup center point corresponding to the right feature region from the second target point cloud data, ensuring the accuracy of the extracted left second backup position information and right second backup position information. It obtains first weight information corresponding to the left first backup position information and the right first backup position information, and second weight information corresponding to the left second backup position information and the right second backup position information; based on the first weight information and the second weight information, it performs a weighted calculation on the left first backup position information, the right first backup position information, the left second backup position information, and the right second backup position information to obtain the first position information of the first target center point and the second position information of the second target center point, ensuring the accuracy of the obtained first position information of the first target center point and the second position information of the second target center point.

[0020] In conjunction with the first aspect, in the fifth embodiment of the first aspect, determining the pose of the target trailer based on the relationship between the first position information and the second position information includes: establishing a target coordinate system with a preset sensor as the origin, the X-axis being parallel to the ground and pointing forward of the target trailer, and the Y-axis being perpendicular to the X-axis and pointing to the left; obtaining the first position coordinates of the first target center point in the target coordinate system, and the second position coordinates of the second target center point in the target coordinate system; calculating the backup heading angle of the target trailer in the target coordinate system based on the relationship between the first position coordinates, the second position coordinates, and the origin coordinates; obtaining the distance between the rear axle center point of the target trailer and the preset sensor; determining the backup position information of the target trailer in the target coordinate system based on the relationship between the distance between the rear axle center point of the target trailer and the preset sensor and the backup heading angle; and transforming the backup heading angle and the backup position information according to the transformation between the target coordinate system and the geodetic coordinate system to obtain the target heading angle and target position information of the target trailer in the geodetic coordinate system.

[0021] The trailer pose detection method provided in this invention establishes a target coordinate system with a preset sensor as the origin, an X-axis parallel to the ground pointing forward of the target trailer, and a Y-axis perpendicular to the X-axis pointing to the left, ensuring the accuracy of the established target coordinate system. The method acquires the first position coordinates of the first target center point and the second position coordinates of the second target center point in the target coordinate system. Based on the relationship between the first position coordinates, the second position coordinates, and the origin coordinates, the method calculates the backup heading angle of the target trailer in the target coordinate system, ensuring the accuracy of the calculated backup heading angle. Then, the method acquires the distance between the rear axle center point of the target trailer and the preset sensor. Based on the relationship between the distance between the rear axle center point of the target trailer and the preset sensor and the backup heading angle, the method determines the backup position information of the target trailer in the target coordinate system, ensuring the accuracy of the determined backup position information. Then, based on the transformation between the target coordinate system and the geodetic coordinate system, the backup heading angle and backup position information are transformed to obtain the target trailer's target heading angle and target position information in the geodetic coordinate system. This ensures the accuracy of the obtained target trailer's target heading angle and target position information, thereby ensuring the accuracy of the determined target trailer's attitude in the geodetic coordinate system. Therefore, during the alignment process between the target trailer and the target trailer, alignment can be achieved quickly and accurately. Furthermore, when the target trailer is towing the target trailer, it can accurately and safely tow the target trailer based on the target trailer's attitude, ensuring driving safety and preventing accidents.

[0022] In conjunction with the fifth embodiment of the first aspect, in the sixth embodiment of the first aspect, the backup heading angle of the target trailer under the target coordinates is calculated based on the relationship between the first position coordinates, the second position coordinates, and the origin coordinates. This includes: determining the first angle between the first line connecting the first position coordinates and the origin coordinates and the Y-axis based on the relationship between the first position coordinates and the origin coordinates; determining the third position coordinates corresponding to the center point between the first position coordinates and the second position coordinates based on the relationship between the first position coordinates and the second position coordinates; determining the second line connecting the origin coordinates and the third position coordinates, and determining the second angle between the first line connecting the second line; and obtaining the backup heading angle by subtracting the second angle from the first angle.

[0023] The trailer pose detection method provided in this invention determines a first angle between the first line connecting the first position coordinates and the origin coordinates and the Y-axis based on the relationship between the first position coordinates and the origin coordinates, ensuring the accuracy of the determined first angle. Based on the relationship between the first and second position coordinates, a third position coordinate corresponding to the center point between the first and second position coordinates is determined, ensuring the accuracy of the determined third position coordinate corresponding to the center point between the first and second position coordinates. A second line connecting the origin coordinates and the third position coordinates is determined, and a second angle between the first and second lines is determined, ensuring the accuracy of the determined second angle. Subtracting the second angle from the first angle yields a backup heading angle, ensuring the accuracy of the obtained backup heading angle, thereby ensuring the accuracy of the determined target trailer pose.

[0024] According to a second aspect, embodiments of the present invention also provide a trailer position detection device, applied to a target trailer, the target trailer being used to tow the target trailer, comprising:

[0025] The acquisition module is used to scan the feature area of ​​the target trailer using a preset sensor installed on the target trailer to obtain the initial point cloud data corresponding to the feature area. The feature area refers to the area on the left and right sides of the target trailer near the target trailer where a reflective strip is pasted on each side.

[0026] The filtering module is used to filter the initial point cloud data using laser reflection detection method and laser edge detection method to obtain the first target point cloud data and / or the second target point cloud data.

[0027] The first determining module is used to determine, based on the first target point cloud data and / or the second target point cloud data, the first position information of the first target center point corresponding to the left feature region and the second position information of the second target center point corresponding to the right feature region;

[0028] The second determining module is used to determine the position and orientation of the target trailer based on the relationship between the first position information and the second position information.

[0029] The trailer pose detection device provided in this embodiment of the invention uses a preset sensor installed on the target trailer to scan the feature areas of the target trailer, obtaining initial point cloud data corresponding to the feature areas, ensuring the accuracy of the obtained initial point cloud data. Then, the initial point cloud data is filtered using a laser reflection detection method and a laser edge detection method to obtain first target point cloud data and / or second target point cloud data, ensuring the accuracy of the obtained first target point cloud data and / or second target point cloud data. Based on the first target point cloud data and / or second target point cloud data, the first position information of the first target center point corresponding to the left feature area and the second position information of the second target center point corresponding to the right feature area are determined, ensuring the accuracy of the determined first target center point information and second target center point information. Then, based on the relationship between the first position information and the second position information, the pose of the target trailer is determined, ensuring the accuracy of the determined target trailer pose. Therefore, during the alignment process between the target trailer and the target trailer, alignment between the target trailer and the target trailer can be achieved quickly and accurately. Furthermore, when the target trailer is towing the target trailer, the target trailer can accurately and safely tow the target trailer according to its position, ensuring driving safety and avoiding accidents.

[0030] According to a third aspect, embodiments of the present invention provide a target trailer, including an electronic device and a trailer body. The electronic device includes a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to perform the trailer pose detection method of the first aspect or any embodiment of the first aspect.

[0031] According to a fourth aspect, embodiments of the present invention provide a computer-readable storage medium storing computer instructions for causing a computer to perform the trailer pose detection method of the first aspect or any embodiment of the first aspect. Attached Figure Description

[0032] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0033] Figure 1This is a flowchart of the trailer position detection method provided in the embodiments of the present invention;

[0034] Figure 2 This is a schematic diagram of the feature area of ​​a target trailer provided by another embodiment of the present invention;

[0035] Figure 3 This is a schematic diagram of using the electronic device provided in the embodiments of the present invention to scan the feature area of ​​the target trailer with a lidar sensor and align with the target trailer.

[0036] Figure 4 This is a flowchart of a trailer position detection method provided by another embodiment of the present invention;

[0037] Figure 5 This is a flowchart of a trailer position detection method provided by another embodiment of the present invention;

[0038] Figure 6 This is a flowchart of a trailer position detection method provided by another embodiment of the present invention;

[0039] Figure 7 This is a schematic diagram illustrating the application of the first position information of the first target center point and the second position information of the second target center point provided in another embodiment of the present invention;

[0040] Figure 8 This is a schematic diagram illustrating the calculation of the spare heading angle of the target trailer using another embodiment of the present invention;

[0041] Figure 9 This is a schematic diagram illustrating the calculation of the backup heading angle of the target trailer when the included angle between the target trailer and the target trailer is large, provided by another embodiment of the present invention.

[0042] Figure 10 This is a schematic diagram of the initial point cloud data collected when the angle between the target trailer and the target tractor is large, as provided in another embodiment of the present invention.

[0043] Figure 11 This is a functional block diagram of the trailer position detection device provided in the embodiments of the present invention;

[0044] Figure 12 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of the present invention. Detailed Implementation

[0045] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0046] It should be noted that the trailer pose detection method provided in this application embodiment can be executed by a trailer pose detection device. This device can be implemented as part or all of the electronic equipment corresponding to the target trailer through software, hardware, or a combination of both. The electronic equipment can be a processor inside the target trailer. Alternatively, it can be a server or terminal independent of the target trailer. In this application embodiment, the server can be a single server or a server cluster composed of multiple servers. The terminal in this application embodiment can be a smartphone, personal computer, tablet computer, wearable device, or other intelligent hardware device such as a smart robot. The following method embodiments will use an electronic device as an example for explanation.

[0047] In one embodiment of this application, such as Figure 1 As shown, a trailer position detection method is provided. Taking the application of this method to the electronic equipment corresponding to the target trailer as an example, the method includes the following steps:

[0048] S11. Use a preset sensor installed on the target trailer to scan the feature area of ​​the target trailer and obtain the initial point cloud data corresponding to the feature area.

[0049] The "featured area" refers to the area on the side of the target trailer closest to the target tractor where two reflective strips are affixed. For example, such as... Figure 2 The diagram shown is a schematic representation of the characteristic area of ​​the target trailer.

[0050] Specifically, such as Figure 3 As shown, the electronic device can use a lidar sensor installed behind the target trailer to scan the feature area of ​​the target trailer, thereby obtaining the initial point cloud data corresponding to the feature area of ​​the target trailer.

[0051] S12. Filter the initial point cloud data using laser reflection detection and laser edge detection methods to obtain the first target point cloud data and / or the second target point cloud data.

[0052] Specifically, after acquiring the initial point cloud data corresponding to the feature area of ​​the target trailer, the electronic device can use laser reflection detection method and laser edge detection method to perform at least two filtering processes on the initial point cloud data to obtain the first target point cloud data and / or the second target point cloud data.

[0053] This step will be explained in detail below.

[0054] S13. Based on the first target point cloud data and / or the second target point cloud data, determine the first position information of the first target center point corresponding to the left feature region and the second position information of the second target center point corresponding to the right feature region.

[0055] In one alternative implementation, the electronic device can identify the first target point cloud data and extract the first position information of the first target center point corresponding to the left feature region and the second position information of the second target center point corresponding to the right feature region from the first target point cloud data.

[0056] In another alternative implementation, the electronic device can identify the second target point cloud data and extract the first position information of the first target center point corresponding to the left feature region and the second position information of the second target center point corresponding to the right feature region from the second target point cloud data.

[0057] In another alternative implementation, the electronic device may further perform fusion processing on the first target point cloud data and the second target point cloud data to determine the first position information of the first target center point and the second position information of the second target center point.

[0058] This step will be explained in detail below.

[0059] S14. Determine the position of the target trailer based on the relationship between the first position information and the second position information.

[0060] Specifically, after obtaining the first position information of the first target center point corresponding to the left feature region and the second position information of the second target center point corresponding to the right feature region, the electronic device can determine the pose of the target trailer based on the relationship between the first position information and the second position information.

[0061] This step will be explained in detail below.

[0062] The trailer pose detection method provided in this invention utilizes a preset sensor installed on the target trailer to scan the feature areas of the target trailer, obtaining initial point cloud data corresponding to the feature areas, ensuring the accuracy of the obtained initial point cloud data. Then, a laser reflection detection method and a laser edge detection method are used to filter the initial point cloud data to obtain first target point cloud data and / or second target point cloud data, ensuring the accuracy of the obtained first target point cloud data and / or second target point cloud data. Based on the first target point cloud data and / or second target point cloud data, the first position information of the first target center point corresponding to the left feature area and the second position information of the second target center point corresponding to the right feature area are determined, ensuring the accuracy of the determined first target center point information and second target center point information. Then, based on the relationship between the first position information and the second position information, the pose of the target trailer is determined, ensuring the accuracy of the determined target trailer pose. Therefore, during the alignment process between the target trailer and the target trailer, alignment can be achieved quickly and accurately. Furthermore, when the target trailer is towing the target trailer, the target trailer can accurately and safely tow the target trailer according to its position, ensuring driving safety and avoiding accidents.

[0063] In one embodiment of this application, such as Figure 4 As shown, a trailer position detection method is provided. Taking the application of this method to electronic equipment as an example, the method includes the following steps:

[0064] S21. Use a preset sensor installed on the target trailer to scan the feature area of ​​the target trailer and obtain the initial point cloud data corresponding to the feature area.

[0065] The characteristic area refers to the area on the left and right sides of the target trailer near the target trailer where two reflective strips are affixed.

[0066] For details on this step, please refer to [link / reference]. Figure 1 The details of S11 will not be elaborated here.

[0067] S22. Filter the initial point cloud data using laser reflection detection and laser edge detection methods to obtain the first target point cloud data and / or the second target point cloud data.

[0068] In an optional embodiment of this application, step S22, "filtering the initial point cloud data using a laser reflection detection method and a laser edge detection method to obtain the first target point cloud data," may include the following steps:

[0069] S221. Obtain the first preset range corresponding to the initial point cloud data.

[0070] Specifically, the electronic device can receive a first preset range corresponding to the initial point cloud data input by the user, or a first preset range corresponding to the initial point cloud data sent by other devices. The electronic device can also acquire images of the feature regions of the target trailer, recognize the acquired feature region images, and determine the size range of the feature regions based on the recognition results. Then, based on the size range of the feature regions, the first preset range corresponding to the initial point cloud data is determined.

[0071] This application does not specifically limit the method by which the electronic device acquires the first preset range corresponding to the initial point cloud data.

[0072] S222. Remove point cloud data outside the first preset range from the initial point cloud data to obtain the first candidate point cloud data.

[0073] Specifically, the electronic device can identify each point cloud data in the initial point cloud data and determine the location information of each point cloud data. Based on the location information of each point cloud data, the electronic device can remove point cloud data outside a first preset range from the initial point cloud data to obtain the first candidate point cloud data.

[0074] For example, the first preset range can be (0≤x) i ≤40), (-30≤y i ≤30), (-0.5≤z i ≤2), the electronic device can calculate the first candidate point cloud data using the following formula:

[0075]

[0076] S223. Obtain the reflectance threshold corresponding to the first candidate point cloud data.

[0077] Specifically, the electronic device can receive the reflectance threshold corresponding to the first candidate point cloud data input by the user, and can also receive the reflectance threshold corresponding to the first candidate point cloud data sent by other devices. The electronic device can also identify the reflectance of each point cloud data in the first candidate point cloud data, determine the reflectance of each point cloud data in the first candidate point cloud data, and determine the reflectance threshold corresponding to the first candidate point cloud data based on the reflectance of each point cloud data in the first candidate point cloud data.

[0078] This application does not specifically limit the method by which the electronic device obtains the reflectivity threshold corresponding to the first candidate point cloud data.

[0079] The reflectivity threshold can be 200, 210, or 220. This application does not specifically limit the reflectivity threshold.

[0080] S224. Remove point cloud data with reflectivity less than the reflectivity threshold from the first candidate point cloud data to obtain the second candidate point cloud data.

[0081] Specifically, after obtaining the reflectivity threshold corresponding to the first candidate point cloud data, the electronic device can compare the reflectivity of each point cloud data in the first candidate point cloud data with the reflectivity threshold, and remove the point cloud data with reflectivity less than the reflectivity threshold from the first candidate point cloud data to obtain the second candidate point cloud data, thereby removing the first candidate point cloud data outside the feature regions on the left and right sides.

[0082] For example, when the reflectivity threshold is 200, I L This indicates that the electronic device performs the following filtering detection:

[0083] P(x i y i , z i I i )=P(x i y i , z i I i ), (200≤I i (2)

[0084] S225. Perform cluster analysis on the second candidate point cloud data to obtain two clusters of third candidate point cloud data, and calculate the initial position information of the initial center point corresponding to each cluster of third candidate point cloud data.

[0085] Specifically, after obtaining the second candidate point cloud data, the electronic device can perform cluster analysis on the second candidate point cloud data using a preset clustering method to obtain two clusters of third candidate point cloud data, so that the two clusters of third candidate point cloud data can respectively represent the left feature region and the right feature region.

[0086] The preset clustering method can be a partitioning clustering method, a density-based clustering method, a hierarchical clustering method, etc. The embodiments of this application do not specifically limit the preset clustering method.

[0087] After obtaining the two clusters of third candidate point cloud data, the electronic device can identify the position of each point cloud data in the two clusters of third candidate point cloud data respectively, and calculate the initial position information of the initial center point corresponding to each cluster of third candidate point cloud data based on the identified position of each point cloud data.

[0088] For example, P can be used respectively. L and P R This represents two clusters of third candidate point cloud data, where P LP represents the third candidate point cloud data from the left. R This represents the third candidate point cloud data on the right. (P) L and P R Each point cloud data is (x i y i , z i I i The initial position information of the initial center point corresponding to the third candidate point cloud data of each cluster is obtained by calculating the centroid coordinates of the third candidate point cloud data of each cluster, as follows:

[0089]

[0090] in, This represents the centroid x-value of the third candidate point cloud data from the left, i.e., the x-axis position information of the initial center point of the third candidate point cloud data from the left. This represents the centroid y-value of the third candidate point cloud data on the left, which is the y-axis position information of the initial center point of the third candidate point cloud data on the left. This represents the centroid x-value of the third candidate point cloud data on the right, i.e., the x-axis position information of the initial center point of the third candidate point cloud data on the right. This represents the centroid y-value of the third candidate point cloud data on the right, i.e., the y-axis position information of the initial center point of the third candidate point cloud data on the right. i，l The x-value and y-value represent the i-th point cloud data value of the third candidate point cloud data on the left. i，l Let x represent the y-value of the i-th point cloud data in the third candidate point cloud data on the left. i，r The x-value and y-value represent the i-th point cloud data value of the third candidate point cloud data on the right. i，r This represents the y-value of the i-th point cloud data in the third candidate point cloud data on the right.

[0091] S226. Obtain the second preset range corresponding to each initial center point.

[0092] Specifically, the electronic device can receive the second preset range corresponding to the initial position information of each initial center point input by the user, and can also receive the second preset range corresponding to the initial position information of each initial center point sent by other devices. The electronic device can also identify the position of each point cloud data in the two clusters of third candidate point cloud data, and determine the second preset range corresponding to the initial position information of each initial center point based on the position of each point cloud data in the two clusters of third candidate point cloud data.

[0093] This application embodiment does not specifically limit the method by which the electronic device obtains the second preset range corresponding to the initial position information of each initial center point.

[0094] S227. Using each initial center point as the center, retain the point cloud data within the second preset range corresponding to each initial center point to obtain the fourth candidate point cloud data.

[0095] Specifically, after obtaining the second preset range corresponding to the initial position information of each initial center point, the electronic device can take each initial center point as the center and retain the point cloud data within the second preset range corresponding to the initial center point to obtain the fourth candidate point cloud data.

[0096] For example, the second preset range can be (Δx, Δy), denoted by q(x). i y i , z i I i P(x) represents the extraction of the optimized fourth candidate point cloud data. i y i , z i I i () indicates the third candidate point cloud data:

[0097]

[0098] Similarly, q(x) i y i , z i I i The same method is used to process y-values.

[0099]

[0100] S228. Based on the fourth candidate point cloud data, obtain the first target point cloud data.

[0101] In one optional embodiment of this application, the electronic device may determine the fourth candidate point cloud data as the first target point cloud data.

[0102] In an optional embodiment of this application, step S228, "obtaining the first target point cloud data based on the fourth candidate point cloud data," may include the following steps:

[0103] (1) Use normal estimation and grid occupancy methods to perform edge detection on the fourth candidate point cloud data to obtain the first edge point cloud data.

[0104] Specifically, after acquiring the fourth candidate point cloud data, the electronic device can obtain the normal vector corresponding to each point cloud data in the fourth candidate point cloud data, and then determine the point cloud data in the same plane based on the normal vectors corresponding to each point cloud data. Then, the point cloud data in the same plane is divided into a grid, and the edge grid is obtained based on the number and position information of the point cloud data in each grid. Then, the first edge point cloud data is obtained based on the position information of the point cloud data in the edge grid.

[0105] (2) Identify the first edge point cloud data, extract the left and right edge point cloud data from the first edge point cloud data, and obtain the first target point cloud data.

[0106] Specifically, after obtaining the first edge point cloud data, the electronic device can identify the position of each point cloud data in the first edge point cloud data, and extract the point cloud data of the left and right edges in the first edge point cloud data based on the identified position of each point cloud data in the first edge point cloud data to obtain the first target point cloud data.

[0107] S23. Based on the first target point cloud data and / or the second target point cloud data, determine the first position information of the first target center point corresponding to the left feature region and the second position information of the second target center point corresponding to the right feature region.

[0108] For details on this step, please refer to [link / reference]. Figure 1 The details of S13 will not be elaborated here.

[0109] S24. Determine the position of the target trailer based on the relationship between the first position information and the second position information.

[0110] For details on this step, please refer to [link / reference]. Figure 1 The details of S14 will not be elaborated here.

[0111] The trailer pose detection method provided in this embodiment of the invention obtains a first preset range corresponding to initial point cloud data. Then, point cloud data outside the first preset range is removed from the initial point cloud data to obtain first candidate point cloud data, ensuring the accuracy of the obtained first candidate point cloud data and avoiding the first candidate point cloud data range being too large. Next, a reflectance threshold corresponding to the first candidate point cloud data is obtained, and point cloud data with reflectance less than the reflectance threshold is removed from the first candidate point cloud data to obtain second candidate point cloud data, ensuring the accuracy of the obtained second candidate point cloud data and removing point cloud data outside the left and right feature regions. Cluster analysis is performed on the second candidate point cloud data to obtain two clusters of third candidate point cloud data, ensuring the accuracy of the obtained two clusters of third candidate point cloud data, so that the two clusters of third candidate point cloud data respectively represent the left and right feature regions. Then, the initial position information of the initial center point corresponding to each cluster of third candidate point cloud data is calculated, ensuring the accuracy of the calculated initial center point position information. Then, a second preset range corresponding to each initial center point is obtained. Using each initial center point as the center, point cloud data within the second preset range corresponding to each initial center point is retained to obtain fourth candidate point cloud data, ensuring the accuracy of the obtained fourth candidate point cloud data. Next, edge detection is performed on the fourth candidate point cloud data using normal estimation and grid occupancy methods to obtain first edge point cloud data, ensuring the accuracy of the obtained first edge point cloud data. Then, the first edge point cloud data is identified, and the point cloud data of the left and right edges are extracted to obtain the first target point cloud data, ensuring the accuracy of the obtained first target point cloud data and enabling the first target point cloud data to more accurately represent the point cloud data corresponding to the left and right feature regions.

[0112] In one embodiment of this application, such as Figure 5 As shown, a trailer position detection method is provided. Taking the application of this method to the electronic equipment corresponding to the target trailer as an example, the method includes the following steps:

[0113] S31. Use a preset sensor installed on the target trailer to scan the feature area of ​​the target trailer and obtain the initial point cloud data corresponding to the feature area.

[0114] The characteristic area refers to the area on the left and right sides of the target trailer near the target trailer where two reflective strips are affixed.

[0115] For details on this step, please refer to [link / reference]. Figure 4 The details of S21 will not be elaborated here.

[0116] S32. Filter the initial point cloud data using laser reflection detection and laser edge detection methods to obtain the first target point cloud data and / or the second target point cloud data.

[0117] In an optional embodiment of this application, step S32, "filtering the initial point cloud data using a laser reflection detection method and a laser edge detection method to obtain first target point cloud data and / or second target point cloud data," may include the following steps:

[0118] S321. Obtain the first preset range corresponding to the initial point cloud data.

[0119] Specifically, the electronic device can receive a first preset range corresponding to the initial point cloud data input by the user, or a first preset range corresponding to the initial point cloud data sent by other devices. The electronic device can also acquire images of the feature regions of the target trailer, recognize the acquired feature region images, and determine the size range of the feature regions based on the recognition results. Then, based on the size range of the feature regions, the first preset range corresponding to the initial point cloud data is determined.

[0120] This application does not specifically limit the method by which the electronic device acquires the first preset range corresponding to the initial point cloud data.

[0121] S322. Remove point cloud data outside the first preset range from the initial point cloud data to obtain the first candidate point cloud data.

[0122] Specifically, the electronic device can identify each point cloud data in the initial point cloud data and determine the location information of each point cloud data. Based on the location information of each point cloud data, the electronic device can remove point cloud data outside a first preset range from the initial point cloud data to obtain the first candidate point cloud data.

[0123] For example, the first preset range can be (0≤x) i ≤40), (-30≤y i ≤30), (-0.5≤z i ≤2), the electronic device can calculate the first candidate point cloud data using the following formula:

[0124]

[0125] S323. Use normal estimation and grid occupancy methods to perform edge detection on the first candidate point cloud data to obtain the second edge point cloud data.

[0126] Specifically, after acquiring the first candidate point cloud data, the electronic device can obtain the normal vector corresponding to each point cloud data in the first candidate point cloud data, and then determine the point cloud data in the same plane based on the normal vectors corresponding to each point cloud data. Then, the point cloud data in the same plane is divided into grids, and edge grids are obtained based on the number and position information of point cloud data in each grid. Then, the second edge point cloud data is obtained based on the position information of the point cloud data in the edge grids.

[0127] S324. Identify the second edge point cloud data, extract the contours of the X-axis, Y-axis and Z-axis corresponding to the second edge point cloud data, and obtain the contour range corresponding to the second edge point cloud data.

[0128] Specifically, after acquiring the second edge point cloud data, the electronic device can identify the position of each point cloud data in the second edge point cloud data, and extract the contours of the X-axis, Y-axis and Z-axis corresponding to the second edge point cloud data according to the identification results, so as to obtain the contour range corresponding to the second edge point cloud data.

[0129] S325. Obtain the third preset range of the Z-axis corresponding to the second edge point cloud data.

[0130] Specifically, the electronic device can receive the third preset range of the Z-axis corresponding to the second edge point cloud data input by the user, or it can receive the third preset range of the Z-axis corresponding to the second edge point cloud data sent by other devices.

[0131] This application embodiment does not specifically limit the method by which the electronic device obtains the third preset range of the Z-axis corresponding to the second edge point cloud data.

[0132] S326. Remove point cloud data whose Z-axis range is outside the third preset range from the second edge point cloud data to obtain the third edge point cloud data.

[0133] Specifically, after obtaining the third preset range of the Z-axis corresponding to the second edge point cloud data, the electronic device can compare the actual range of the Z-axis corresponding to the second edge point cloud data with the third preset range of the Z-axis corresponding to the second edge point cloud data, and remove point cloud data whose Z-axis range is outside the third preset range from the second edge point cloud data according to the comparison result, so as to obtain the third edge point cloud data.

[0134] S327. Perform cluster analysis on the third edge point cloud data to obtain two clusters of fourth edge point cloud data.

[0135] Specifically, after acquiring the third edge point cloud data, the electronic device can use a preset clustering analysis method to perform clustering analysis on the third edge point cloud data to obtain two clusters of fourth edge point cloud data.

[0136] The preset clustering method can be a partitioning clustering method, a density-based clustering method, a hierarchical clustering method, etc. The embodiments of this application do not specifically limit the preset clustering method.

[0137] S328. The two clusters of fourth edge point cloud data are identified as the second target point cloud data.

[0138] Specifically, after obtaining two clusters of fourth edge point cloud data, the electronic device can identify the two clusters of fourth edge point cloud data as the second target point cloud data.

[0139] S33. Based on the first target point cloud data and / or the second target point cloud data, determine the first position information of the first target center point corresponding to the left feature region and the second position information of the second target center point corresponding to the right feature region.

[0140] For details on this step, please refer to [link / reference]. Figure 4 The details of S23 will not be elaborated here.

[0141] S34. Determine the position of the target trailer based on the relationship between the first position information and the second position information.

[0142] For details on this step, please refer to [link / reference]. Figure 4 The details of S24 will not be elaborated here.

[0143] The trailer pose detection method provided in this embodiment of the invention obtains a first preset range corresponding to initial point cloud data; point cloud data outside the first preset range is removed from the initial point cloud data to obtain first candidate point cloud data, ensuring the accuracy of the obtained first candidate point cloud data. Edge detection is performed on the first candidate point cloud data using normal estimation and mesh occupancy methods to obtain second edge point cloud data, ensuring the accuracy of the obtained second edge point cloud data. The second edge point cloud data is identified, and the contours of the X-axis, Y-axis, and Z-axis corresponding to the second edge point cloud data are extracted to obtain the contour range corresponding to the second edge point cloud data, ensuring the accuracy of the obtained contour range corresponding to the second edge point cloud data. Then, a third preset range of the Z-axis corresponding to the second edge point cloud data is obtained; point cloud data outside the third preset range of the Z-axis range are removed from the second edge point cloud data to obtain third edge point cloud data, ensuring the accuracy of the obtained third edge point cloud data. Cluster analysis is performed on the third edge point cloud data to obtain two clusters of fourth edge point cloud data, ensuring the accuracy of the obtained two clusters of fourth edge point cloud data. By identifying the two clusters of fourth-edge point cloud data as the second target point cloud data, the accuracy of the obtained second target point cloud data is ensured. This also allows the second target point cloud data to more accurately represent the point cloud data corresponding to the left and right feature regions.

[0144] In one embodiment of this application, such as Figure 6 As shown, a trailer position detection method is provided. Taking the application of this method to the electronic equipment corresponding to the target trailer as an example, the method includes the following steps:

[0145] S41. Use a preset sensor installed on the target trailer to scan the feature area of ​​the target trailer and obtain the initial point cloud data corresponding to the feature area.

[0146] The characteristic area refers to the area on the left and right sides of the target trailer near the target trailer where two reflective strips are affixed.

[0147] For details on this step, please refer to [link / reference]. Figure 5 The details of the S31 will not be elaborated here.

[0148] S42. Filter the initial point cloud data using laser reflection detection and laser edge detection methods to obtain the first target point cloud data and / or the second target point cloud data.

[0149] For details on this step, please refer to [link / reference]. Figure 4 The introductions to S22 and S32 will not be repeated here.

[0150] S43. Based on the first target point cloud data and / or the second target point cloud data, determine the first position information of the first target center point corresponding to the left feature region and the second position information of the second target center point corresponding to the right feature region.

[0151] In an optional embodiment of this application, the above-mentioned step S43, "determining the first position information of the first target center point corresponding to the left feature region and the second position information of the second target center point corresponding to the right feature region based on the first target point cloud data and / or the second target point cloud data," may include the following steps:

[0152] S431. Extract the left first backup position information of the left first backup center point corresponding to the left feature region and the right first backup position information of the right first backup center point corresponding to the right feature region from the first target point cloud data.

[0153] Specifically, after acquiring the first target point cloud data, the electronic device can identify the positions of the point cloud data corresponding to the left feature region and the point cloud data corresponding to the right feature region in the first target point cloud data. Then, based on the identification results, it determines to calculate the centroid coordinates of the point cloud data corresponding to the left feature region and the point cloud data corresponding to the right feature region, and obtains the left first backup position information of the left first backup center point corresponding to the left feature region and the right first backup position information of the right first backup center point corresponding to the right feature region.

[0154] S432. Extract the left second backup position information of the left second backup center point corresponding to the left feature region and the right second backup position information of the right second backup center point corresponding to the right feature region from the second target point cloud data.

[0155] Specifically, after acquiring the second target point cloud data, the electronic device can identify the positions of the point cloud data corresponding to the left feature region and the point cloud data corresponding to the right feature region in the second target point cloud data. Then, based on the identification results, it determines to calculate the centroid coordinates of the point cloud data corresponding to the left feature region and the point cloud data corresponding to the right feature region, thereby obtaining the left second backup position information of the left second backup center point corresponding to the left feature region and the right second backup position information of the right second backup center point corresponding to the right feature region.

[0156] For example, the first backup position information on the left can be represented as The first backup position information on the right can be represented as The information for the second backup position on the left can be represented as follows: The information for the second backup position on the right can be represented as follows:

[0157] S433. Obtain the first weight information corresponding to the first backup position information on the left and the first backup position information on the right, and the second weight information corresponding to the second backup position information on the left and the second backup position information on the right.

[0158] Specifically, the electronic device can receive first weight information corresponding to the first backup location information on the left and the first backup location information on the right, as well as second weight information corresponding to the second backup location information on the left and the second backup location information on the right, input by the user; it can also receive first weight information corresponding to the first backup location information on the left and the first backup location information on the right, as well as second weight information corresponding to the second backup location information on the left and the second backup location information on the right, sent by other devices; the electronic device can also determine the first weight information corresponding to the first backup location information on the left and the first backup location information on the right, as well as the second weight information corresponding to the second backup location information on the left and the second backup location information on the right, based on the accuracy of the first target point cloud data and the second target point cloud data.

[0159] This application does not specifically limit the method by which the electronic device obtains the first weight information corresponding to the first backup position information on the left and the first backup position information on the right, as well as the second weight information corresponding to the second backup position information on the left and the second backup position information on the right.

[0160] S434. Based on the first weight information and the second weight information, perform weighted calculations on the left first backup position information, the right first backup position information, the left second backup position information and the right second backup position information to obtain the first position information of the first target center point and the second position information of the second target center point.

[0161] Specifically, after obtaining the first weight information and the second weight information, the electronic device can perform a weighted calculation on the left first backup position information, the right first backup position information, the left second backup position information, and the right second backup position information based on the first weight information and the second weight information to obtain the first position information of the first target center point and the second position information of the second target center point. For example, as shown... Figure 7 As shown.

[0162] In one optional embodiment of this application, the electronic device can multiply the first weight information by the X-axis coordinate in the first backup position information on the left, then multiply the second weight information by the X-axis coordinate in the second backup position information on the left, and then add them together to obtain the X-axis coordinate in the first position information of the first target center point; multiply the first weight information by the Y-axis coordinate in the first backup position information on the left, then multiply the second weight information by the Y-axis coordinate in the second backup position information on the left, and then add them together to obtain the Y-axis coordinate in the first position information of the first target center point; multiply the first weight information by the X-axis coordinate in the first backup position information on the right, then multiply the second weight information by the X-axis coordinate in the second backup position information on the right, and then add them together to obtain the X-axis coordinate in the second position information of the second target center point; multiply the first weight information by the Y-axis coordinate in the first backup position information on the right, then multiply the second weight information by the Y-axis coordinate in the second backup position information on the right, and then add them together to obtain the Y-axis coordinate in the second position information of the second target center point.

[0163] In another optional embodiment of this application, the electronic device can calculate the first position information of the first target center point and the second position information of the second target center point using the following formula:

[0164]

[0165]

[0166] Among them, (X′ L ,Y′ L (X′) represents the first position information of the first center point. R ,Y′ R This represents the second location information of the center point of the second target. This is the first backup position information on the left. This is the first backup location information on the right. This is the information for the second backup position on the left. The information is the second backup position on the right, k1 is the first weight information, and k2 is the second weight information.

[0167] S44. Determine the position of the target trailer based on the relationship between the first position information and the second position information.

[0168] In an optional embodiment of this application, the above-mentioned step S34, "determining the pose of the target trailer based on the relationship between the first position information and the second position information," may include the following steps:

[0169] S441. Establish a target coordinate system with the preset sensor as the origin, the X-axis parallel to the ground and pointing in front of the target trailer as the X-axis, and the Y-axis perpendicular to the X-axis and pointing to the left as the Y-axis.

[0170] Specifically, the electronic device can establish a target coordinate system with a preset sensor as the origin, an X-axis parallel to the ground pointing in front of the target trailer as the X-axis, and a Y-axis perpendicular to the X-axis pointing to the left as the Y-axis.

[0171] S442. Obtain the first position coordinates of the first target center point in the target coordinate system, and the second position coordinates of the second target center point in the target coordinate system.

[0172] Specifically, after establishing the target coordinate system, the electronic device can obtain the first position coordinates of the first target center point in the target coordinate system, and the second position coordinates of the second target center point in the target coordinate system.

[0173] S443. Based on the relationship between the first position coordinates, the second position coordinates, and the origin coordinates, calculate the spare heading angle of the target trailer in the target coordinates.

[0174] In an optional embodiment of this application, the above-mentioned step S443, "calculating the spare heading angle of the target trailer in the target coordinates based on the relationship between the first position coordinates, the second position coordinates, and the origin coordinates," may further include the following steps:

[0175] (1) Based on the relationship between the first position coordinates and the origin coordinates, determine the first angle between the first line connecting the first position coordinates and the origin coordinates and the Y-axis.

[0176] Specifically, the electronic device can determine the first line connecting the first position coordinates and the origin coordinates based on the relationship between the first position coordinates and the origin coordinates, and then determine the first angle between the first line and the Y-axis.

[0177] (2) Based on the relationship between the first position coordinates and the second position coordinates, determine the third position coordinates corresponding to the center point between the first position coordinates and the second position coordinates;

[0178] Specifically, after acquiring the first position coordinates and the second position coordinates, the electronic device can determine the third position coordinates corresponding to the center point between the first position coordinates and the second position coordinates based on the relationship between the first position coordinates and the second position coordinates.

[0179] (3) Determine the second line connecting the origin coordinates and the third position coordinates, and determine the second included angle between the first line and the second line.

[0180] Specifically, the electronic device can determine the second line connecting the origin coordinates and the third position coordinates based on the relationship between the third position coordinates and the origin coordinates, and determine the second included angle between the first line and the second line.

[0181] (4) Subtract the second angle from the first included angle to obtain the spare heading angle.

[0182] Specifically, after determining the first included angle and the second included angle, the electronic device can subtract the second included angle from the first included angle to obtain the backup heading angle.

[0183] For example, such as Figure 8 As shown in the figure, the coordinates of point L are the first position coordinates (X′) of the center point of the first target. R ,Y′ R From the diagram, we can see that ∠COF = ∠ROH - ∠ROM. Let α represent ∠ROH, β represent the first angle between the first line connecting the first position coordinates and the origin coordinates and the Y-axis, denoted as ∠ROM, and θ represent the second angle between the first and second connecting lines, denoted as ∠COF, which is the alternative heading angle. (X′) L ,Y′ L (X′) represents the first position information of the first center point. R ,Y′ R ) represents the second location information of the center point of the second target.

[0184] Step 1: Solve for β

[0185] Point M is the center point between the first and second position coordinates, X M =(X′) L +X′ R ) / 2, Y M =(Y′) L +Y′ R ) / 2. Use D rm D represents the length of RM. or This represents the length of the OR, therefore sinβ = D rm / D or β is calculated.

[0186] Step 2: Solve for α

[0187] Use D rh D represents the length of RH. rh =||Y′ R ||,sinα=D rh / D or Solve for α.

[0188] Step 3: Solve for θ

[0189] θ = α - β.

[0190] S444: Obtain the distance between the center point of the rear axle of the target trailer and the preset sensor.

[0191] Specifically, the electronic device can acquire a first distance between the center point of the rear axle of the target trailer and the center point between the first target center point and the second target center point. Then, based on the point cloud data obtained by the preset sensor, a second distance between the preset sensor and the center point between the first target center point and the second target center point is determined. The first distance and the second distance are added together to obtain the distance between the center point of the rear axle of the target trailer and the preset sensor.

[0192] S445. Based on the relationship between the distance between the center point of the rear axle of the target trailer and the preset sensor and the backup heading angle, determine the backup position information of the target trailer in the target coordinate system.

[0193] Specifically, after obtaining the distance between the center point of the rear axle of the target trailer and the preset sensor, the electronic device can use the distance between the center point of the rear axle of the target trailer and the preset sensor multiplied by the cosine value of the backup heading angle to determine the position information of the target trailer on the Y-axis in the target coordinate system.

[0194] Then, the electronic equipment uses the distance between the center point of the rear axle of the target trailer and the preset sensor multiplied by the sine of the backup heading angle to determine the position information of the target trailer on the X-axis in the target coordinate system.

[0195] For example, such as Figure 8 As shown, the first distance between the center point of the rear axle of the target trailer and the center point M between the first target center point C and the second target center point is known, and is denoted as d. v Use D om Let OM represent the second distance between the preset sensor point O and the center point M between the first and second target center points, denoted as OM, and let represent the backup heading of the target trailer. Therefore, the backup position information of the target trailer in the target coordinate system is calculated as follows:

[0196] X w =(D om +d v )*cos(θ) (8)

[0197] Y w =(D om +d v sin(θ) (9)

[0198] Among them, D om The second distance is the distance between the preset sensor point O and the center point M between the center points of the first and second targets; d v θ is the first distance between the center point C of the rear axle of the target trailer and the center point M between the first target center point and the second target center point; θ is the spare heading angle.

[0199] S446. Based on the relationship between the target coordinate system and the geodetic coordinate system, the backup heading angle and backup position information are transformed to obtain the target trailer's target heading angle and target position information in the geodetic coordinate system.

[0200] Specifically, the electronic device can determine the vehicle coordinates of the target trailer based on the positional relationship between a preset sensor and the center point of the rear axle of the target trailer. Then, based on the heading angle of the target trailer, a second relationship between the vehicle coordinate system and the geodetic coordinate system is determined. Then, based on the first and second relationships, the relationship transformation between the target coordinate system and the geodetic coordinate system is determined, and the backup heading angle and backup position information are transformed to obtain the target heading angle and target position information of the target trailer in the geodetic coordinate system.

[0201] The trailer pose detection method provided in this embodiment of the invention extracts the left first backup position information of the left first backup center point corresponding to the left feature region and the right first backup position information of the right first backup center point corresponding to the right feature region from the first target point cloud data, ensuring the accuracy of the extracted left first backup position information and right first backup position information. Then, it extracts the left second backup position information of the left second backup center point corresponding to the left feature region and the right second backup center point corresponding to the right feature region from the second target point cloud data, ensuring the accuracy of the extracted left second backup position information and right second backup position information. It obtains first weight information corresponding to the left first backup position information and the right first backup position information, and second weight information corresponding to the left second backup position information and the right second backup position information; based on the first weight information and the second weight information, it performs a weighted calculation on the left first backup position information, the right first backup position information, the left second backup position information, and the right second backup position information to obtain the first position information of the first target center point and the second position information of the second target center point, ensuring the accuracy of the obtained first position information of the first target center point and the second position information of the second target center point.

[0202] Then, using the preset sensor as the origin, the X-axis (parallel to the ground pointing forward of the target trailer) and the Y-axis (perpendicular to the X-axis pointing to the left) are used to establish a target coordinate system, ensuring the accuracy of the established target coordinate system. Based on the relationship between the first position coordinates and the origin coordinates, the first angle between the first line connecting the first position coordinates and the origin coordinates and the Y-axis is determined, ensuring the accuracy of the determined first angle. Based on the relationship between the first and second position coordinates, the third position coordinates corresponding to the center point between the first and second position coordinates are determined, ensuring the accuracy of the determined third position coordinates corresponding to the center point between the first and second position coordinates. The second line connecting the origin coordinates and the third position coordinates is determined, and the second angle between the first and second lines is determined, ensuring the accuracy of the determined second angle. Subtracting the second angle from the first angle yields a backup heading angle, ensuring the accuracy of the obtained backup heading angle, thereby ensuring the accuracy of the determined target trailer's pose. Then, the distance between the center point of the rear axle of the target trailer and the preset sensor is obtained. Based on the relationship between this distance and the backup heading angle, the backup position information of the target trailer in the target coordinate system is determined, ensuring the accuracy of this information. Next, the backup heading angle and position information are transformed according to the relationship between the target coordinate system and the geodetic coordinate system to obtain the target heading angle and position information of the target trailer in the geodetic coordinate system. This ensures the accuracy of the obtained target heading angle and position information, thereby guaranteeing the accuracy of the determined pose of the target trailer in the geodetic coordinate system. Therefore, during the alignment process between the target trailer and the target trailer, alignment can be achieved quickly and accurately. Furthermore, when the target trailer is towing the target trailer, it can accurately and safely tow the target trailer based on its pose, ensuring driving safety and preventing accidents.

[0203] In one optional embodiment of this application, when a target trailer towing a target tractor makes a sharp turn at a large angle, there is a significant difference in the turning angle between the target trailer and the target tractor. The judgment condition is that the laser reflection method cannot detect the point cloud of two reflective band feature regions, but can only detect the point cloud of one of the feature regions. In this case, a first preset range corresponding to the initial point cloud data is obtained; point cloud data outside the first preset range is removed from the initial point cloud data to obtain first candidate point cloud data. Then, a reflectivity threshold corresponding to the first candidate point cloud data is obtained, and point cloud data with reflectivity less than the reflectivity threshold is removed from the first candidate point cloud data to obtain second candidate point cloud data. Cluster analysis is performed on the second candidate point cloud data to obtain two clusters of third candidate point cloud data, and the initial position information of the initial center point corresponding to each cluster of third candidate point cloud data is calculated. Then, a second preset range corresponding to each initial center point is obtained, and point cloud data within the second preset range corresponding to each initial center point are retained as the center to obtain fourth candidate point cloud data. Edge detection is performed on the fourth candidate point cloud data using normal estimation and mesh occupancy methods to obtain first edge point cloud data. The first edge point cloud data is then identified, and the left and right edge point cloud data are extracted to obtain the first target point cloud data. The normal vector estimate of the first target point cloud data relative to the plane is calculated, and two cross-sections are distinguished based on the normal vector direction threshold, as exemplified by... Figure 9 and Figure 10 As shown. Point cloud clustering and quantity statistics are performed on the two cross-sections. Based on the proportion of point clouds in the two cross-sections, the angle is estimated based on the trailer heading angle at the previous time step. N1 is used. size and N2 size θ represents the number of point clouds in the two cross-section clusters. k θ represents the heading angle of the trailer at the current moment. k-1 This represents the trailer's heading angle at the previous moment. The estimated method for calculating the trailer's heading angle in this case is as follows:

[0204]

[0205] This is a special case of low-speed turning at a large angle, where estimating the heading angle is more important than estimating the trailer position for vehicle control. In this situation, the trailer's pose cannot be calculated using methods S1-S9. Instead, the vehicle speed is used to perform displacement integration in both the forward and lateral directions based on the trailer angle increment. V M，k-1 This represents the trailer's speed at the previous moment. (Used as X) w，k-1 and Y w，k-1 This indicates the position of the trailer at the previous moment. Δθ k Let represent the trailer heading angle increment at time k. The approximate position estimate for this case is as follows:

[0206] X w，k =X w，k-1 +V M，k-1 *cos(Δθ k )*(t k -t k-1 (11)

[0207] Y w，k =Y w，k-1 +V M，k-1 *sin(Δθ k )*(t k -t k-1 (12)

[0208] Among them, t k and t k-1 Let k-1 and k represent the times.

[0209] It should be understood that, although Figure 1 as well as Figure 4-6 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 1 as well as Figure 4-6 At least some of the steps in the process may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but may be executed at different times. The execution order of these steps or stages is not necessarily sequential, but may be executed in turn or alternately with other steps or at least some of the steps or stages in other steps.

[0210] like Figure 11 As shown, this embodiment provides a trailer position detection device, including:

[0211] The acquisition module 51 is used to scan the feature area of ​​the target trailer using a preset sensor installed on the target trailer to obtain the initial point cloud data corresponding to the feature area. The feature area refers to the area on the target trailer with a reflective strip pasted on each of the left and right sides of the side closest to the target trailer.

[0212] The filtering module 52 is used to filter the initial point cloud data using the laser reflection detection method and the laser edge detection method to obtain the first target point cloud data and / or the second target point cloud data.

[0213] The first determining module 53 is used to determine the first position information of the first target center point corresponding to the left feature region and the second position information of the second target center point corresponding to the right feature region based on the first target point cloud data and / or the second target point cloud data.

[0214] The second determining module 54 is used to determine the position of the target trailer based on the relationship between the first position information and the second position information.

[0215] In one embodiment of this application, the filtering module 52 is specifically used to: obtain a first preset range corresponding to the initial point cloud data; remove point cloud data outside the first preset range from the initial point cloud data to obtain first candidate point cloud data; obtain a reflectance threshold corresponding to the first candidate point cloud data; remove point cloud data with reflectance less than the reflectance threshold from the first candidate point cloud data to obtain second candidate point cloud data; perform cluster analysis on the second candidate point cloud data to obtain two clusters of third candidate point cloud data, and calculate the initial position information of the initial center point corresponding to each cluster of third candidate point cloud data; obtain a second preset range corresponding to each initial center point; retain the point cloud data within the second preset range corresponding to each initial center point as the center to obtain fourth candidate point cloud data; and obtain the first target point cloud data based on the fourth candidate point cloud data.

[0216] In one embodiment of this application, the filtering module 52 is specifically used to perform edge detection on the fourth candidate point cloud data using normal estimation and grid occupancy methods to obtain the first edge point cloud data; to identify the first edge point cloud data and extract the point cloud data of the left and right edges in the first edge point cloud data to obtain the first target point cloud data.

[0217] In one embodiment of this application, the filtering module 52 is specifically used to: obtain a first preset range corresponding to the initial point cloud data; remove point cloud data outside the first preset range from the initial point cloud data to obtain a first candidate point cloud data; perform edge detection on the first candidate point cloud data using normal estimation and grid occupancy methods to obtain second edge point cloud data; identify the second edge point cloud data and extract the contours of the X-axis, Y-axis, and Z-axis corresponding to the second edge point cloud data to obtain the contour range corresponding to the second edge point cloud data; obtain a third preset range of the Z-axis corresponding to the second edge point cloud data; remove point cloud data whose Z-axis range is outside the third preset range from the second edge point cloud data to obtain third edge point cloud data; perform cluster analysis on the third edge point cloud data to obtain two clusters of fourth edge point cloud data; and determine the two clusters of fourth edge point cloud data as the second target point cloud data.

[0218] In one embodiment of this application, the first determining module 53 is specifically used to extract from the first target point cloud data the left first backup position information of the left first backup center point corresponding to the left feature region and the right first backup position information of the right first backup center point corresponding to the right feature region; extract from the second target point cloud data the left second backup position information of the left second backup center point corresponding to the left feature region and the right second backup position information of the right second backup center point corresponding to the right feature region; obtain the first weight information corresponding to the left first backup position information and the right first backup position information, and the second weight information corresponding to the left second backup position information and the right second backup position information; and perform weighted calculation on the left first backup position information, the right first backup position information, the left second backup position information and the right second backup position information according to the first weight information and the second weight information to obtain the first position information of the first target center point and the second position information of the second target center point.

[0219] In one embodiment of this application, the second determining module 54 is specifically used to establish a target coordinate system with a preset sensor as the origin, an X-axis parallel to the ground pointing forward of the target trailer as the X-axis, and a Y-axis perpendicular to the X-axis pointing to the left as the Y-axis; to obtain the first position coordinates of the first target center point in the target coordinate system and the second position coordinates of the second target center point in the target coordinate system; to calculate the spare heading angle of the target trailer in the target coordinate system based on the relationship between the first position coordinates, the second position coordinates, and the origin coordinates; to obtain the distance between the rear axle center point of the target trailer and the preset sensor; to determine the spare position information of the target trailer in the target coordinate system based on the relationship between the distance between the rear axle center point of the target trailer and the preset sensor and the spare heading angle; and to transform the spare heading angle and the spare position information according to the relationship between the target coordinate system and the geodetic coordinate system to obtain the target heading angle and target position information of the target trailer in the geodetic coordinate system.

[0220] In one embodiment of this application, the second determining module 54 is specifically used to determine, based on the relationship between the first position coordinates and the origin coordinates, a first angle between the first line connecting the first position coordinates and the origin coordinates and the Y-axis; based on the relationship between the first position coordinates and the second position coordinates, a third position coordinate corresponding to the center point between the first position coordinates and the second position coordinates; a second line connecting the origin coordinates and the third position coordinates, and a second angle between the first line connecting the first line and the second line connecting the second line; and subtracting the second angle from the first angle to obtain the backup heading angle.

[0221] For specific limitations and beneficial effects regarding the trailer position detection device, please refer to the limitations of the trailer position detection method above, which will not be repeated here. Each module in the aforementioned trailer position 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 the electronic device, or stored in the memory of the electronic device as software, so that the processor can call and execute the corresponding operations of each module.

[0222] This invention also provides a target trailer, which includes a trailer body and electronic equipment, wherein the electronic equipment has the above-described features. Figure 11 The trailer position detection device shown.

[0223] like Figure 12 As shown, Figure 12 This is a schematic diagram of the structure of an electronic device provided in an optional embodiment of the present invention, such as... Figure 12 As shown, the electronic device may include: at least one processor 61, such as a CPU (Central Processing Unit), at least one communication interface 63, memory 64, and at least one communication bus 62. The communication bus 62 is used to enable communication between these components. The communication interface 63 may include a display screen or a keyboard; optionally, the communication interface 63 may also include a standard wired interface or a wireless interface. The memory 64 may be high-speed RAM (Random Access Memory) or non-volatile memory, such as at least one disk storage device. Optionally, the memory 64 may also be at least one storage device located remotely from the aforementioned processor 61. The processor 61 may be combined with... Figure 1 as well as Figure 4-6 The described apparatus has an application program stored in memory 64, and the processor 61 calls the program code stored in memory 64 to perform any of the above method steps.

[0224] The communication bus 62 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The communication bus 62 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 12 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0225] The memory 64 may include volatile memory, such as random-access memory (RAM); the memory may also include non-volatile memory, such as flash memory, hard disk drive (HDD) or solid-state drive (SSD); the memory 64 may also include a combination of the above types of memory.

[0226] The processor 61 can be a central processing unit (CPU), a network processor (NP), or a combination of CPU and NP.

[0227] The processor 61 may further include a hardware chip. This hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0228] Optionally, memory 64 is also used to store program instructions. Processor 61 can invoke program instructions to implement the functions described in this application. Figure 1 as well as Figure 4-6 The trailer position detection method shown in the embodiment.

[0229] This invention also provides a non-transitory computer storage medium storing computer-executable instructions that can execute the trailer pose detection method in any of the above method embodiments. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk drive (HDD), or solid-state drive (SSD), etc.; the storage medium may also include combinations of the above types of memory.

[0230] This invention also provides a trailer, including an electronic device and a trailer body, wherein the electronic device is used to perform the functions described in this application. Figure 1 as well as Figure 4-6 The trailer position detection method shown in the embodiment.

[0231] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for detecting the position and orientation of a trailer, characterized in that, Applied to a target trailer, the target trailer being used to tow a target trailer, including: The feature area of ​​the target trailer is scanned by a preset sensor installed on the target trailer to obtain the initial point cloud data corresponding to the feature area. The feature area refers to the area on the target trailer with a reflective strip pasted on each of the left and right sides near the side of the target trailer. The initial point cloud data is filtered using laser reflection detection and laser edge detection methods to obtain first target point cloud data and / or second target point cloud data. Extract the left first backup position information of the left first backup center point corresponding to the left feature region and the right first backup center point corresponding to the right feature region from the first target point cloud data. Extract the left second backup position information of the left second backup center point corresponding to the left feature region and the right second backup center point corresponding to the right feature region from the second target point cloud data; Obtain first weight information corresponding to the first backup position information on the left and the first backup position information on the right, and second weight information corresponding to the second backup position information on the left and the second backup position information on the right; Based on the first weight information and the second weight information, the first backup position information on the left, the first backup position information on the right, the second backup position information on the left, and the second backup position information on the right are weighted and calculated to obtain the first position information of the first target center point corresponding to the feature region on the left and the second position information of the second target center point corresponding to the feature region on the right. The position of the target trailer is determined based on the relationship between the first position information and the second position information.

2. The method according to claim 1, characterized in that, The step of filtering the initial point cloud data using laser reflection detection and laser edge detection methods to obtain the first target point cloud data includes: Obtain the first preset range corresponding to the initial point cloud data; Point cloud data outside the first preset range is removed from the initial point cloud data to obtain the first candidate point cloud data; Obtain the reflectance threshold corresponding to the first candidate point cloud data; The second candidate point cloud data is obtained by removing point cloud data with reflectance less than the reflectance threshold from the first candidate point cloud data. Cluster analysis is performed on the second candidate point cloud data to obtain two clusters of third candidate point cloud data, and the initial position information of the initial center point corresponding to each cluster of the third candidate point cloud data is calculated. Obtain the second preset range corresponding to each of the initial center points; Using each of the initial center points as the center, retain the point cloud data within the second preset range corresponding to each initial center point to obtain the fourth candidate point cloud data; The first target point cloud data is obtained based on the fourth candidate point cloud data.

3. The method according to claim 2, characterized in that, The step of obtaining the first target point cloud data based on the fourth candidate point cloud data includes: Edge detection is performed on the fourth candidate point cloud data using normal estimation and grid occupancy methods to obtain the first edge point cloud data. The first edge point cloud data is identified, and the point cloud data of the left and right edges in the first edge point cloud data are extracted to obtain the first target point cloud data.

4. The method according to claim 1, characterized in that, The step of filtering the initial point cloud data using laser reflection detection and laser edge detection methods to obtain the second target point cloud data further includes: Obtain the first preset range corresponding to the initial point cloud data; Point cloud data outside the first preset range is removed from the initial point cloud data to obtain the first candidate point cloud data; Edge detection is performed on the first candidate point cloud data using normal estimation and grid occupancy methods to obtain the second edge point cloud data. The second edge point cloud data is identified, and the contours of the X-axis, Y-axis and Z-axis corresponding to the second edge point cloud data are extracted to obtain the contour range corresponding to the second edge point cloud data. Obtain the third preset range of the Z-axis corresponding to the second edge point cloud data; The third edge point cloud data is obtained by removing point cloud data whose Z-axis range is outside the third preset range from the second edge point cloud data; Cluster analysis was performed on the third edge point cloud data to obtain two clusters of fourth edge point cloud data; The two clusters of fourth edge point cloud data are identified as the second target point cloud data.

5. The method according to claim 1, characterized in that, Determining the pose of the target trailer based on the relationship between the first location information and the second location information includes: A target coordinate system is established with the preset sensor as the origin, the X-axis parallel to the ground and pointing in front of the target trailer as the X-axis, and the Y-axis perpendicular to the X-axis and pointing to the left as the Y-axis. Obtain the first position coordinates of the first target center point in the target coordinate system, and the second position coordinates of the second target center point in the target coordinate system; Based on the relationship between the first position coordinates, the second position coordinates, and the origin coordinates, calculate the spare heading angle of the target trailer at the target coordinates; Obtain the distance between the center point of the rear axle of the target trailer and the preset sensor; Based on the relationship between the distance between the rear axle center point of the target trailer and the preset sensor and the backup heading angle, the backup position information of the target trailer in the target coordinate system is determined; Based on the relationship between the target coordinate system and the geodetic coordinate system, the backup heading angle and the backup position information are transformed to obtain the target trailer's target heading angle and target position information in the geodetic coordinate system.

6. The method according to claim 5, characterized in that, The step of calculating the spare heading angle of the target trailer at the target coordinates based on the relationship between the first position coordinates, the second position coordinates, and the origin coordinates includes: Based on the relationship between the first position coordinates and the origin coordinates, determine the first angle between the first line connecting the first position coordinates and the origin coordinates and the Y-axis; Based on the relationship between the first position coordinates and the second position coordinates, determine the third position coordinates corresponding to the center point between the first position coordinates and the second position coordinates; Determine the second line connecting the origin coordinates and the third position coordinates, and determine the second included angle between the first line and the second line; The backup heading angle is obtained by subtracting the second angle from the first angle.

7. A trailer position and posture detection device, characterized in that, Applied to a target trailer, the target trailer being used to tow a target trailer, including: The acquisition module is used to scan the feature area of ​​the target trailer using a preset sensor installed on the target trailer to obtain the initial point cloud data corresponding to the feature area. The feature area refers to the area on the target trailer with a reflective strip pasted on each of the left and right sides near the side of the target trailer. The filtering module is used to filter the initial point cloud data using a laser reflection detection method and a laser edge detection method to obtain first target point cloud data and / or second target point cloud data. A first determining module is configured to determine, based on the first target point cloud data and / or the second target point cloud data, a first position information of a first target center point corresponding to a left-side feature region and a second position information of a second target center point corresponding to a right-side feature region. The method for determining the first and second position information includes: extracting left-side first backup position information of a left-side first backup center point corresponding to a left-side feature region and right-side first backup position information of a right-side first backup center point corresponding to a right-side feature region from the first target point cloud data; extracting left-side second backup position information of a left-side second backup center point corresponding to a left-side feature region and right-side second backup position information of a right-side second backup center point corresponding to a right-side feature region from the second target point cloud data; obtaining first weight information corresponding to the left-side first backup position information and the right-side first backup position information, and second weight information corresponding to the left-side second backup position information and the right-side second backup position information; and performing a weighted calculation on the left-side first backup position information, the right-side first backup position information, the left-side second backup position information, and the right-side second backup position information based on the first weight information and the second weight information to obtain the first position information of the first target center point corresponding to the left-side feature region and the second position information of the second target center point corresponding to the right-side feature region. The second determining module is used to determine the position of the target trailer based on the relationship between the first position information and the second position information.

8. A target trailer, characterized in that, The device includes an electronic device and a trailer body. The electronic device includes a memory and a processor. The memory stores computer instructions. The processor executes the computer instructions to perform the trailer position detection method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to perform the trailer position detection method according to any one of claims 1-6.

Images