Agricultural machine hangar positioning method and device based on point cloud registration

Abstract

The invention provides an agricultural machinery hangar positioning method and device based on point cloud registration, and relates to the field of indoor navigation positioning, and the method comprises the steps: carrying out the first-order annular key rough matching and second-order sector key fine matching of a hangar real-time point cloud frame obtained by an agricultural machinery laser radar which is installed in an inclined manner and a prior three-dimensional point cloud map through employing an improved Scan Context + + algorithm, obtaining a candidate key frame and a rotation angle of a hangar real-time point cloud frame and a candidate key frame point cloud, and generating an initial registration matrix of normal distribution transformation according to the rotation angle; and by taking the initial registration matrix as an initial value, continuously registering the collected hangar real-time positioning point cloud frame data with a prior three-dimensional point cloud map, outputting the pose of the agricultural machine, and re-initializing when the positioning is interrupted due to a dynamic scene. According to the invention, indoor positioning initialization and continuous positioning functions without external information assistance except for the laser radar can be realized.

Description

Technical Field

[0001] The present invention relates to the field of indoor navigation and positioning, and in particular to a method and device for positioning an agricultural machinery hangar based on point cloud registration. Background Art

[0002] Precision positioning technology is key to realizing the functions and tasks of intelligent unmanned operation systems. In recent years, with the development of LiDAR technology, laser point cloud registration has become an important method for unmanned system positioning. By comparing a set of points in three-dimensional space with a pre-established point cloud map, extracting the intrinsic structural features of the point cloud, and establishing a conversion relationship between the real-time point cloud frame and the point cloud map, it is possible to accurately estimate the position and posture of the unmanned system. This technology has the advantages of being unaffected by lighting conditions and being able to handle complex scenes. It has broad application prospects in the field of unmanned agricultural machinery hangar positioning. To address the problems of indoor GNSS satellite signal loss, dynamic changes in the hangar scene, and image blurring caused by mechanical vibration when agricultural machinery is positioned in the hangar, a method for agricultural machinery hangar positioning based on point cloud registration is studied. This is of great significance for improving the automation and intelligence level of unmanned agricultural machinery operations.

[0003] Point cloud positioning technology relies on sensor characteristics, scene environment, and carrier positioning requirements. It is necessary to comprehensively consider internal and external factors such as the agricultural machinery LiDAR scanning field of view, the hangar structural characteristics, and the motion characteristics of the agricultural machinery carrier to design a reasonable and effective agricultural machinery hangar positioning method. Furthermore, the hangar environment changes as operations progress, such as the movement of agricultural machinery and the relocation of stacked items. This means that the adaptability of point cloud positioning technology to environmental changes needs to be improved. Furthermore, how to effectively initialize hangar positioning without prior pose is also a key issue. Therefore, it is urgent to propose a method and device for agricultural machinery hangar positioning based on point cloud registration to address technical deficiencies in initial positioning, continuous positioning, and environmental adaptability within the hangar, thereby improving the reliability and robustness of agricultural machinery hangar positioning. Summary of the Invention

[0004] In order to solve the above technical problems, the present invention provides a method and device for positioning an agricultural machinery hangar based on point cloud registration, and provides an indoor positioning method for low-speed unmanned agricultural machinery under indoor satellite signal denial conditions, which can realize indoor positioning initialization and continuous positioning functions without external information assistance except lidar.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] A method for positioning an agricultural machinery hangar based on point cloud registration includes the following steps:

[0007] S1. Use the improved Scan Context++ algorithm to perform first-order ring key coarse matching and second-order fan key fine matching on the hangar real-time point cloud frame obtained by the tilted agricultural machinery lidar and the prior 3D point cloud map, obtain the candidate key frame and the rotation angle between the hangar real-time point cloud frame and the candidate key frame point cloud, and generate the initial registration matrix of the normal distribution transformation based on this;

[0008] S2. Using the initial registration matrix as the initial value, continuously register the collected hangar real-time positioning point cloud frame data with the prior three-dimensional point cloud map, output the agricultural machinery posture, and return to S1 for reinitialization when the dynamic scene causes positioning interruption.

[0009] The present invention also provides an agricultural machinery hangar positioning device based on point cloud registration, which is used to implement the above method and includes the following modules:

[0010] The initial registration module uses the improved Scan Context++ algorithm to perform first-order ring key coarse matching and second-order fan key fine matching on the hangar real-time point cloud frame acquired by the tilted agricultural machinery lidar and the prior 3D point cloud map. It obtains the candidate keyframes and the rotation angles between the hangar real-time point cloud frame and the candidate keyframe point cloud, and generates the initial registration matrix of the normal distribution transformation based on this.

[0011] The continuous registration module uses the initial registration matrix as the initial value to continuously register the collected hangar real-time positioning point cloud frame data with the prior three-dimensional point cloud map, outputs the agricultural machinery posture, and uses the initial registration module to reinitialize when the dynamic scene causes positioning interruption.

[0012] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and runnable on the processor. When the processor executes the program, the steps of the above-mentioned agricultural machinery hangar positioning method based on point cloud registration are implemented.

[0013] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the above-mentioned agricultural machinery hangar positioning method based on point cloud registration are implemented.

[0014] Beneficial effects:

[0015] The present invention combines the advantages of high precision and high reliability of second-order positioning, realizes the positioning initialization and continuous positioning functions of agricultural machinery in the hangar under satellite signal denial conditions, and can respond to dynamic changes in the environment in the hangar, with strong robustness and environmental adaptability. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a flow chart of a method for positioning an agricultural machinery hangar based on point cloud registration according to the present invention;

[0017] Figure 2 This is a schematic diagram of a hangar point cloud frame collected by agricultural machinery lidar;

[0018] Figure 3 Figure 1 is a visualization diagram of a frame of hangar point cloud scan context descriptor; (a) is the real-time hangar point cloud frame scan context obtained by the present invention, and (b) is the real-time hangar point cloud frame scan context obtained by the original method;

[0019] Figure 4 This is a schematic diagram of the positioning results of the agricultural machinery hangar;

[0020] Figure 5 This is a schematic diagram of an agricultural machinery hangar positioning device based on point cloud registration according to the present invention. DETAILED DESCRIPTION

[0021] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only intended to illustrate the present invention and are not intended to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.

[0022] This invention provides a method and device for locating agricultural machinery hangars based on point cloud registration. This method achieves precise hangar positioning by registering point cloud data acquired by scanning with pre-established three-dimensional point cloud map data using a laser radar installed on the agricultural machinery. Specifically, the laser point cloud positioning module loads the pre-established hangar point cloud map data and receives the hangar point cloud frame scanned by the laser radar to be registered. The registration result between the point cloud frame and the point cloud map is the positioning result of the agricultural machinery on the hangar point cloud map. This invention is suitable for initial positioning of a surround-view scanning laser radar installed at an angle on top of agricultural machinery.

[0023] like Figure 1 As shown in FIG, the agricultural machinery hangar positioning method based on point cloud registration of the present invention is improved based on the Scan Context++ open source algorithm to realize the initialization of agricultural machinery lidar hangar point cloud positioning, which specifically includes the following steps:

[0024] S1. Use the improved Scan Context++ algorithm to perform first-order ring key coarse matching and second-order fan key fine matching (including column offset coarse search and fine search) on the hangar real-time point cloud frame obtained by the tilted agricultural machinery lidar and the prior 3D point cloud map. Obtain the candidate key frame and the rotation angle between the hangar real-time point cloud frame and the candidate key frame point cloud. Based on this, generate the initial registration matrix of the normal distribution transformation, including:

[0025] S1.1 Load the prior 3D point cloud map pre-built based on the agricultural machinery lidar, and load the keyframe point cloud and keyframe pose of the prior 3D point cloud map. Among them, the prior 3D point cloud map is established using the SLAM algorithm based on the hangar point cloud, inertial navigation and other data collected during the movement of agricultural machinery. The keyframe is a representative frame in the process of establishing the prior 3D point cloud map. When establishing the prior 3D point cloud map, the pose of the keyframe in the point cloud map is saved at the same time, which is called the keyframe pose, and the point cloud scanned by the agricultural machinery lidar corresponding to the keyframe is saved, which is called the keyframe point cloud. Calculate the improved scan context descriptor of each keyframe point cloud, further generate a ring key, and establish a kd-tree of the keyframe point cloud ring key;

[0026] The agricultural machinery lidar used to construct the prior 3D point cloud map and collect the hangar's real-time point cloud frames for positioning initialization is the same device. Because the agricultural machinery lidar is installed at an angle, the hangar's real-time point cloud frames collected by the agricultural machinery lidar need to be converted to the same horizontal body coordinate system as the key frame point cloud and key frame pose of the prior 3D point cloud map. Tilt correction is performed to ensure the vertical distribution of the point cloud is valid, thereby preventing distortion of the scan context descriptor.

[0027] S1.2 receives the real-time point cloud frame of the hangar collected by the agricultural machinery lidar for positioning initialization, converts it to the horizontal body coordinate system, calculates the improved scan context descriptor of the real-time point cloud frame of the hangar after the coordinate system conversion, further generates a ring key, and searches for several nearest neighbors of the ring key of the real-time point cloud frame of the hangar in the kd-tree established in S1.1, thereby completing the first-order coarse search of candidate key frames;

[0028] Improve the scan context descriptor of the hangar point cloud frame and divide the point cloud into Ring, divided evenly along the circumference into The average elevation of the point cloud within each ring and sector is selected as the real value of the area, so that the boundary features of the hangar wall are effectively retained, avoiding the extraction of only the maximum value, that is, the hangar top feature, which leads to the feature degradation of the scan context descriptor of the key frame point cloud and the real-time point cloud frame of the hangar in the rotation direction of the symmetry axis of the collected hangar top point cloud at some initialization positions within the hangar.

[0029] Regional real value The calculation formula is:

[0030] ;

[0031] Where, Indicates the A ring and A sector-shaped area, represents the real value of the region, is the first Point cloud coordinate vectors, It is a function that returns the value of the point cloud coordinate vector in the z coordinate system. is the number of point clouds in the region, Represents the sum of all point cloud function values.

[0032] S1.3 performs a second-order precise search for candidate key frames, including:

[0033] Generate the fan-shaped key of the hangar real-time point cloud frame and each candidate key frame point cloud, and compare the distance between the hangar real-time point cloud frame and each candidate key frame point cloud in turn.

[0034] S1.3.1. Perform an L2 norm comparison of the sector key of the hangar real-time point cloud frame with the sector key of the candidate key frame after column traversal offset, and search for the rough value of column offset;

[0035] The point cloud data collected by tilted agricultural machinery lidar lacks 360-degree rotation invariance of the point cloud descriptor in the horizontal direction of the fuselage. To strengthen the rotation constraint, improve the solution speed, and further prevent the misdetection of the rotation angle, the ScanContext++ method is improved to add constraints when searching for the rough value (rough value) of the column offset. The column offset traversal range of the fan key of the candidate keyframe point cloud is set to 0~90 degrees and 270 degrees~360 degrees. The number of column offsets is for:

[0036] ;

[0037] Where, is the number of sectors;

[0038] S1.3.2 The fan-shaped key of the candidate key frame point cloud is expanded on both sides of the column offset with the rough value of the column offset as the center. The precise distance between the hangar real-time point cloud frame and the candidate key frame point cloud after the column offset is calculated through cosine similarity. The column offset corresponding to the shortest distance can be converted into the rotation angle between the hangar real-time point cloud frame and the candidate key frame point cloud. This shortest distance is the distance between the hangar real-time point cloud frame and the candidate key frame point cloud.

[0039] Column offset Converted to the rotation angle of the hangar real-time point cloud frame and the candidate key frame point cloud The calculation formula is:

[0040] ;

[0041] Where, It is a function of converting degrees to radians.

[0042] S1.3.3 After implementing S1.3.1 and S1.3.2 for each candidate keyframe point cloud, that is, after calculating the distance between the hangar real-time point cloud frame and each candidate keyframe point cloud, several candidate keyframes that meet the set distance threshold are selected as second-order candidate keyframes.

[0043] In step S1.4, the prior 3D point cloud map is set as the target point cloud for the normal distribution transformation initial registration. The hangar real-time point cloud frame, after voxel filtering and conversion to the horizontal body coordinate system, is used as the source point cloud. The rotation angles of the hangar real-time point cloud frame and several second-order candidate keyframes obtained in step S1.3 are applied to the corresponding second-order candidate keyframe poses, and used as the initial values ​​for the normal distribution transformation initial registration to perform point cloud registration. The point cloud registration probability and transformation matrix calculated for each initial value are obtained. The maximum value of the point cloud registration probability is selected. If it is greater than the preset initial registration probability threshold, the corresponding transformation matrix is ​​the registration initial value for continuous positioning.

[0044] Specifically, the rotation angles of the hangar real-time point cloud frame and several second-order candidate key frames are applied to the corresponding second-order candidate key frame poses as the initial values ​​of point cloud registration. The calculation method is:

[0045] ;

[0046] Where, is the rotation angle between the hangar real-time point cloud frame and a second-order candidate key frame, is the homogeneous matrix of the second-order candidate keyframe pose.

[0047] S2, using the initial registration matrix as the initial value, continuously registering the collected hangar real-time positioning point cloud frame data with the prior 3D point cloud map, outputting the agricultural machinery posture, and returning to S1 for reinitialization when positioning is interrupted due to dynamic scenes, including:

[0048] S2.1 Normal distribution transformation continuous positioning uses the prior three-dimensional point cloud map as the target point cloud, and the voxel filtering and converted into the hangar real-time positioning point cloud frame data in the horizontal body coordinate system collected by the agricultural machinery positioning lidar as the source point cloud. The transformation matrix obtained in S1.4 is used as the initial value for point cloud registration, and the point cloud registration probability and the transformation matrix are output. If the point cloud registration probability is greater than the preset initial positioning success threshold, the initialization is successful. The transformation matrix is ​​the initial positioning result of the agricultural machinery on the prior three-dimensional point cloud map.

[0049] Specifically, the source point cloud for continuous positioning using normal distribution transformation is a point cloud collected based on agricultural machinery for continuous positioning of the hangar, which includes but is not limited to the real-time point cloud frame data of the laser radar scan used in S1 to construct the hangar prior three-dimensional point cloud map and positioning initialization, and is transferred to the same horizontal body coordinate system;

[0050] When the continuous positioning of normal distribution transformation is successfully initialized in S2.1, S2.2 takes into account the characteristics of low-speed movement of agricultural machinery in the hangar, and obtains the initial value of positioning and registration of the next frame based on the uniform motion model, and then carries out the normal distribution transformation positioning operation of the next frame in sequence, and outputs continuous positioning results; when initialization fails or the positioning is interrupted due to dynamic transformation of the environment, the transformation matrix obtained in S1.4 is used as the initial value of registration for reinitialization.

[0051] Specifically, the initial value of the next frame positioning and registration is obtained based on the uniform motion model The calculation formula is:

[0052] ;

[0053] Where, is the positioning result of the previous frame, Positioning result for the current frame.

[0054] Example:

[0055] In length, width and height approximately Experiments were conducted in a rectangular hangar. The agricultural machinery LiDAR was installed on top of the machinery at a 30-degree downward tilt, approximately 3.5 meters high. Key parameters were set: 20 rings, 60 sectors, a maximum radius of 40 meters, a LiDAR height of 4 meters, a distance threshold of 0.8 meters, and a preset initial registration probability threshold of 4.8.

[0056] A frame of point cloud collected by agricultural machinery laser radar in the hangar is as follows Figure 2 As shown in FIG, the set of white scattered points in the figure is the real-time point cloud frame of the hangar transferred to the horizontal body coordinate system.

[0057] The visualization diagram of the scan context descriptor generated based on the real-time point cloud frame of the hangar is as follows Figure 3 As shown, Figure 3 The horizontal axis is a fan-shaped sequence, the vertical axis is a ring-shaped sequence, and the value of each color block is the real value of the area composed of the ring-shaped fan. Figure 3 (b) is the scan context descriptor of the hangar real-time point cloud frame obtained by the method proposed in this invention. Figure 3Compared to the scan context descriptor obtained by the original method in (a) for the same hangar real-time point cloud frame, the column offset feature constraint of the fan-shaped feature is added, effectively reducing the detection ambiguity of the rotation angle. Table 1 shows the initialization process and result data of the agricultural machinery hangar positioning. It shows the second-order candidate keyframes and rotation angles searched based on the hangar real-time point cloud frame data, and the registration probability after the second-order candidate keyframe poses and rotation angles are used as the initial values ​​of the normal distribution transformation initial registration module. It can be seen that ScanContext++ encounters rotation angle detection ambiguity in multiple keyframes, resulting in the registration probability not meeting the preset initial registration probability threshold, making it difficult to provide the registration initial value of the normal distribution continuous positioning module, and may cause mismatching in the 255th keyframe. The improved ScanContext++ method achieves effective detection of rotation angles in multiple second-order candidate keyframes, alleviating the mismatch problem caused by the lack of rotation invariance of the descriptor of the tilted installation of the LiDAR agricultural machinery and the degradation of the symmetric features of the hangar scene. It has certain environmental adaptability to point cloud scene structure transformation and enhances the robustness of initial positioning.

[0058] Table 1 Agricultural machinery hangar positioning initialization data

[0059]

[0060] The positioning results of agricultural machinery in the hangar are as follows: Figure 4 As shown, positioning initialization (obtaining the initial positioning point) can be achieved, and the continuous positioning results of the agricultural machinery along the motion trajectory can be output.

[0061] like Figure 5 As shown, the present invention also provides an agricultural machinery hangar positioning device based on point cloud registration, which is used to implement the above method and includes the following modules:

[0062] The initial registration module uses the improved Scan Context++ algorithm to perform first-order ring key coarse matching and second-order fan key fine matching on the hangar real-time point cloud frame acquired by the tilted agricultural machinery lidar and the prior 3D point cloud map. It obtains the candidate keyframes and the rotation angles between the hangar real-time point cloud frame and the candidate keyframe point cloud, and generates the initial registration matrix of the normal distribution transformation based on this.

[0063] The continuous registration module uses the initial registration matrix as the initial value to continuously register the collected hangar real-time positioning point cloud frame data with the prior three-dimensional point cloud map, outputs the agricultural machinery posture, and uses the initial registration module to reinitialize when the dynamic scene causes positioning interruption.

[0064] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and runnable on the processor. When the processor executes the program, the steps of the above-mentioned agricultural machinery hangar positioning method based on point cloud registration are implemented.

[0065] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the above-mentioned agricultural machinery hangar positioning method based on point cloud registration are implemented.

[0066] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk drives, CD-ROMs, optical storage devices, etc.) containing computer-usable program code. The solutions in the embodiments of the present invention may be implemented using various computer languages, such as the object-oriented programming language Java and the interpreted scripting language JavaScript.

[0067] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0068] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0069] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0070] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0071] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A method for positioning agricultural machinery hangars based on point cloud registration, characterized in that: The steps include: S1. Use the improved Scan Context++ algorithm to perform first-order ring key coarse matching and second-order fan key fine matching on the hangar real-time point cloud frame obtained by the tilted agricultural machinery lidar and the prior 3D point cloud map, obtain the candidate key frame and the rotation angle between the hangar real-time point cloud frame and the candidate key frame point cloud, and generate the initial registration matrix of the normal distribution transformation based on this; S2. Using the initial registration matrix as the initial value, continuously register the collected hangar real-time positioning point cloud frame data with the prior three-dimensional point cloud map, output the agricultural machinery posture, and return to S1 for reinitialization when the dynamic scene causes positioning interruption.

2. The method for positioning an agricultural machinery hangar based on point cloud registration according to claim 1, characterized in that: In S1, the real-time point cloud frame of the hangar collected by the agricultural machinery laser radar is converted to the same horizontal body coordinate system as the key frame point cloud and key frame pose of the prior three-dimensional point cloud map.

3. The method for positioning an agricultural machinery hangar based on point cloud registration according to claim 1, characterized in that: The improved Scan Context++ algorithm in S1 uses the average elevation of the point cloud within the annular and sector-shaped division area as the area value, retaining the boundary features of the hangar wall.

4. The method for positioning an agricultural machinery hangar based on point cloud registration according to claim 1, characterized in that: In the improved Scan Context++ algorithm in S1, in the second-order sector bond precise matching, the sector bond is first traversed in the range of 0–90° and 270°–360° to search for the rough value of the column offset, thereby constraining the offset range and further determining the rotation angle.

5. The method for positioning an agricultural machinery hangar based on point cloud registration according to claim 1, characterized in that: In S1, the same agricultural machinery laser radar is used to obtain the real-time point cloud frame of the hangar and the prior point cloud map.

6. The method for positioning an agricultural machinery hangar based on point cloud registration according to claim 1, characterized in that: In S2, the continuous registration uses a uniform motion model to predict the initial value of the next frame.

7. The method for positioning an agricultural machinery hangar based on point cloud registration according to claim 1, characterized in that: In S2, the determination of positioning interruption includes triggering reinitialization when the registration probability is lower than a threshold.

8. An agricultural machinery hangar positioning device based on point cloud registration, characterized in that: Includes the following modules: The initial registration module uses the improved Scan Context++ algorithm to perform first-order ring key coarse matching and second-order fan key fine matching on the hangar real-time point cloud frame acquired by the tilted agricultural machinery lidar and the prior 3D point cloud map. It obtains the candidate keyframes and the rotation angles between the hangar real-time point cloud frame and the candidate keyframe point cloud, and generates the initial registration matrix of the normal distribution transformation based on this. The continuous registration module uses the initial registration matrix as the initial value to continuously register the collected hangar real-time positioning point cloud frame data with the prior three-dimensional point cloud map, outputs the agricultural machinery posture, and uses the initial registration module to reinitialize when the dynamic scene causes positioning interruption.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the agricultural machinery hangar positioning method based on point cloud registration as described in any one of claims 1 to 7 are implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the agricultural machinery hangar positioning method based on point cloud registration as described in any one of claims 1 to 7 are implemented.

Images