Automated method and device for measuring the volume of a stack

Abstract

This application relates to an automated method and apparatus for measuring the volume of a pile. The method includes: scanning the target pile and the container environment storing the target pile to collect scanned point cloud data and sampled point cloud data; performing point cloud registration on the scanned and sampled point cloud data to obtain registered point cloud data, and then cropping and snapping it to obtain a set of boundary points at the boundary between the target pile and the container environment; based on the boundary point set, denoising and segmenting the cropped registered point cloud data to obtain segmented point clouds; and extracting the complete surface information of the target pile based on the boundary point set and the segmented point clouds to perform surface reconstruction to generate a closed triangular mesh corresponding to the target pile, and using the closed triangular mesh to calculate the volume of the target pile. This solves the problems of insufficient accuracy, difficulty in handling boundary issues, high data acquisition requirements, and limited application scenarios in existing point cloud volume measurement technologies.

Description

Technical Field

[0001] This application relates to the field of point cloud data processing technology, and in particular to an automated method and apparatus for measuring the volume of a stack. Background Technology

[0002] Traditional volume measurement methods are mostly based on manual measurement or two-dimensional image analysis. These methods are not only time-consuming and labor-intensive, but also difficult to guarantee accuracy. In recent years, with the development of laser scanning technology, volume measurement methods based on LiDAR point cloud data have gradually become mainstream, among which 2.5D point cloud volume measurement technology is widely used.

[0003] 2.5D point cloud volume measurement mainly relies on projecting point cloud data in three-dimensional space onto a two-dimensional plane to form a so-called "height map". In this method, each projection point retains its corresponding height information, thereby enabling the calculation of the approximate volume of the object. The advantage of this method is that its calculation is relatively simple and it is suitable for stacks with relatively regular geometric shapes. By reducing the dimensionality of point cloud data, 2.5D technology can effectively reduce computational complexity, so it can also operate well in resource-constrained environments.

[0004] However, 2.5D point cloud volume measurement technology also has the following significant limitations and drawbacks:

[0005] 1. Insufficient accuracy: 2.5D technology ignores the complex geometry of the stack, especially when the surface of the stack has large undulations or there are suspended areas, the accuracy of the measurement results will decrease significantly.

[0006] 2. Difficulty in handling boundary issues: In actual measurement scenarios, the surface of the stack may be partially obscured by other objects or in contact with containers (such as warehouse walls). 2.5D technology cannot accurately handle these complex situations, especially showing limitations in boundary handling, which further affects the reliability of measurement results.

[0007] 3. High requirements for data acquisition: Although the 2.5D technology is relatively simple to calculate, its accuracy still depends on high-quality point cloud data. This means that during the data acquisition process, the point cloud density must be high enough and the coverage must be comprehensive. If there are omissions or noise in the data, it may lead to inaccurate volume measurement results.

[0008] 4. Limited application scenarios: 2.5D technology is only applicable to stacks with relatively regular boundaries and surfaces, and cannot meet the measurement needs of some complex scenarios. For example, the surface shape and stacking pattern of materials stacked in containers may be very complex. In these cases, 2.5D technology is difficult to provide accurate measurement results.

[0009] In summary, existing point cloud volume measurement technologies lack accuracy, struggle to handle boundary issues, have high data acquisition requirements, and are limited in application scenarios, thus requiring urgent solutions. Summary of the Invention

[0010] This application provides an automated method and apparatus for measuring the volume of a stack, which solves the problems of insufficient accuracy, difficulty in handling boundary issues, high data acquisition requirements, and limited application scenarios of existing point cloud volume measurement technologies.

[0011] The first aspect of this application provides an automated method for measuring the volume of a pile, comprising the following steps: scanning a target pile and a container environment containing the target pile to collect scanned point cloud data corresponding to the target pile and sampled point cloud data corresponding to the container environment; performing point cloud registration on the scanned point cloud data and the sampled point cloud data to obtain registered point cloud data, and performing cropping and snap-fit ​​matching operations on the registered point cloud data to obtain a set of boundary points at the boundary between the target pile and the container environment; based on the boundary point set, performing denoising and point cloud segmentation on the cropped registered point cloud data to obtain a segmented point cloud, and extracting complete surface information of the target pile based on the boundary point set and the segmented point cloud, and performing surface reconstruction operation using the complete surface information to generate a closed triangular mesh corresponding to the target pile, and using the closed triangular mesh to calculate the volume of the target pile.

[0012] Optionally, in one embodiment of this application, the step of scanning the target pile and the container environment storing the target pile to collect scanned point cloud data corresponding to the target pile and sampled point cloud data corresponding to the container environment includes: determining the container environment of the target pile, and constructing a container 3D model corresponding to the container environment based on a preset Poisson reconstruction strategy or Alpha Wrap reconstruction strategy; sampling the container 3D model to generate sampled point cloud data of the container 3D model; and performing a preset full scan operation on the target pile using a preset laser scanner to obtain the scanned point cloud data corresponding to the target pile.

[0013] Optionally, in one embodiment of this application, the step of performing point cloud registration on the scanned point cloud data and the sampled point cloud data to obtain registered point cloud data, and performing cropping and snap-fit ​​matching operations on the registered point cloud data to obtain the boundary point set at the boundary of the target heap and the container environment, includes: performing a coarse registration operation on the scanned point cloud data and the sampled point cloud data to obtain a coarse registration result; performing a fine registration operation on the scanned point cloud data and the sampled point cloud data based on the coarse registration result to obtain the registered point cloud data; constructing a spatial index tree through the alignment bounding box of the container 3D model, and using the spatial index tree to crop the registered point cloud data to obtain cropped point cloud data; and performing a matching operation on the cropped point cloud data and the container 3D model based on a preset threshold matching algorithm until a preset number of times is reached to obtain the boundary point set.

[0014] Optionally, in one embodiment of this application, the step of denoising and segmenting the clipped registration point cloud data based on the boundary point set to obtain a segmented point cloud, and extracting the complete surface information of the target pile body based on the boundary point set and the segmented point cloud, includes: denoising the clipped point cloud data to obtain denoised point cloud data, and segmenting the denoised point cloud data to obtain the segmented point cloud; drawing a perpendicular line from each point in the boundary point set to the nearest surface of the container inner wall of the container environment, extending beyond the container space, and sampling the perpendicular line at equal intervals to obtain an extended point set; merging the boundary point set, the extended point set, and the segmented point cloud to obtain a first merged point cloud, and performing Alpha Wrap 3D reconstruction on the first merged point cloud to generate a clipping surface corresponding to the target pile body; extracting the contact area between the container inner wall of the container environment and the pile body surface of the target pile body based on the clipping surface, and obtaining the complete surface information of the target pile body through the contact area.

[0015] Optionally, in one embodiment of this application, the step of performing surface reconstruction using the complete surface information to generate a closed triangular mesh corresponding to the target pile, and using the closed triangular mesh to calculate the pile volume corresponding to the target pile, includes: sampling the contact surface to obtain contact surface point cloud data, and merging the boundary point set, the extended point set, the segmented point cloud, and the contact surface point cloud data to obtain a second merged point cloud; performing Alpha Wrap reconstruction on the second merged point cloud to obtain a first closed three-dimensional model volume; merging the boundary point set and the segmented point cloud to obtain a third merged point cloud, and performing Alpha Wrap reconstruction on the third merged point cloud to obtain a second closed three-dimensional model volume; and calculating the pile volume corresponding to the target pile based on the first closed three-dimensional model volume and the second closed three-dimensional model volume.

[0016] A second aspect of this application provides an automated pile volume measurement device, comprising: a data acquisition module for scanning a target pile and a container environment containing the target pile to acquire scanned point cloud data corresponding to the target pile and sampled point cloud data corresponding to the container environment; an adsorption matching module for performing point cloud registration operations on the scanned point cloud data and the sampled point cloud data to obtain registered point cloud data, and performing clipping and adsorption matching operations on the registered point cloud data to obtain a set of boundary points at the boundary between the target pile and the container environment; and a calculation module for performing denoising and point cloud segmentation on the clipped registered point cloud data based on the boundary point set to obtain a segmented point cloud, extracting complete surface information of the target pile based on the boundary point set and the segmented point cloud, performing surface reconstruction operations using the complete surface information to generate a closed triangular mesh corresponding to the target pile, and calculating the pile volume corresponding to the target pile using the closed triangular mesh.

[0017] Optionally, in one embodiment of this application, the acquisition module includes: a first reconstruction unit, configured to determine the container environment of the target stack and construct a container 3D model corresponding to the container environment based on a preset Poisson reconstruction strategy or an Alpha Wrap reconstruction strategy; a generation unit, configured to sample the container 3D model and generate sampled point cloud data of the container 3D model; and a scanning unit, configured to perform a preset full-scale scanning operation on the target stack using a preset laser scanner to obtain scanned point cloud data corresponding to the target stack.

[0018] Optionally, in one embodiment of this application, the adsorption matching module includes: a coarse registration unit, used to perform coarse registration operation on the scanned point cloud data and the sampled point cloud data to obtain a coarse registration result; a fine registration unit, used to perform fine registration operation on the scanned point cloud data and the sampled point cloud data based on the coarse registration result to obtain the registered point cloud data; a clipping unit, used to construct a spatial index tree through the alignment bounding box of the container 3D model, and use the spatial index tree to clip the registered point cloud data to obtain clipped point cloud data; and a matching unit, used to perform matching operation on the clipped point cloud data and the container 3D model based on a preset threshold matching algorithm until a preset number of times is reached to obtain the boundary point set.

[0019] Optionally, in one embodiment of this application, the calculation module includes: a denoising unit, configured to denoise the point cloud clipping data to obtain denoised point cloud data, and segment the denoised point cloud data to obtain the segmented point cloud; an acquisition unit, configured to draw a perpendicular line from each point in the boundary point set to the nearest surface of the container inner wall of the container environment, extending beyond the container space, and sampling the perpendicular line at equal intervals to obtain an extended point set; a first merging unit, configured to merge the boundary point set, the extended point set, and the segmented point cloud to obtain a first merged point cloud, and perform Alpha Wrap three-dimensional reconstruction on the first merged point cloud to generate a clipping surface corresponding to the target pile; and an extraction unit, configured to extract the contact area between the container inner wall of the container environment and the pile surface of the target pile based on the clipping surface, and obtain the complete surface information of the target pile through the contact area.

[0020] Optionally, in one embodiment of this application, the calculation module further includes: a second merging unit, used to sample the contact surface to obtain contact surface point cloud data, and merge the boundary point set, the extended point set, the segmented point cloud, and the contact surface point cloud data to obtain a second merged point cloud; a second reconstruction unit, used to perform Alpha Wrap reconstruction on the second merged point cloud to obtain a first closed three-dimensional model volume; a third merging unit, used to merge the boundary point set and the segmented point cloud to obtain a third merged point cloud, and perform Alpha Wrap reconstruction on the third merged point cloud to obtain a second closed three-dimensional model volume; and a calculation unit, used to calculate the pile volume corresponding to the target pile based on the first closed three-dimensional model volume and the second closed three-dimensional model volume.

[0021] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the automated stack volume measurement method as described in the above embodiments.

[0022] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described automated stack volume measurement method.

[0023] A fifth aspect of this application provides a computer program product, including a computer program that is executed to implement the above-described automated stack volume measurement method.

[0024] Therefore, the embodiments of this application have the following beneficial effects:

[0025] The embodiments of this application can collect scanned point cloud data corresponding to the target pile and sampled point cloud data corresponding to the container environment by scanning the target pile and the container environment. Point cloud registration is performed on the scanned point cloud data and sampled point cloud data to obtain registered point cloud data. The registered point cloud data is then cropped and snapped to obtain the boundary point set at the boundary between the target pile and the container environment. Based on the boundary point set, the cropped registered point cloud data is denoised and segmented to obtain segmented point clouds. Complete surface information of the target pile is extracted based on the boundary point set and segmented point clouds, and surface reconstruction is performed using this complete surface information to generate a closed triangular mesh corresponding to the target pile. The volume of the target pile is then calculated using this closed triangular mesh. This application achieves accurate measurement of pile volume through data preprocessing, point cloud registration, contact surface extraction, and surface reconstruction, significantly improving the automation and accuracy of the measurement. This solves the problems of insufficient accuracy, difficulty in handling boundary issues, high data acquisition requirements, and limited application scenarios in existing point cloud volume measurement technologies.

[0026] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0027] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0028] Figure 1 This is a flowchart of an automated stack volume measurement method provided according to an embodiment of this application;

[0029] Figure 2 A schematic diagram illustrating the relationship between various targets involved in an adsorption matching operation, provided as an embodiment of this application;

[0030] Figure 3 A schematic diagram of the execution logic of an automated stack volume measurement method provided for one embodiment of this application;

[0031] Figure 4 This is an example diagram of an automated stack volume measuring device according to an embodiment of this application;

[0032] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0033] Among them, 10-automated stack volume measurement device; 100-acquisition module, 200-adsorption matching module, 300-computation module; 501-memory, 502-processor, 503-communication interface. Detailed Implementation

[0034] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0035] The following describes an automated method and apparatus for measuring the volume of a stack according to embodiments of this application, with reference to the accompanying drawings. Addressing the problems mentioned in the background art, this application provides an automated method for measuring the volume of a stack. In this method, the target stack and the container environment storing the target stack are scanned to collect scanned point cloud data corresponding to the target stack and sampled point cloud data corresponding to the container environment. Point cloud registration is performed on the scanned and sampled point cloud data to obtain registered point cloud data. The registered point cloud data is then cropped and snapped to obtain a set of boundary points at the boundary between the target stack and the container environment. Based on the boundary point set, the cropped registered point cloud data is denoised and segmented to obtain a segmented point cloud. Complete surface information of the target stack is extracted based on the boundary point set and the segmented point cloud. Surface reconstruction is performed using the complete surface information to generate a closed triangular mesh corresponding to the target stack. The volume of the target stack is then calculated using the closed triangular mesh. This application achieves accurate measurement of the stack volume through data preprocessing, point cloud registration, contact surface extraction, and surface reconstruction, significantly improving the automation and accuracy of the measurement. This solves the problems of insufficient accuracy, difficulty in handling boundary issues, high data acquisition requirements, and limited application scenarios of existing point cloud volume measurement technologies.

[0036] Specifically, Figure 1 This is a flowchart of an automated stack volume measurement method provided in an embodiment of this application.

[0037] like Figure 1 As shown, the automated method for measuring the volume of a stack includes the following steps:

[0038] In step S101, the target pile and the container environment storing the target pile are scanned to collect the scanned point cloud data corresponding to the target pile and the sampled point cloud data corresponding to the container environment.

[0039] The embodiments of this application can first be implemented by using LiDAR scanning to scan the target heap and the container environment in which the heap is stored. The specific requirements for data acquisition via LiDAR scanning are as follows:

[0040] 1. The scan of the pile body must cover the entire visible surface of the object being measured, as well as the junction between the visible surface and the inner wall of the container;

[0041] 2. The point cloud data shows uniform point density on the surface of the heap without any omissions;

[0042] 3. The target pile body shall not come into contact with any unrelated objects;

[0043] 4. The closed nature of the container model: Taking the warehouse scene as an example, the 3D model of the inner wall of the warehouse needs to be topologically closed, the doors and windows are filled with geometric shapes, and the outer surface of the columns is part of the inner wall of the container.

[0044] Furthermore, embodiments of this application can also construct a three-dimensional model of the container inner wall by modeling with engineering drawings or by point cloud scanning, and obtain point cloud data of the container inner wall (i.e., sampled point cloud data) by sampling from the three-dimensional model of the container inner wall.

[0045] It should be noted that the pile body in this application embodiment is the processing object, and its surface information is obtained by laser scanning to form scan point cloud data; the container is the closed geometry in which the pile body is located, and its inner wall is in contact with the invisible surface of the pile body. The container model involved in this application embodiment is the three-dimensional model data of the container, which is used to define the boundary of the pile body to ensure that the measurement results are within the closed range of the container.

[0046] Optionally, in one embodiment of this application, scanning the target heap and the container environment storing the target heap to collect scanned point cloud data corresponding to the target heap and sampled point cloud data corresponding to the container environment includes: determining the container environment of the target heap and constructing a container 3D model corresponding to the container environment based on a preset Poisson reconstruction strategy or Alpha Wrap reconstruction strategy; sampling the container 3D model to generate sampled point cloud data of the container 3D model; and performing a preset full scan operation on the target heap using a preset laser scanner to obtain scanned point cloud data corresponding to the target heap.

[0047] Specifically, for containers that can be emptied, embodiments of this application can use a laser scanner to scan the inner wall of the container, and reconstruct it based on Poisson or Alpha Wrap. After processing by modeling software, a usable three-dimensional model of the closed container (i.e., the container model) can be obtained. If the container information cannot be obtained by scanning, embodiments of this application can obtain the corresponding container model by manually modeling from BIM or engineering drawings.

[0048] It should be noted that if the stack is located in an open space, the embodiments of this application need to determine the virtual container that can accommodate the stack based on the surface in contact with the stack.

[0049] Secondly, embodiments of this application can sample the container model by selecting sampling algorithms such as random uniform sampling or grid sampling, and the sampling density matches the density of the scanned point cloud to facilitate subsequent point cloud registration.

[0050] Subsequently, embodiments of this application may use a laser scanner to perform a full scan of the stack to ensure coverage of the visible surface of the stack, and the generated scan point cloud data should ensure uniform distribution density of points to avoid omissions.

[0051] Therefore, the embodiments of this application reduce manual intervention, improve the automation level of volume measurement, and enhance measurement efficiency and accuracy through laser scanning and point cloud data processing.

[0052] In step S102, point cloud registration is performed on the scanned point cloud data and the sampled point cloud data to obtain registered point cloud data. Then, the registered point cloud data is cropped and snap-fitted to obtain the boundary point set at the boundary of the target stack and the container environment.

[0053] Furthermore, embodiments of this application also require registering the scanned point cloud data with the sampled point cloud data obtained from the container model, so that the scanned point cloud and the container model are aligned to obtain registered point cloud data; then, the registered point cloud data is cropped and snapped to remove the point set located outside the container in the scanned point cloud, and the boundary point set at the junction of the stack and the container is obtained, thereby ensuring that the boundary information of the stack surface is accurate for subsequent volume calculation.

[0054] Optionally, in one embodiment of this application, point cloud registration is performed on scanned point cloud data and sampled point cloud data to obtain registered point cloud data. Then, clipping and snapping matching operations are performed on the registered point cloud data to obtain a set of boundary points at the boundary of the target heap and the container environment. This includes: performing coarse registration on the scanned point cloud data and sampled point cloud data to obtain a coarse registration result; performing fine registration on the scanned point cloud data and sampled point cloud data based on the coarse registration result to obtain registered point cloud data; constructing a spatial index tree using the bounding box of the container's 3D model, and clipping the registered point cloud data using the spatial index tree to obtain clipped point cloud data; and performing matching operations on the clipped point cloud data and the container's 3D model based on a preset threshold matching algorithm until a preset number of matching operations is reached to obtain a set of boundary points.

[0055] It should be noted that the embodiments of this application can register the scanned point cloud data with the point cloud data sampled from the container model to align the scanned point cloud data to the container. The specific registration steps are as follows:

[0056] Step 1: Coarse registration

[0057] The embodiments of this application use the 4PCS (4-point coplanar consistency) algorithm to perform preliminary alignment of the scanned point cloud data and the sampled point cloud of the container model (i.e., sampled point cloud data). In other words, in the coarse registration stage, the embodiments of this application mainly ensure that the two are roughly aligned in three-dimensional space.

[0058] Step 2: Precise registration

[0059] After coarse registration is completed, embodiments of this application may use the ICP (Iterative Closest Point) algorithm for precise registration to obtain registered point cloud data, further improving the alignment accuracy of the two and ensuring the accuracy of the measurement results.

[0060] Subsequently, embodiments of this application can also use the enclosed space defined by the container model as the boundary to crop the registered point cloud data, in order to remove point sets located outside the container in the scanned point cloud. The specific cropping steps are as follows:

[0061] Step 1: Construct a spatial index tree

[0062] A spatial index tree is constructed using the AABB (Axis Aligned Bounding Box) of the container model to support subsequent pruning operations;

[0063] Step 2: Point Cloud Cropping

[0064] By using the constructed spatial index tree, the scanned point cloud data is traversed, and it is determined whether each point in the scanned point cloud data is located inside the container model. Point cloud data located outside the container is removed, and only the point cloud within the enclosed space of the container is retained to obtain point cloud clipping data, thereby ensuring the accuracy of the final volume measurement.

[0065] Furthermore, embodiments of this application also require an snap-fit ​​operation on the point cloud cropping data, such as... Figure 2 As shown. To facilitate understanding of the adsorption matching operation process by those skilled in the art, embodiments of this application may first define a threshold matching algorithm, the input parameters accepted by which the algorithm are shown in Table 1:

[0066] Table 1

[0067] Parameter name Parameter type Remark Source Cloud Point cloud Target point cloud or 3D model Point cloud or 3D model threshold floating point This parameter is greater than 0.

[0068] It should be noted that the output of this threshold matching algorithm is the set of points in the source point cloud that match the target point cloud or 3D model. When the matching target is a point cloud, the output point set consists of those points in the source point cloud whose distance to the nearest neighbor in the target point cloud is less than or equal to the threshold; when the matching target is a 3D model, the output point set consists of those points in the source point cloud whose distance to the nearest face in the target 3D model is less than or equal to the threshold.

[0069] To determine the nearest point or surface in the target for each point in the source point cloud, embodiments of this application require first constructing a KD tree for the target point cloud, or constructing an AABB tree for the target 3D model.

[0070] In the actual execution of the adsorption matching operation, in order to obtain the boundary point set, the embodiments of this application can first use a threshold matching algorithm to match the scanned point cloud (i.e., the point cloud clipping data) after the previous step with the container model, and obtain a new point cloud composed of the boundary point set and the container inner wall points obtained during the scanning point cloud process; then, the new point cloud is matched with the remaining point set in the source point cloud again, and the resulting point set is the boundary point set.

[0071] In actual data processing, the above matching process needs to be executed 3 to 5 times, each time based on a different threshold. The final set of boundary points is formed by merging the results of multiple matches. The initial threshold can be the average point distance of the scanned point cloud after cropping. In the loop, n times the initial threshold is used as the threshold for this match.

[0072] In addition, the adsorption matching step also needs to export the set of points remaining in the scanned point cloud after removing the points on the inner wall and boundary of the container. This part usually includes the main part of the target pile point cloud, the noise points, and the main part of the irrelevant object surface points.

[0073] Therefore, the embodiments of this application obtain the boundary point set at the boundary of the target stack and the container environment through point cloud registration, cropping and snap-fit ​​operations, thereby providing reliable data support for the calculation of the stack volume.

[0074] In step S103, based on the boundary point set, the clipped registered point cloud data is denoised and segmented to obtain a segmented point cloud. The complete surface information of the target pile is extracted based on the boundary point set and the segmented point cloud. The surface reconstruction operation is performed using the complete surface information to generate a closed triangular mesh corresponding to the target pile. The volume of the target pile is calculated using the closed triangular mesh.

[0075] Furthermore, embodiments of this application also require eliminating isolated points and abnormal point cloud data by statistically analyzing the density of points in the neighborhood to ensure the quality of the remaining point cloud; secondly, the point cloud after noise reduction is segmented based on the DBSCAN (Density-based spatial clustering of applications with noise) algorithm to distinguish the point cloud of the stack from that of irrelevant objects.

[0076] After that, as Figure 3 As shown, embodiments of this application can extract the contact area between the surface of the stack and the inner wall of the container by analyzing the boundary point set, thereby obtaining complete surface information of the stack.

[0077] Finally, embodiments of this application can perform Alpha Wrap surface reconstruction on the complete pile point cloud to obtain a closed triangular mesh, and calculate the pile volume (i.e., the spatial volume occupied by the irregular geometry of the pile) using the volume element integration method and the closed triangular mesh.

[0078] Therefore, the embodiments of this application achieve accurate measurement of the volume of the stack through innovative data preprocessing, point cloud registration, cropping, adsorption matching, noise reduction, segmentation, contact surface extraction and surface reconstruction, which significantly improves the automation and accuracy of the measurement.

[0079] Optionally, in one embodiment of this application, based on the boundary point set, the clipped registered point cloud data is denoised and segmented to obtain a segmented point cloud, and the complete surface information of the target pile is extracted based on the boundary point set and the segmented point cloud, including: denoising the clipped point cloud data to obtain denoised point cloud data, and segmenting the denoised point cloud data to obtain a segmented point cloud; drawing a perpendicular line from each point in the boundary point set to the nearest surface of the container inner wall of the container environment, extending it beyond the container space, and sampling the perpendicular lines at equal intervals to obtain an extended point set; merging the boundary point set, the extended point set, and the segmented point cloud to obtain a first merged point cloud, and performing Alpha Wrap 3D reconstruction on the first merged point cloud to generate a clipping surface corresponding to the target pile; based on the clipping surface, extracting the contact area between the container inner wall of the container environment and the pile surface of the target pile, and obtaining the complete surface information of the target pile through the contact area.

[0080] Specifically, embodiments of this application may also use SOR (Statistical Outlier Removal, a spatial distribution-based denoising algorithm) to denoise the point cloud cropping data in order to eliminate noise that may be generated during laser point cloud scanning, thereby obtaining denoised point cloud data.

[0081] Secondly, the embodiments of this application also require the DBSCAN clustering algorithm to separate the main part of the target pile point cloud from the main part of the surface of irrelevant objects. The neighborhood radius eps is selected as 8 to 16 times the average point distance, and the minimum number of points minPts is selected as 1 / 2 of the average number of points within the eps radius. In order to determine which clusters belong to the target pile, the embodiments of this application can first filter out point clusters with too high centroid and too few points. These two parameters are pre-configured based on empirical values ​​of the measurement scenario, and then user input is accepted, and the target pile is selected through a graphical interface.

[0082] Subsequently, embodiments of this application can measure the close contact between the invisible surface portion (i.e., the contact surface) of the target stack and the container by cutting out a three-dimensional model of the inner wall of the container.

[0083] In the specific implementation process, the point cloud of the pile needs to be preprocessed before the trimming step. The boundary point set obtained in the adsorption matching operation may contain the boundary between irrelevant objects and the inner wall of the container, which needs to be removed first. Then, a threshold matching is performed again, using the boundary point set as the source point cloud and the pile point cloud (i.e., the segmented point cloud) obtained in the segmentation step as the target point cloud. The threshold is selected as 3 to 5 times the average point distance, and the boundary point set of the target pile and the inner wall of the container can be obtained.

[0084] Furthermore, the specific steps for creating the cutting surface in this application embodiment are as follows:

[0085] Step 1: Extend a perpendicular line from each point in the boundary point set to the nearest face of the container's inner wall, beyond the container space, and sample the extended point set at equal intervals along the perpendicular line.

[0086] Step 2: Merge the boundary point set, the extended point set, and the target heap point cloud to obtain the first merged point cloud;

[0087] Step 3: Perform Alpha Wrap 3D reconstruction on the first merged point cloud to obtain an appropriate clipping surface (actually a clipping volume). In the Alpha Wrap algorithm parameters, the alpha value can be selected to be about twice the average point distance, and the offset can be selected to be half the average point distance.

[0088] After obtaining the trimming plane, the container model is segmented using the trimming plane to obtain three connected parts (based on the direction of gravity): one above the target pile, one inside the trimming body, and one below the target pile. (In reality, there may be more than three connected parts.) Strictly speaking, in actual execution, the boundaries of all three parts are not necessarily on the trimming body. The embodiments of this application can distinguish these three parts through the following steps:

[0089] Step 1: Traverse all vertices of the connected component. For vertex v, determine the relative position of v with respect to the clipping body. If v is inside the clipping body, then this part is the part inside the clipping body, and the algorithm ends. If v is outside the clipping body, proceed to step 3. If v is exactly on the surface of the clipping body, continue the loop.

[0090] Step 2: If the algorithm in Step 1 traverses to the last vertex, then that part is inside the clipping body;

[0091] Step 3: Treat all vertices of the connected component as point clouds, perform threshold matching with the boundary point set, and accumulate the vector formed by each boundary point-vertex ordered pair to obtain the feature vector of the connected component;

[0092] Step 4: The connected components with small z values ​​(generally less than 0) are located below the target pile, while the connected components with large z values ​​(generally greater than 0) are located above the target pile.

[0093] Finally, embodiments of this application may preserve the connected portion located below the target stack and use it as a contact surface (i.e., complete surface information).

[0094] Therefore, the embodiments of this application, by introducing steps such as registration, trimming, and segmentation of the container model and the stack, can effectively handle the relationship between the stack and the complex environment, so as to ensure that the measurement results are limited to the target stack and avoid interference from the external environment of the container or irrelevant objects on the volume calculation.

[0095] Optionally, in one embodiment of this application, a surface reconstruction operation is performed using complete surface information to generate a closed triangular mesh corresponding to the target pile body, and the pile body volume corresponding to the target pile body is calculated using the closed triangular mesh, including: sampling the contact surface to obtain contact surface point cloud data, and merging the boundary point set, extended point set, segmented point cloud, and contact surface point cloud data to obtain a second merged point cloud; performing Alpha Wrap reconstruction on the second merged point cloud to obtain a first closed three-dimensional model volume; merging the boundary point set and segmented point cloud to obtain a third merged point cloud, and performing Alpha Wrap reconstruction on the third merged point cloud to obtain a second closed three-dimensional model volume; and calculating the pile body volume corresponding to the target pile body based on the first closed three-dimensional model volume and the second closed three-dimensional model volume.

[0096] It should be noted that, due to the characteristics of Alpha Wrap reconstruction, the portion of the joint with the target stack will be lost. Therefore, the embodiments of this application also need to extend the boundary point set to fill in the joint.

[0097] Specifically, in the embodiments of this application, the main parts of the extended point set, the boundary point set, the target pile point cloud (i.e., the segmented point cloud) and the point cloud obtained by sampling the contact surface (i.e., the contact surface point cloud data) need to be merged to obtain the second merged point cloud, and the second merged point cloud is reconstructed by Alpha Wrap so that the volume of the obtained closed three-dimensional model is (i.e., the volume of the first closed three-dimensional model) V1.

[0098] In ideal scanning data, the surface of the target object is a layer with no thickness, but in reality, it often has thickness, which introduces errors in volume measurement. Therefore, embodiments of this application also need to merge the boundary point set and the main part of the target pile point cloud (i.e., the third merged point cloud) to perform Alpha Wrap reconstruction, and calculate the volume of the closed three-dimensional model as (i.e., the volume of the second closed three-dimensional model) V2.

[0099] Furthermore, based on the volumes of the first and second closed three-dimensional models, the volume of the target pile body is calculated, resulting in the final volume of the target pile body: V1 - 1 / 2 * V2.

[0100] Therefore, the embodiments of this application ensure the integrity of point cloud data and filter out irrelevant points during registration, cropping, and segmentation processes, thereby minimizing the accumulation of errors and providing more reliable volume measurement results.

[0101] The automated pile volume measurement method proposed in this application involves scanning the target pile and the container environment containing it to collect scanned point cloud data corresponding to the target pile and sampled point cloud data corresponding to the container environment. Point cloud registration is performed on the scanned and sampled point cloud data to obtain registered point cloud data. The registered point cloud data is then cropped and snapped to obtain boundary point sets at the boundary between the target pile and the container environment. Based on the boundary point sets, the cropped registered point cloud data is denoised and segmented to obtain segmented point clouds. Complete surface information of the target pile is extracted from the boundary point sets and segmented point clouds, and surface reconstruction is performed using this complete surface information to generate a closed triangular mesh corresponding to the target pile. The pile volume is then calculated using this closed triangular mesh. This application achieves accurate measurement of pile volume through data preprocessing, point cloud registration, contact surface extraction, and surface reconstruction, significantly improving the automation and accuracy of the measurement.

[0102] Secondly, an automated stack volume measurement device according to an embodiment of this application is described with reference to the accompanying drawings.

[0103] Figure 4 This is a block diagram of an automated stack volume measurement device according to an embodiment of this application.

[0104] like Figure 4 As shown, the automated stack volume measurement device 10 includes: a data acquisition module 100, an adsorption matching module 200, and a calculation module 300.

[0105] The acquisition module 100 is used to scan the target pile and the container environment in which the target pile is stored, so as to acquire the scanned point cloud data corresponding to the target pile and the sampled point cloud data corresponding to the container environment.

[0106] The adsorption matching module 200 is used to perform point cloud registration operations on the scanned point cloud data and the sampled point cloud data to obtain registered point cloud data, and to perform cropping and adsorption matching operations on the registered point cloud data to obtain the boundary point set at the boundary of the target pile and the container environment.

[0107] The calculation module 300 is used to denoise and segment the clipped registered point cloud data based on the boundary point set to obtain the segmented point cloud. It also extracts the complete surface information of the target pile body based on the boundary point set and the segmented point cloud, and performs surface reconstruction operation based on the complete surface information to generate a closed triangular mesh corresponding to the target pile body. Finally, it uses the closed triangular mesh to calculate the pile body volume corresponding to the target pile body.

[0108] Optionally, in one embodiment of this application, the acquisition module 100 includes: a first reconstruction unit, a generation unit, and a scanning unit.

[0109] The first reconstruction unit is used to determine the container environment of the target heap and construct a 3D model of the container environment based on a preset Poisson reconstruction strategy or Alpha Wrap reconstruction strategy.

[0110] The generation unit is used to sample the 3D model of the container and generate sampled point cloud data of the 3D model of the container.

[0111] The scanning unit is used to perform a preset full scan of the target pile using a preset laser scanner to obtain the corresponding scan point cloud data of the target pile.

[0112] Optionally, in one embodiment of this application, the adsorption matching module 200 includes: a coarse registration unit, a fine registration unit, a trimming unit, and a matching unit.

[0113] The coarse registration unit is used to perform coarse registration on the scanned point cloud data and the sampled point cloud data to obtain the coarse registration result.

[0114] The fine registration unit is used to perform fine registration operations on the scanned point cloud data and the sampled point cloud data based on the coarse registration results, so as to obtain registered point cloud data.

[0115] The clipping unit is used to construct a spatial index tree by aligning the bounding box of the container's 3D model, and to clip the registered point cloud data using the spatial index tree to obtain clipped point cloud data.

[0116] The matching unit is used to perform matching operations on point cloud cropping data and container 3D models based on a preset threshold matching algorithm until a preset number of times is reached to obtain the boundary point set.

[0117] Optionally, in one embodiment of this application, the calculation module 300 includes: a denoising unit, an acquisition unit, a first merging unit, and an extraction unit.

[0118] The denoising unit is used to denoise the point cloud cropping data to obtain denoised point cloud data, and to segment the denoised point cloud data to obtain segmented point cloud.

[0119] The acquisition unit is used to draw a perpendicular line from each point in the boundary point set to the nearest face of the container inner wall of the container environment, and extend it beyond the container space, and to sample the perpendicular line at equal intervals to obtain the extended point set.

[0120] The first merging unit is used to merge the boundary point set, the extended point set, and the segmented point cloud to obtain the first merged point cloud, and to perform Alpha Wrap 3D reconstruction on the first merged point cloud to generate the clipping surface corresponding to the target heap.

[0121] The extraction unit is used to extract the contact area between the inner wall of the container environment and the surface of the target stack based on the cutting surface, and to obtain the complete surface information of the target stack through the contact area.

[0122] Optionally, in one embodiment of this application, the calculation module 300 further includes: a second merging unit, a second reconstruction unit, a third merging unit, and a calculation unit.

[0123] The second merging unit is used to sample the contact surface to obtain contact surface point cloud data, and merge the boundary point set, extended point set, segmented point cloud and contact surface point cloud data to obtain the second merged point cloud;

[0124] The second reconstruction unit is used to perform Alpha Wrap reconstruction on the second merged point cloud to obtain the first closed 3D model volume.

[0125] The third merging unit is used to merge the boundary point set and the segmented point cloud to obtain the third merged point cloud, and to perform Alpha Wrap reconstruction on the third merged point cloud to obtain the volume of the second closed 3D model.

[0126] The computing unit is used to calculate the volume of the target pile body based on the volume of the first closed three-dimensional model and the volume of the second closed three-dimensional model.

[0127] It should be noted that the foregoing explanation of the embodiment of the automated stack volume measurement method also applies to the automated stack volume measurement device of this embodiment, and will not be repeated here.

[0128] The automated pile volume measurement device proposed in this application includes a data acquisition module for scanning the target pile and the container environment storing the target pile to acquire scanned point cloud data corresponding to the target pile and sampled point cloud data corresponding to the container environment; an adsorption matching module for performing point cloud registration operations on the scanned point cloud data and sampled point cloud data to obtain registered point cloud data, and performing clipping and adsorption matching operations on the registered point cloud data to obtain the boundary point set at the boundary between the target pile and the container environment; and a calculation module for denoising and segmenting the clipped registered point cloud data based on the boundary point set to obtain segmented point clouds, extracting complete surface information of the target pile based on the boundary point set and segmented point clouds, and performing surface reconstruction operations using the complete surface information to generate a closed triangular mesh corresponding to the target pile, and calculating the pile volume corresponding to the target pile using the closed triangular mesh. This application achieves accurate measurement of pile volume through data preprocessing, point cloud registration, contact surface extraction, and surface reconstruction, significantly improving the automation and accuracy of the measurement.

[0129] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include:

[0130] The memory 501, the processor 502, and the computer program stored on the memory 501 and capable of running on the processor 502.

[0131] When processor 502 executes the program, it implements the automated stack volume measurement method provided in the above embodiments.

[0132] Furthermore, electronic devices also include:

[0133] Communication interface 503 is used for communication between memory 501 and processor 502.

[0134] The memory 501 is used to store computer programs that can run on the processor 502.

[0135] The memory 501 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0136] If the memory 501, processor 502, and communication interface 503 are implemented independently, then the communication interface 503, memory 501, and processor 502 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 5 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.

[0137] Optionally, in a specific implementation, if the memory 501, processor 502, and communication interface 503 are integrated on a single chip, then the memory 501, processor 502, and communication interface 503 can communicate with each other through an internal interface.

[0138] Processor 502 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0139] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described automated stack volume measurement method.

[0140] This application also provides a computer program product, including a computer program, which, when executed, is used to implement the above-described automated stack volume measurement method.

[0141] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0142] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0143] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0144] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0145] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0146] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0147] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0148] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. An automated method for measuring the volume of a stack, characterized in that, Includes the following steps: Scan the target heap and the container environment in which the target heap is stored to collect scanned point cloud data corresponding to the target heap and sampled point cloud data corresponding to the container environment; Point cloud registration is performed on the scanned point cloud data and the sampled point cloud data to obtain registered point cloud data. Then, the registered point cloud data is cropped and snap-fitted to obtain the boundary point set at the boundary between the target pile and the container environment. Based on the boundary point set, the clipped registered point cloud data is denoised and segmented to obtain a segmented point cloud. The complete surface information of the target pile is extracted based on the boundary point set and the segmented point cloud. The surface reconstruction operation is performed using the complete surface information to generate a closed triangular mesh corresponding to the target pile. The pile volume corresponding to the target pile is calculated using the closed triangular mesh. The step of denoising and segmenting the clipped registered point cloud data based on the boundary point set to obtain a segmented point cloud, and extracting the complete surface information of the target pile body based on the boundary point set and the segmented point cloud, includes: The point cloud cropping data is denoised to obtain denoised point cloud data, and the denoised point cloud data is segmented to obtain the segmented point cloud. Draw a perpendicular line from each point in the boundary point set to the nearest face of the container inner wall of the container environment, and extend it beyond the container space. Sample the perpendicular lines at equal intervals to obtain the extended point set. The boundary point set, the extended point set, and the segmented point cloud are merged to obtain a first merged point cloud, and the first merged point cloud is subjected to Alpha Wrap 3D reconstruction to generate the clipping surface corresponding to the target heap. Based on the cutting surface, the contact area between the inner wall of the container environment and the surface of the target pile is extracted, and the complete surface information of the target pile is obtained through the contact area.

2. The method according to claim 1, characterized in that, The scanning of the target pile and the container environment storing the target pile, to collect scanned point cloud data corresponding to the target pile and sampled point cloud data corresponding to the container environment, includes: The container environment of the target heap is determined, and a 3D model of the container corresponding to the container environment is constructed based on a preset Poisson reconstruction strategy or Alpha Wrap reconstruction strategy. The container's 3D model is sampled to generate sampled point cloud data of the container's 3D model; The target pile is subjected to a pre-set full scan operation using a pre-set laser scanner to obtain the scan point cloud data corresponding to the target pile.

3. The method according to claim 2, characterized in that, The step of performing point cloud registration on the scanned point cloud data and the sampled point cloud data to obtain registered point cloud data, and then performing cropping and snapping matching operations on the registered point cloud data to obtain the boundary point set at the boundary of the target heap and the container environment, includes: A coarse registration operation is performed on the scanned point cloud data and the sampled point cloud data to obtain the coarse registration result; Based on the coarse registration result, a fine registration operation is performed on the scanned point cloud data and the sampled point cloud data to obtain the registered point cloud data. A spatial index tree is constructed using the aligned bounding box of the container's 3D model, and the registered point cloud data is clipped using the spatial index tree to obtain clipped point cloud data. Based on a preset threshold matching algorithm, the point cloud cropping data and the container 3D model are matched until a preset number of times are reached to obtain the boundary point set.

4. The method according to claim 1, characterized in that, The step of performing surface reconstruction using the complete surface information to generate a closed triangular mesh corresponding to the target pile body, and calculating the pile body volume corresponding to the target pile body using the closed triangular mesh, includes: The complete surface information, i.e. the contact surface, is sampled to obtain contact surface point cloud data, and the boundary point set, the extended point set, the segmented point cloud and the contact surface point cloud data are merged to obtain a second merged point cloud; Alpha Wrap reconstruction is performed on the second merged point cloud to obtain the volume of the first closed 3D model; The boundary point set and the segmented point cloud are merged to obtain a third merged point cloud, and the third merged point cloud is reconstructed using Alpha Wrap to obtain a second closed 3D model volume. Based on the volume of the first closed three-dimensional model and the volume of the second closed three-dimensional model, the volume of the target pile body is calculated.

5. An automated device for measuring the volume of a stack, characterized in that, include: The acquisition module is used to scan the target pile and the container environment in which the target pile is stored, so as to acquire the scanned point cloud data corresponding to the target pile and the sampled point cloud data corresponding to the container environment; The adsorption matching module is used to perform point cloud registration operation on the scanned point cloud data and the sampled point cloud data to obtain registered point cloud data, and to perform cropping and adsorption matching operation on the registered point cloud data to obtain the boundary point set at the boundary of the target pile and the container environment. The calculation module is used to perform noise reduction and point cloud segmentation on the clipped registration point cloud data based on the boundary point set to obtain a segmented point cloud, and to extract the complete surface information of the target pile body according to the boundary point set and the segmented point cloud, and to perform surface reconstruction operation through the complete surface information to generate a closed triangular mesh corresponding to the target pile body, and to calculate the pile body volume corresponding to the target pile body using the closed triangular mesh. The calculation module includes: The denoising unit is used to denoise the point cloud cropping data to obtain denoised point cloud data, and to segment the denoised point cloud data to obtain the segmented point cloud. The acquisition unit is used to draw a perpendicular line from each point in the boundary point set to the nearest surface of the container inner wall of the container environment, and extend it beyond the container space, and to sample the perpendicular line at equal intervals to obtain the extended point set. The first merging unit is used to merge the boundary point set, the extended point set, and the segmented point cloud to obtain the first merged point cloud, and to perform Alpha Wrap three-dimensional reconstruction on the first merged point cloud to generate the clipping surface corresponding to the target heap. An extraction unit is used to extract the contact area between the inner wall of the container environment and the surface of the target pile based on the cutting surface, and to obtain the complete surface information of the target pile through the contact area.

6. The apparatus according to claim 5, characterized in that, The acquisition module includes: The first reconstruction unit is used to determine the container environment of the target heap and construct a container 3D model corresponding to the container environment based on a preset Poisson reconstruction strategy or Alpha Wrap reconstruction strategy. The generation unit is used to sample the three-dimensional model of the container and generate sampled point cloud data of the three-dimensional model of the container. The scanning unit is used to perform a preset full-scale scan of the target pile using a preset laser scanner to obtain the scan point cloud data corresponding to the target pile.

7. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the automated stack volume measurement method as described in any one of claims 1-4.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the automated stack volume measurement method as described in any one of claims 1-4.

9. A computer program product, comprising a computer program, characterized in that, The computer program is executed by a processor to implement the automated stack volume measurement method as described in any one of claims 1-4.

Images