Material scanning method, system, equipment, medium and program based on laser radar

Abstract

The invention relates to a material scanning method, system and device based on a laser radar, a storage medium and a computer program, and the method comprises the steps: obtaining the three-dimensional point cloud data of a preset material, carrying out the coordinate transformation of the three-dimensional point cloud data, obtaining the updated point cloud data, carrying out the filtering of the updated point cloud data, obtaining the standard point cloud data, and carrying out the calculation of the standard point cloud data. And extracting target features of the standard point cloud data, and supplementing missing data points in the standard point cloud data according to the target features to obtain complete material data. And the measurement precision and the measurement efficiency of the ground material are improved.

Description

Technical Field

[0001] The present application relates to the field of automated machinery, and in particular to a laser radar-based material scanning method, system, device, medium and program. Background Art

[0002] Existing scanning technologies for ground materials in bulk handling can meet basic needs to a certain extent, but there are still several significant shortcomings. Manual measurement not only relies on the experience and skills of the staff, is prone to human errors, but is also inefficient in large-scale or complex environments. Although traditional sensors (such as laser rangefinders, ultrasonic sensors, etc.) can provide basic distance or object recognition data, their accuracy and reliability are often interfered by environmental factors, such as weather conditions, dust, humidity, etc., which may affect the normal operation of the sensor. These technologies usually perform poorly under dynamic scanning, and often find it difficult to provide fast and accurate feedback in application scenarios with high real-time requirements. The existing technology has a low degree of automation and cannot be tightly integrated with the crane operating system, resulting in low operating efficiency and difficulty in meeting the efficient operation requirements of modern ports and warehousing. Therefore, it is necessary to develop more efficient, accurate, and environmentally adaptable technologies to improve the overall performance of material scanning and handling.

[0003] The existing technology has the problems of low measurement accuracy and low measurement efficiency for ground materials. Summary of the invention

[0004] The present application provides a laser radar-based material scanning method, system, device, medium and program to solve the problems of low measurement accuracy and low measurement efficiency of ground materials.

[0005] In a first aspect, the present application provides a material scanning method based on laser radar, comprising:

[0006] Acquire three-dimensional point cloud data of a preset material, and perform coordinate transformation on the three-dimensional point cloud data to obtain updated point cloud data;

[0007] Filtering the updated point cloud data to obtain standard point cloud data;

[0008] Extracting target features of the standard point cloud data;

[0009] The missing data points in the standard point cloud data are supplemented according to the target features to obtain complete material data.

[0010] In some embodiments, the coordinate transformation of the three-dimensional point cloud data to obtain updated point cloud data includes:

[0011] Acquire a preset update coordinate system, and generate a translation transformation matrix, a rotation transformation matrix, and a scaling transformation matrix according to the update coordinate system;

[0012] Converting the three-dimensional point cloud data into an initial point cloud matrix;

[0013] Multiplying the initial point cloud matrix with the translation transformation matrix, the rotation transformation matrix and the scaling transformation matrix to obtain an updated transformation matrix;

[0014] Generate updated point cloud data according to the updated transformation matrix.

[0015] In some embodiments, filtering the updated point cloud data to obtain standard point cloud data includes:

[0016] Performing spatial division on the updated point cloud data to obtain a plurality of first voxels;

[0017] Calculate the coordinate average of the updated point cloud data in each of the first voxels;

[0018] Aggregate each of the coordinate averages into key point cloud data;

[0019] Calculating the Euclidean distance between every two data in the key point cloud data;

[0020] Randomly select target data from the key point cloud data, and recursively traverse the adjacent data of the target data to group the target data and the adjacent data whose Euclidean distance between the target data and the adjacent data is less than a preset distance threshold into one cluster;

[0021] Counting the number of key point cloud data in each cluster, and filtering out key clusters that are less than a preset first number threshold and greater than a preset second number threshold according to the number;

[0022] The height of the key point cloud data in each of the key clusters is obtained, and a preset color is mapped to each key point cloud data according to the height and a preset height value range to obtain standard point cloud data.

[0023] In some embodiments, mapping a preset color to each key point cloud data according to the height and the preset height value range to obtain standard point cloud data includes:

[0024] Sort the heights from small to large to obtain a minimum height and a maximum height;

[0025] Generate a height value range according to the minimum height and the maximum height;

[0026] Generate a mapping rule according to the height value range and the preset color;

[0027] Acquire the color value of each key point cloud data according to the height and the mapping rule;

[0028] The RGB information of the preset color is obtained, and the RGB information is applied to the key point cloud data corresponding to the color value according to the color value to obtain the standard point cloud data.

[0029] In some embodiments, the target features of the standard point cloud data include: the maximum height, position and volume of a preset material, etc.

[0030] In detail, the extracting target features of the standard point cloud data includes:

[0031] Sort the height coordinates of the standard point cloud data from large to small to obtain the highest height of the preset material;

[0032] Dividing the standard point cloud data according to a preset volume size to obtain a plurality of second voxels;

[0033] Counting the total number of standard point cloud data in each of the second voxels;

[0034] Multiplying each of the total number of data by the volume of the second voxel corresponding to the total number of data to obtain a plurality of second voxel volumes;

[0035] Performing weighted summation on a plurality of the second voxel volumes to obtain a preset material volume;

[0036] The maximum height and the preset material volume are summarized as a target feature.

[0037] In some embodiments, the method of supplementing missing data points in the standard point cloud data according to the target features to obtain complete material data includes:

[0038] Projecting a plurality of the second voxels onto a two-dimensional plane to obtain two-dimensional point cloud data;

[0039] Identifying missing areas in the standard point cloud data according to the two-dimensional point cloud data;

[0040] Obtaining a first coordinate of a preset laser radar sensor and a second coordinate in the standard point cloud data;

[0041] Linear interpolation is performed on each missing point in the missing area one by one according to the first coordinate and the second coordinate to obtain complete material data.

[0042] In a second aspect, the present application provides a material scanning system based on laser radar, comprising:

[0043] A coordinate conversion module is used to obtain three-dimensional point cloud data of a preset material, and to perform coordinate conversion on the three-dimensional point cloud data to obtain updated point cloud data;

[0044] A data processing module, used for filtering the updated point cloud data to obtain standard point cloud data;

[0045] A feature extraction module, used to extract target features of the standard point cloud data;

[0046] The data supplement module is used to supplement the missing data points in the standard point cloud data according to the target features to obtain complete material data.

[0047] In a third aspect, the present application provides a computer device, comprising a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method described in the above aspects.

[0048] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the method described in the above aspects when executed by a processor.

[0049] In a fifth aspect, the present application provides a computer program product, including a computer program, which implements the steps of the method described in the above aspects when executed by a processor.

[0050] The present application provides a laser radar-based material scanning method, system, device, medium and program, which obtains the three-dimensional point cloud data of the preset material, performs coordinate transformation on the three-dimensional point cloud data to obtain updated point cloud data, filters the updated point cloud data to obtain standard point cloud data, extracts the target features of the standard point cloud data, supplements the missing data points in the standard point cloud data according to the target features, and obtains complete material data. It mainly solves the problems of low measurement accuracy and low measurement efficiency of ground materials. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The present application will be described in more detail below based on embodiments and with reference to the accompanying drawings:

[0052] Figure 1 A schematic diagram of a process of a material scanning method based on a laser radar provided in an embodiment of the present application;

[0053] Figure 2 A schematic diagram of a material scanning method based on laser radar provided in an embodiment of the present application;

[0054] Figure 3 A schematic diagram of functional modules of a laser radar-based material scanning system provided in an embodiment of the present application;

[0055] Figure 4 A schematic diagram of the structure of an electronic device for material scanning based on laser radar provided in an embodiment of the present application.

[0056] In the drawings, the same reference numerals are used for the same components, and the drawings are not drawn to scale. DETAILED DESCRIPTION

[0057] In order to enable those skilled in the art to better understand the technical solution of the present application, and to fully understand and implement how the present application applies technical means to solve technical problems and achieve the corresponding technical effects, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only embodiments of a part of the present application, not all embodiments. The embodiments of the present application and the various features in the embodiments can be combined with each other without conflict, and the technical solutions formed are all within the scope of protection of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work should belong to the scope of protection of the present application.

[0058] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0059] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0060] Based on the above background, this scheme proposes a material scanning method based on laser radar, which obtains three-dimensional point cloud data of preset materials, performs coordinate transformation on the three-dimensional point cloud data to obtain updated point cloud data, filters the updated point cloud data to obtain standard point cloud data, extracts target features of the standard point cloud data, supplements missing data points in the standard point cloud data according to the target features, and obtains complete material data, thereby improving the measurement accuracy and efficiency of ground materials.

[0061] Embodiment 1

[0062] Figure 1 A schematic diagram of a material scanning method based on a laser radar is provided in an embodiment of the present application, such as Figure 1 As shown, a material scanning method based on laser radar includes:

[0063] S1. Acquire three-dimensional point cloud data of a preset material, and perform coordinate transformation on the three-dimensional point cloud data to obtain updated point cloud data.

[0064] In an embodiment of the present invention, Figure 2 A schematic diagram of a material scanning method based on a laser radar provided in an embodiment of the present application, such as Figure 2 The pan-tilt and scanning system shown are installed on the gantry crane. The pan-tilt and scanning system form a scanning pan-tilt. The movable scanning pan-tilt can rotate with a larger scanning range. The pan-tilt is fixedly installed below the rotating platform of the gantry crane and rotates with the rotating platform of the gantry crane. At the same time, the laser scanning system can use the laser radar sensor to obtain the three-dimensional point cloud data of the preset material. The three-dimensional point cloud data includes: spatial position coordinates, point density, normal vector information, color information, reflection intensity, timestamp, etc.

[0065] In detail, the coordinate transformation of the three-dimensional point cloud data to obtain updated point cloud data includes:

[0066] Acquire a preset update coordinate system, and generate a translation transformation matrix, a rotation transformation matrix, and a scaling transformation matrix according to the update coordinate system;

[0067] Converting the three-dimensional point cloud data into an initial point cloud matrix;

[0068] Multiplying the initial point cloud matrix with the translation transformation matrix, the rotation transformation matrix and the scaling transformation matrix to obtain an updated transformation matrix;

[0069] Generate updated point cloud data according to the updated transformation matrix.

[0070] In detail, the translation transformation matrix, rotation transformation matrix and scaling transformation matrix are generated according to the updated coordinate system, and the formulas are as follows:

[0071] Translation transformation matrix:

[0072]

[0073] Among them, t x represents the translation of the x-axis, t y Represents the translation of the y-axis, t z Indicates the translation amount on the z-axis.

[0074] Rotation transformation matrix:

[0075]

[0076] Here, θ represents the rotation angle.

[0077] Scaling transformation matrix:

[0078]

[0079] Among them, s x Indicates the scaling factor of the x-axis, s y Indicates the scaling factor of the y-axis, s z Indicates the scaling factor of the z-axis.

[0080] In detail, when scanning is required, the industrial computer communicates with the PTZ to send a scanning command, the scanning program runs in the industrial computer on the gantry crane, and the 3D point cloud data obtained by the PTZ scanning is sent to the industrial computer. The point cloud coordinate system of the 3D point cloud data is consistent with the world coordinate system of the gantry crane through calibration rotation. The points on the calibration plane are the ground, the height is 0, and the points above the ground are materials. Points of different heights are displayed in different colors.

[0081] By performing coordinate transformation on 3D point cloud data, the original 3D point cloud data can be mapped to a new coordinate system, thus facilitating unified processing and analysis of the data. Generating translation, rotation, and scaling transformation matrices can effectively adjust the position, direction, and scale of the 3D point cloud data so that the 3D point cloud data is aligned with the updated coordinate system. This transformation not only improves the comparability and accuracy of the data, but also optimizes subsequent analysis tasks of the 3D point cloud data and enhances the flexibility and accuracy of data processing.

[0082] S2. Filter the updated point cloud data to obtain standard point cloud data.

[0083] In an embodiment of the present invention, an industrial computer is connected to a laser radar sensor for processing and analyzing the acquired three-dimensional point cloud data, including operations such as point cloud filtering, segmentation, and visualization, so as to improve material measurement accuracy and efficiency.

[0084] In detail, filtering the updated point cloud data to obtain standard point cloud data includes:

[0085] Performing spatial division on the updated point cloud data to obtain a plurality of first voxels;

[0086] Calculate the coordinate average of the updated point cloud data in each of the first voxels;

[0087] Aggregate each of the coordinate averages into key point cloud data;

[0088] Calculating the Euclidean distance between every two data in the key point cloud data;

[0089] Randomly select target data from the key point cloud data, and recursively traverse the adjacent data of the target data to group the target data and the adjacent data whose Euclidean distance between the target data and the adjacent data is less than a preset distance threshold into one cluster;

[0090] Counting the number of key point cloud data in each cluster, and filtering out key clusters that are less than a preset first number threshold and greater than a preset second number threshold according to the number;

[0091] The height of the key point cloud data in each of the key clusters is obtained, and a preset color is mapped to each key point cloud data according to the height and a preset height value range to obtain standard point cloud data.

[0092] In detail, mapping the preset color to each key point cloud data according to the height and the preset height value range to obtain standard point cloud data includes:

[0093] Sort the heights from small to large to obtain a minimum height and a maximum height;

[0094] Generate a height value range according to the minimum height and the maximum height;

[0095] Generate a mapping rule according to the height value range and the preset color;

[0096] Acquire the color value of each key point cloud data according to the height and the mapping rule;

[0097] The RGB information of the preset color is obtained, and the RGB information is applied to the key point cloud data corresponding to the color value according to the color value to obtain the standard point cloud data.

[0098] In detail, standard point cloud data contains not only three-dimensional coordinates (x, y, z) but also corresponding colors (r, g, b).

[0099] In detail, by spatially dividing the updated point cloud data, the entire point cloud space is divided into a number of first voxels, each of which is usually represented as a bounding box of a cube. The larger the voxel, the higher the degree of point cloud downsampling, and the smaller the voxel, the more details are retained. The coordinate average of all updated point cloud data in the first voxel is calculated, and the purpose of point cloud downsampling is achieved by reducing the number of points in each first voxel. The coordinate averages of all first voxels are combined to obtain a smaller key point cloud data, which retains the overall shape of the three-dimensional point cloud data and greatly reduces the number of point clouds.

[0100] Specifically, the Euclidean distance between each data in the key point cloud data is calculated, and the calculation formula is as follows:

[0101]

[0102] Among them, p1(a1,b1,c1) and p2(a2,b2,c2) represent two data points in the key point cloud data.

[0103] In detail, in order to ensure valid data, the size of the cluster needs to be screened. Set a maximum point limit for a cluster, and the oversized cluster will be split, retaining the clusters smaller than the preset first number threshold; set a minimum point limit for a cluster, and the smaller cluster will be split, retaining the clusters larger than the preset second number threshold, avoiding noise points and irrelevant objects from being mistakenly identified as valid clusters.

[0104] In detail, the height value of each point in the key point cloud data is mapped to a different color, each key point cloud data is traversed, and the color is mapped to each point in the key point cloud data based on the height value range, using different colors from low to high. After applying the color to the key point cloud data, it is rendered using the point cloud visualization tool to ensure that the color mapping effect is clearly visible.

[0105] By performing spatial division, coordinate averaging, key point extraction and cluster analysis on the updated point cloud data, noise is effectively reduced and meaningful point cloud features are retained. Combining height information and preset color mapping rules, key point cloud data in different height intervals can be intuitively displayed, enhancing the data visualization effect, which not only improves the quality and accuracy of standard point cloud data, but also facilitates subsequent data analysis.

[0106] S3. Extract target features of the standard point cloud data.

[0107] In the embodiment of the present invention, the target features of the standard point cloud data include: the maximum height, position and volume of the preset material.

[0108] In detail, the extracting target features of the standard point cloud data includes:

[0109] Sort the height coordinates of the standard point cloud data from large to small to obtain the highest height of the preset material;

[0110] Dividing the standard point cloud data according to a preset volume size to obtain a plurality of second voxels;

[0111] Counting the total number of standard point cloud data in each of the second voxels;

[0112] Multiplying each of the total number of data by the volume of the second voxel corresponding to the total number of data to obtain a plurality of second voxel volumes;

[0113] Performing weighted summation on a plurality of the second voxel volumes to obtain a preset material volume;

[0114] The maximum height and the preset material volume are summarized as a target feature.

[0115] Specifically, each of the total data is multiplied by the volume of the second voxel corresponding to the total data to obtain a plurality of second voxel volumes, and the calculation formula is as follows:

[0116]

[0117] Wherein, Noc represents the total number of standard point cloud data in each of the second voxels, V vox Indicates the preset volume size of each second voxel.

[0118] By performing height sorting and volume division on standard point cloud data, the target features of preset materials are effectively extracted, including maximum height and volume, providing effective support for spatial distribution, shape analysis and material identification of materials, thereby improving the accuracy and efficiency of automated material handling and management systems.

[0119] S4. Supplement the missing data points in the standard point cloud data according to the target features to obtain complete material data.

[0120] In an embodiment of the present invention, when the laser radar sensor encounters occlusion or other reasons during scanning that cause data missing in certain areas, a linear interpolation method is used to infer the possible values ​​of the missing points based on the information of the surrounding points, thereby filling these gaps and making the overall data of the preset material more continuous and complete.

[0121] In detail, the missing data points in the standard point cloud data are supplemented according to the target features to obtain complete material data, including:

[0122] Projecting a plurality of the second voxels onto a two-dimensional plane to obtain two-dimensional point cloud data;

[0123] Identifying missing areas in the standard point cloud data according to the two-dimensional point cloud data;

[0124] Obtaining a first coordinate of a preset laser radar sensor and a second coordinate in the standard point cloud data;

[0125] Linear interpolation is performed on each missing point in the missing area one by one according to the first coordinate and the second coordinate to obtain complete material data.

[0126] Specifically, the first coordinate (x0, y0, z0) of the preset laser radar sensor is obtained, the second coordinate (x1, y1, z1) in the standard point cloud data, and the intersection point with the ground after the missing area is completed is (x2, y2, z2). The calculation formula is as follows:

[0127]

[0128] x1≤x≤x2

[0129] y=y0+t(y1-y0)

[0130] z=z0+t(z1-z0)

[0131] Among them, A(x0,y0,z0) represents the first coordinate, B(x1,y1,z1) represents the second coordinate, t represents the first slope, and C(x2,y2,z2) represents the intersection with the ground after the missing area is completed.

[0132] In detail, since the height of the intersection of the missing area with the ground after completion is 0, the position of x2 can be calculated, and the calculation formula is as follows:

[0133] z2=0=z0+t2(z1-z0)

[0134]

[0135] x2=x0+t2(x1-x0)

[0136] Among them, A(x0, y0, z0) represents the first coordinate, B(x1, y1, z1) represents the second coordinate, and t2 represents the second slope.

[0137] Supplementing missing data points by the above method can effectively improve the integrity and accuracy of standard point cloud data. By projecting the second voxel onto a two-dimensional plane, complex data in high-dimensional space can be converted into easy-to-process two-dimensional information, thereby facilitating the identification of missing areas. Linear interpolation based on the coordinate information of the lidar sensor can generate reasonable estimates in the missing area to fill in the gaps, thereby ensuring the continuity and consistency of material data, significantly improving data reliability, reducing errors caused by missing data, and thus improving the measurement accuracy and efficiency of ground materials.

[0138] Embodiment 2

[0139] like Figure 3 As shown, it is a functional module diagram of a laser radar-based material scanning system 100 provided for this embodiment.

[0140] The laser radar-based material scanning system 100 of the present invention can be installed in an electronic device. According to the functions to be implemented, the laser radar-based material scanning system 100 can include a coordinate conversion module 101, a data processing module 102, a feature extraction module 103 and a data supplement module 104. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0141] In this embodiment, the functions of each module / unit are as follows:

[0142] A coordinate conversion module 101 is used to obtain three-dimensional point cloud data of a preset material, and to perform coordinate conversion on the three-dimensional point cloud data to obtain updated point cloud data;

[0143] A data processing module 102 is used to filter the updated point cloud data to obtain standard point cloud data;

[0144] A feature extraction module 103 is used to extract target features of the standard point cloud data;

[0145] The data supplement module 104 is used to supplement the missing data points in the standard point cloud data according to the target features to obtain complete material data.

[0146] Embodiment 3

[0147] Figure 4 A schematic diagram of the structure of an electronic device for material scanning based on laser radar provided in an embodiment of the present application.

[0148] On the basis of the above embodiments, this embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method described in the above embodiments.

[0149] In some implementations of this embodiment, a computer-readable storage medium is provided, on which a computer program is stored, characterized in that when the computer program is executed by a processor, the steps of the method described in the above embodiment are implemented.

[0150] In some implementations of this embodiment, a computer program product is provided, including a computer program, characterized in that when the computer program is executed by a processor, the steps of the method described in the above embodiment are implemented.

[0151] The processor may include, but is not limited to, one or more processors or microprocessors, etc. Each processor may be an application specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a controller, a microcontroller, a microprocessor or other electronic components to execute the methods in the above embodiments.

[0152] The computer-readable storage medium may be implemented by any type of volatile or non-volatile storage device or a combination thereof, and the computer-readable storage medium may include but is not limited to, for example, random access memory (RAM), read-only memory (ROM), flash memory, EPROM memory, EEPROM memory, registers, computer storage media (e.g., hard disk, floppy disk, solid-state drive, removable disk, CD ROM, DVD ROM, Blu-ray disc, etc.).

[0153] The computer-readable storage medium may also store at least one computer executable program, such as a computer-readable instruction. The computer-readable storage medium includes, but is not limited to, for example, a volatile memory and / or a non-volatile memory. The volatile memory may include, for example, a random access memory (RAM) and / or a cache memory (cache), etc. The computer-readable storage medium may include, for example, a read-only memory (ROM), a hard disk, a flash memory, etc. For example, a non-transitory computer-readable storage medium may be connected to a computing device such as a computer, and then, when the computing device runs the computer-readable instructions stored on the computer-readable storage medium, the various methods described above may be performed.

[0154] In addition, the computer device may also include (but not limited to) a data bus, an input / output (I / O) bus, a display, and input / output devices (eg, keyboard, mouse, speaker, etc.), etc.

[0155] The processor may communicate with a communication interface of an external device via an I / O bus via a wired or wireless network.

[0156] In one embodiment, the at least one computer executable instruction may also be compiled into or constitute a software product / computer program product, wherein one or more computer executable instructions are executed by a processor to perform the various functions and / or method steps in the embodiments described in the present technology.

[0157] In the embodiments provided in the present application, it should be understood that the disclosed systems and methods can also be implemented in other ways. The system embodiments described above are merely schematic, for example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to the multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the above-mentioned module, a program segment or a part of the code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or the flowchart, and the combination of the boxes in the block diagram and / or the flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0158] It should be noted that, in this application, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element limited by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0159] Although the implementation methods disclosed in this application are as above, the above contents are only the implementation methods adopted for facilitating the understanding of this application, and are not intended to limit this application. Any technician in the technical field to which this application belongs can make any modifications and changes in the form and details of the implementation without departing from the spirit and scope disclosed in this application, but the scope of patent protection of this application shall still be based on the scope defined in the attached claims.

Claims

1. A material scanning method based on laser radar, characterized in that: include: Acquire three-dimensional point cloud data of a preset material, and perform coordinate transformation on the three-dimensional point cloud data to obtain updated point cloud data; Filtering the updated point cloud data to obtain standard point cloud data; Extracting target features of the standard point cloud data; The missing data points in the standard point cloud data are supplemented according to the target features to obtain complete material data.

2. The method according to claim 1, characterized in that The step of performing coordinate transformation on the three-dimensional point cloud data to obtain updated point cloud data includes: Acquire a preset update coordinate system, and generate a translation transformation matrix, a rotation transformation matrix, and a scaling transformation matrix according to the update coordinate system; Converting the three-dimensional point cloud data into an initial point cloud matrix; Multiplying the initial point cloud matrix with the translation transformation matrix, the rotation transformation matrix and the scaling transformation matrix to obtain an updated transformation matrix; Generate updated point cloud data according to the updated transformation matrix.

3. The method according to claim 1, characterized in that The filtering of the updated point cloud data to obtain standard point cloud data includes: Performing spatial division on the updated point cloud data to obtain a plurality of first voxels; Calculate the coordinate average of the updated point cloud data in each of the first voxels; Aggregate each of the coordinate averages into key point cloud data; Calculating the Euclidean distance between every two data in the key point cloud data; Randomly select target data from the key point cloud data, and recursively traverse the adjacent data of the target data to group the target data and the adjacent data whose Euclidean distance between the target data and the adjacent data is less than a preset distance threshold into one cluster; Counting the number of key point cloud data in each cluster, and filtering out key clusters that are less than a preset first number threshold and greater than a preset second number threshold according to the number; The height of the key point cloud data in each of the key clusters is obtained, and a preset color is mapped to each key point cloud data according to the height and a preset height value range to obtain standard point cloud data.

4. The method according to claim 3, characterized in that The step of mapping the preset color to each key point cloud data according to the height and the preset height value range to obtain standard point cloud data includes: Sort the heights from small to large to obtain a minimum height and a maximum height; Generate a height value range according to the minimum height and the maximum height; Generate a mapping rule according to the height value range and the preset color; Acquire the color value of each key point cloud data according to the height and the mapping rule; The RGB information of the preset color is obtained, and the RGB information is applied to the key point cloud data corresponding to the color value according to the color value to obtain the standard point cloud data.

5. The method according to claim 1, characterized in that The target features of the standard point cloud data include: the maximum height, position and volume of the preset material. In detail, the extracting target features of the standard point cloud data includes: Sort the height coordinates of the standard point cloud data from large to small to obtain the highest height of the preset material; Dividing the standard point cloud data according to a preset volume size to obtain a plurality of second voxels; Counting the total number of standard point cloud data in each of the second voxels; Multiplying each of the total number of data by the volume of the second voxel corresponding to the total number of data to obtain a plurality of second voxel volumes; Performing weighted summation on a plurality of the second voxel volumes to obtain a preset material volume; The maximum height and the preset material volume are summarized as a target feature.

6. The method according to claim 5, characterized in that The step of supplementing the missing data points in the standard point cloud data according to the target features to obtain complete material data includes: Projecting a plurality of the second voxels onto a two-dimensional plane to obtain two-dimensional point cloud data; Identifying missing areas in the standard point cloud data according to the two-dimensional point cloud data; Obtaining a first coordinate of a preset laser radar sensor and a second coordinate in the standard point cloud data; Linear interpolation is performed on each missing point in the missing area one by one according to the first coordinate and the second coordinate to obtain complete material data.

7. A material scanning system based on laser radar, characterized in that: The system comprises: A coordinate conversion module is used to obtain three-dimensional point cloud data of a preset material, and to perform coordinate conversion on the three-dimensional point cloud data to obtain updated point cloud data; A data processing module, used for filtering the updated point cloud data to obtain standard point cloud data; A feature extraction module, used to extract target features of the standard point cloud data; The data supplement module is used to supplement the missing data points in the standard point cloud data according to the target features to obtain complete material data.

8. A computer device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 6.

9. A 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 method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images