Point cloud classification result checking method, electronic device, and storage medium

Abstract

The application provides a point cloud classification result checking method, an electronic device and a storage medium. The method comprises the following steps: S10: acquiring a point cloud classification result, and respectively extracting point cloud data of a building layer, a vegetation layer and a ground layer according to layers; S20: selecting a target building point in the building layer, and constructing a dimension range; S30: grouping all points in the vegetation layer and the ground layer based on the dimension range, and outputting selected data in the dimension range; S40: setting an elevation threshold, and filtering an elevation difference between the selected data and the target building point based on the elevation threshold, and classifying points lower than the elevation threshold to the building layer; and S50: repeating S20 to S40 until all points in the building layer are processed. The point cloud classification result checking method has the beneficial effect of improving classification accuracy by constructing a dimension range with the points in the building layer as the center and setting an elevation threshold to filter the points in the vegetation layer and the ground layer.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method for checking point cloud classification results, an electronic device, and a storage medium. Background Technology

[0002] LiDAR point cloud data is a dataset of spatial points obtained by 3D LiDAR equipment scanning, characterized by its discreteness and massive volume. Point cloud classification assigns a semantic label to each point, categorizing the point cloud into different point cloud layers. Data within the same point cloud layer share similar or identical attributes.

[0003] Point cloud classification includes coarse classification and fine classification. Coarse classification uses existing macro commands in relevant software, such as Terrasolid and Lastools, to classify isolated points and nearest neighbors. Fine classification, also known as manual interactive classification, uses methods such as manual reference images and TIN models to check and classify the point cloud data after coarse classification, and to reclassify points that were not classified in the coarse classification. The results of point cloud classification are widely used in the creation of digital elevation models, geological disaster monitoring, and 3D modeling.

[0004] However, in actual operation, due to the high level of professional knowledge required for detailed classification, the classification results often vary among different operators. For example, the classification of building layers may be incomplete, and some classifications may still contain data for vegetation layers or ground layers, resulting in insufficient accuracy, low work efficiency, and the need for repeated verification. Summary of the Invention

[0005] In view of the above, this application proposes a method, electronic device and storage medium for checking point cloud classification results, in order to solve the above problems.

[0006] This application provides a method for checking point cloud classification results, including the following steps:

[0007] S10: Obtain the point cloud classification results and extract the point cloud data of the building layer, vegetation layer and ground layer respectively;

[0008] S20: Select a target building point in the building layer and construct the dimensional range;

[0009] S30: Based on the dimensional range, group all points of the vegetation layer and the ground layer, and output the candidate data within the dimensional range;

[0010] S40: Set an elevation threshold, and filter the elevation difference between the candidate data and the target building point based on the elevation threshold, and classify the points below the elevation threshold to the building layer;

[0011] S50: Repeat S20 to S40 until all points of the building layer have been processed.

[0012] In at least one embodiment, step S20 further includes:

[0013] Set the radius, and construct the dimensional range of the circle with the target building point as the center.

[0014] In at least one embodiment, step S30 further includes:

[0015] S31: Determine whether all points of the vegetation layer and the ground layer are within the dimensional range, and classify the points that are yes into the group corresponding to the target building point, and regard them as the candidate data.

[0016] In at least one embodiment, step S31 further includes:

[0017] The point Q in the vegetation layer and the ground layer is output by the following formula. m With the target building point P n Distance value d i :

[0018]

[0019] Where, x n y n For the target building point P n The coordinates, x m y m Point Q is the junction of the vegetation layer and the ground layer. m The coordinates are given, where n is the index of the target building point and m is the index of the midpoint between the vegetation layer and the ground layer.

[0020] In at least one embodiment, step S40 further includes:

[0021] Set the elevation threshold H, and output the elevation difference h using the following formula. i To filter all points in the candidate data:

[0022] h i =±(h) n -h m (2)

[0023] Among them, h n For the target building point P n Elevation value, h m For point Q in the candidate data m The elevation value.

[0024] In at least one embodiment, step S40 further includes:

[0025] Points in the candidate data whose elevation difference from the target building point is greater than the elevation threshold are retained in the vegetation layer and the ground layer.

[0026] In at least one embodiment, step S50 further includes:

[0027] Output the point cloud classification results after updating the data.

[0028] In at least one embodiment, step S10 further includes:

[0029] The point cloud classification results are point cloud data that have undergone manual interactive processing.

[0030] This application also proposes an electronic device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the point cloud classification result inspection method described above.

[0031] This application also proposes a computer-readable storage medium, which includes a stored computer program, wherein the computer program, when running, controls the device where the computer-readable storage medium is located to perform the point cloud classification result inspection method as described above.

[0032] Compared with existing technologies, the point cloud classification result inspection method proposed in this application filters points in the vegetation layer and ground layer by constructing a dimensional range with the points in the building layer as the center and setting an elevation threshold, thereby further improving the accuracy of the point cloud classification results. It has the beneficial effects of improving accuracy and efficiency. Attached Figure Description

[0033] Figure 1 This is a flowchart illustrating the steps of an embodiment of the point cloud classification result inspection method in this application;

[0034] Figure 2 yes Figure 1 The diagram illustrates the dimensional range in the method for checking point cloud classification results. Detailed Implementation

[0035] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without inventive effort are within the scope of protection of this invention.

[0036] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," and "counterclockwise," etc., indicating orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. 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 indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of the stated features. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0037] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection, an electrical connection, or a connection that allows for communication; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0038] In this invention, unless otherwise explicitly specified and limited, "above" or "below" the second feature can include direct contact between the first and second features, or contact between the first and second features through another feature between them. Furthermore, "above," "over," and "on top" of the second feature includes the first feature being directly above or diagonally above the second feature, or simply indicates that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature includes the first feature being directly above or diagonally above the second feature, or simply indicates that the first feature is at a lower horizontal level than the second feature.

[0039] The following disclosure provides many different embodiments or examples for implementing various structures of the invention. To simplify the disclosure, specific examples of components and arrangements are described below. These are merely examples and are not intended to limit the invention. Furthermore, reference numerals and / or letters may be repeated in different examples; such repetition is for simplification and clarity and does not in itself indicate a relationship between the various embodiments and / or arrangements discussed. In addition, examples of various specific processes and materials are provided in this invention, but those skilled in the art will recognize the application of other processes and / or the use of other materials.

[0040] Please see Figure 1 This application proposes an automatic inspection method for point cloud classification results, comprising the following steps:

[0041] S10: Obtain the point cloud classification results and extract the point cloud data of the building layer, vegetation layer and ground layer respectively;

[0042] S20: Select a target building point in the building layer and construct the dimensional range;

[0043] S30: Based on the dimensional range, group all points in the vegetation layer and ground layer, and output the candidate data within the dimensional range;

[0044] S40: Set an elevation threshold and filter the elevation difference between the candidate data and the target building point based on the elevation threshold, and classify the points below the elevation threshold to the building level.

[0045] S50: Repeat S20 to S40 until all points on the building layer have been processed.

[0046] It should be explained that in step S10, the point cloud classification result is the result of automatic classification (coarse classification) of the point cloud data using existing software such as Terrasolid and Lastools, followed by further classification (fine classification) through manual interaction. In this embodiment, the data points in the point cloud classification result are all located within the building layer (class-6), vegetation layer (class-3), and ground layer (class-2). Point data in the building layer are also called building points, point data in the vegetation layer are also called vegetation points, and points in the ground layer are also called ground points. Point data classified into the same layer set have similar or identical attributes. Because the fine classification process is easily affected by the subjective influence of the operator, the point cloud classification result may have accuracy errors, that is, some points that should fall into the building layer are misclassified into the vegetation layer or the ground layer. Therefore, the purpose of this embodiment is to filter these points and output more accurate classification results. The classification result is data in LAS format, which includes the general attribute of layer set (class), and the naming of each layer set is also universal.

[0047] In step S20, the selection of building points can be regular or random, with the goal of eventually traversing all building points. This embodiment does not impose any restrictions on the selection of building points.

[0048] In step S30, all vegetation points and ground points are filtered by dimensional range.

[0049] In step S40, by setting an elevation threshold, the remaining vegetation points and ground points are further screened to complete one round of operation.

[0050] In step S50, for points that have been classified into building layers after being processed by steps S20 to S40, the above processing is not performed, that is, the results are not used as conditions for nested processing.

[0051] Please see Figure 2 In one embodiment, step S20 further includes:

[0052] Set the radius D, and use the target building point P as the reference. n Using the circle as its center, construct the dimensional range of the circle. The choice of radius D can be determined based on actual parameters, and the selection of radius D directly affects the screening accuracy of this embodiment.

[0053] In one embodiment, step S30 further includes:

[0054] S31: Determine whether all points in the vegetation layer and ground layer are within the dimension range, and classify the points that are within the dimension range to the target building point P. n Corresponding group G n In the middle, it is considered as candidate data.

[0055] All vegetation points and all ground points are filtered by dimensional range. Points falling within the dimensional range are selected as candidate data and assigned a group G. n Attributes. Group G n It is related to the target building point P n According to the attributes corresponding to the sequence number n. After this step, each target building point P n Each is associated with a corresponding group G n Each group G n This includes all points located at point P. n Vegetation points and ground points Q within the dimensional range m .

[0056] In one embodiment, step S31 further includes:

[0057] The point Q in the vegetation layer and the ground layer is output by the following formula. m With the target building point P n Distance value di :

[0058]

[0059] Where, x n y n For the target building point P n The coordinates, x m y m Point Q is the junction of the vegetation layer and the ground layer. m The coordinates are given, where n is the index of the target building point, and m is the index of the midpoint between the vegetation layer and the ground layer. The distance d is compared... i Determine the value of radius D to determine point Q. m Whether it falls within the dimensional range. When the distance d i If the radius is less than D, then determine point Q. m It falls within the dimensional range and is assigned to the target building point P. n Corresponding group G n Inside.

[0060] In one embodiment, step S40 further includes:

[0061] Set the elevation threshold H, and output the elevation difference h using the following formula. i To filter all points in the candidate data:

[0062] h i =±(h) n -h m (2)

[0063] Among them, h n For the target building point P n Elevation value, h m For point Q in the candidate data m The elevation value. By comparing the elevation difference h... i The data to be selected is filtered based on the elevation threshold H. If the elevation difference h is satisfied... i If the elevation is less than the elevation threshold H, then point Q is... m It was moved from its original location to a floor within the building.

[0064] In one embodiment, step S40 further includes:

[0065] Select the data from the candidate data and match the target building point P. n elevation difference h i Point Q above the elevation threshold H m It is retained in the vegetation layer and ground layer.

[0066] For the elevation difference h i Point Q above the elevation threshold H mIt can be considered as a point that was correctly classified earlier, so it is retained in its original position.

[0067] In one embodiment, step S50 further includes:

[0068] Output the point cloud classification results after updating the data.

[0069] After filtering through the above embodiments, the data is adjusted based on the results, and the adjusted data is output as a new classification result according to the building layer, vegetation layer and ground layer.

[0070] In one embodiment, step S10 further includes:

[0071] The point cloud classification results are point cloud data that have undergone manual interactive processing.

[0072] This application also proposes an electronic device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the above-mentioned method for checking point cloud classification results.

[0073] The electronic device may be a desktop computer, laptop, handheld computer, or smart tablet, etc. The electronic device may include, but is not limited to, a processor and memory. Those skilled in the art will understand that the above components are merely examples of electronic devices and do not constitute a limitation on the electronic device. It may include more or fewer components than described above, or combine certain components, or different components. For example, the electronic device may also include input / output devices, network access devices, buses, etc.

[0074] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the terminal device, connecting all parts of the terminal device via various interfaces and lines.

[0075] The memory can be used to store the computer programs and / or modules. The processor implements various functions of the terminal device by running or executing the computer programs and / or modules stored in the memory and by calling data stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, phonebook, etc.). In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0076] This application also proposes a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, it controls the device where the computer-readable storage medium is located to perform the above-described method for checking point cloud classification results.

[0077] Specifically, a system or apparatus equipped with a storage medium may be provided, on which software program code implementing the functions of any of the above embodiments is stored, and the electronic device of the system or apparatus may read and execute the program code stored in the storage medium.

[0078] In this case, the program code read from the storage medium can itself implement the function of any of the above embodiments, and therefore the program code and the storage medium storing the program code constitute a part of this specification.

[0079] Examples of storage media used to provide program code include floppy disks, hard disks, magneto-optical disks, optical disks (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW), magnetic tapes, non-volatile memory cards, and ROMs. Optionally, it may also include downloading program code from a server computer via a communication network.

[0080] Furthermore, it should be clear that not only can the program code read by the computer be executed, but also the operating system or other components operating on the computer can be instructed based on the program code to perform some or all of the actual operations, thereby realizing the function of any of the embodiments described above.

[0081] Furthermore, it is understood that the program code read from the storage medium is written to the memory set in the expansion board inserted into the computer or to the memory set in the expansion module connected to the computer. Then, based on the instructions of the program code, the CPU or other components installed on the expansion board or expansion module execute some and all of the actual operations, thereby realizing the function of any of the above embodiments.

[0082] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, it is intended that all variations falling within the meaning and scope of equivalents of the claims be incorporated into the present invention.

[0083] The above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for checking point cloud classification results, characterized in that, Includes the following steps: S10: Obtain the point cloud classification results and extract the point cloud data of the building layer, vegetation layer and ground layer respectively; S20: Select a target building point in the building layer, set the radius, and construct the dimensional range of a circle with the target building point as the center; S30: Based on the dimensional range, group all points of the vegetation layer and the ground layer, and output the candidate data within the dimensional range; S40: Set an elevation threshold, and filter the elevation difference between the candidate data and the target building point based on the elevation threshold, and classify the points below the elevation threshold to the building layer; S50: Repeat S20 to S40 until all points of the building layer have been processed; Step S30 further includes: S31: Determine whether all points of the vegetation layer and the ground layer are within the dimensional range, and classify the points that are yes into the group corresponding to the target building point, and regard them as the candidate data.

2. The method for checking point cloud classification results as described in claim 1, characterized in that, Step S31 further includes: The points in the vegetation layer and the ground layer are output by the following formula. Q m With the target building point P n Distance value d i : （1） in, , For the target building point P n coordinates , Points between vegetation layer and ground layer Q m coordinates n The serial number of the target building point. m This is the serial number of the midpoint between the vegetation layer and the ground layer.

3. The method for checking point cloud classification results as described in claim 1, characterized in that, Step S40 further includes: Set elevation threshold H The elevation difference is output using the following formula. h i To filter all points in the candidate data: （2） in, h n For the target building point P n Elevation value, h m Points in the candidate data Q m The elevation value.

4. The method for checking point cloud classification results as described in claim 1, characterized in that, Step S40 further includes: Points in the candidate data whose elevation difference from the target building point is greater than the elevation threshold are retained in the vegetation layer and the ground layer.

5. The method for checking point cloud classification results as described in claim 1, characterized in that, Step S50 further includes: Output the point cloud classification results after updating the data.

6. The method for checking point cloud classification results as described in claim 1, characterized in that, Step S10 further includes: The point cloud classification results are point cloud data that have undergone manual interactive processing.

7. An electronic device, characterized in that, The device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method for checking point cloud classification results as described in any one of claims 1 to 6.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, it controls the device on which the computer-readable storage medium is located to perform a method for checking point cloud classification results as described in any one of claims 1 to 6.

Images