Modeling method and system based on three-dimensional point cloud and processor

Abstract

The embodiment of the invention provides a modeling method and system based on three-dimensional point cloud and a processor, and belongs to the technical field of image modeling. The modeling method comprises the following steps: acquiring a plurality of groups of pictures containing point clouds of equipment in a transformer substation; the picture is preprocessed; after preprocessing, phase correlation correction is carried out on the picture; after the phase correlation is corrected, data about the point cloud in the picture is optimized; and generating a three-dimensional model according to the optimized data of the point cloud. According to the modeling method, three-dimensional modeling can be accurately carried out on the target.

Description

Technical Field

[0001] The present invention relates to the technical field of image modeling, and in particular to a modeling method, system and processor based on three-dimensional point cloud. Background Art

[0002] Substations are places in power systems that transform voltage and current, and receive and distribute electric energy. It mainly uses transformers and other equipment to reduce the high-voltage electric energy generated by power plants to a low voltage suitable for users, or to increase the low-voltage electric energy to a high voltage suitable for long-distance transmission. In addition, substations are also responsible for receiving, distributing and controlling electric energy to ensure the safe, stable and efficient operation of the power system. The development of substations is closely linked to the progress of power systems. In the early days, substations mainly used air as an insulating medium and had a relatively simple structure. However, with the increase in power demand and technological progress, substations gradually introduced more advanced technologies and equipment. For example, the application of gas-insulated metal-enclosed switchgear (GIS) makes substations more compact, safe and easy to maintain. At the same time, the introduction of intelligent technology has also made the operation of substations more automated and intelligent, improving operational efficiency and reliability. Due to the importance of substations, modeling substation equipment is an important task, but the existing three-dimensional modeling has low modeling accuracy, so a modeling method that can accurately model the target object is needed. Summary of the invention

[0003] The purpose of the embodiments of the present invention is to provide a modeling method, system and processor based on three-dimensional point cloud, which can accurately perform three-dimensional modeling on the target.

[0004] In order to achieve the above object, an embodiment of the present invention provides a modeling method based on a three-dimensional point cloud, the modeling method comprising: Get multiple sets of pictures containing point clouds of equipment in the substation; Preprocessing the image; After preprocessing, the image is subjected to phase correlation correction; After phase correlation correction, optimizing the data on the point cloud in the image; Generate a 3D model based on the optimized point cloud data.

[0005] Optionally, the point cloud is acquired by scanning with a terrestrial laser scanner or an airborne laser scanner.

[0006] Optionally, the image is further preprocessed, including: Get multiple sets of pictures containing point clouds of equipment in the substation; Obtaining a point cloud in the image; Obtain the position of the point cloud, and divide the image containing all the point clouds into multiple small blocks; Calculate the number of point clouds in each patch divided by the space it occupies; Remove the point clouds in small blocks whose results are smaller than a preset threshold.

[0007] Optionally, after preprocessing, the image is subjected to phase correlation correction, including: Get the preprocessed image containing the point cloud; Performing Fourier transform on the image to extract phase information of the image; Select one of the pictures, and calculate the phase difference between the remaining pictures and the selected picture; According to the calculation of the phase difference, the remaining images are translated, rotated or scaled so as to be aligned with the selected image.

[0008] Optionally, after the phase correlation correction, the data on the point cloud in the image is optimized, including: Get the registered image; Acquire data about a point cloud in the image, and divide the point cloud in the image into a plurality of regions; Select a point cloud area in one image and match the corresponding point cloud area in the remaining images; The regions of the matched point clouds in the multiple images are intersected to obtain a certain point cloud region; All the determined point cloud areas are merged to obtain a determined point cloud image.

[0009] Optionally, a 3D model is generated based on the optimized point cloud data, including: Get the confirmed point cloud image; voxelize the point cloud in the determined point cloud image to convert it into voxels; Based on the voxels, a surface reconstruction algorithm is performed to obtain a surface representation of the object; After obtaining the surface representation of the object, it is smoothed and optimized to obtain a three-dimensional model.

[0010] On the other hand, the present invention also provides a modeling system based on three-dimensional point cloud, the system comprising: LiDAR camera, to obtain images of the target; The background computing module is connected to the laser radar camera to obtain the image and execute a three-dimensional point cloud-based modeling method as described above.

[0011] On the other hand, the present invention further provides a processor for running a program, wherein the program, when being run, is used to execute a three-dimensional point cloud-based modeling method as described above.

[0012] Through the above technical solution, the present invention provides a modeling method, system and processor based on three-dimensional point cloud, which obtains multiple groups of pictures containing point clouds of equipment in the substation, and can pre-process the pictures. After the pre-processing is completed, the pictures can be phase-correlation corrected. After the phase-correlation correction is completed, the data about the point cloud in the picture can be optimized. After the optimization is completed, a three-dimensional model can be generated based on the optimized point cloud data. This modeling method can accurately perform three-dimensional modeling on the target.

[0013] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings: Figure 1 is a flow chart of a modeling method based on three-dimensional point cloud according to one embodiment of the present invention; Figure 2 is a flowchart of preprocessing of a modeling method based on three-dimensional point cloud according to one embodiment of the present invention; Figure 3 is a flow chart of a registration of a modeling method based on a three-dimensional point cloud according to an embodiment of the present invention; Figure 4 is a flow chart of point cloud screening of a modeling method based on three-dimensional point cloud according to one embodiment of the present invention; Figure 5 is a flow chart of generating a three-dimensional model according to a three-dimensional point cloud-based modeling method according to an embodiment of the present invention; Figure 6 This is a picture of a point cloud of a substation. DETAILED DESCRIPTION

[0015] The specific implementation of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiment of the present invention, and is not used to limit the embodiment of the present invention.

[0016] Figure 1 1 is a flow chart of a modeling method based on a three-dimensional point cloud according to an embodiment of the present invention. In the present invention, the process of the three-dimensional modeling method may include: In step S1, multiple groups of pictures containing point clouds of equipment in the substation are obtained.

[0017] In step S2, the picture is preprocessed.

[0018] In step S3, after pre-processing, the image is subjected to phase correlation correction.

[0019] In step S4, after the phase correlation correction, the data on the point cloud in the image is optimized.

[0020] In step S5, a three-dimensional model is generated based on the optimized point cloud data.

[0021] In the present invention, when three-dimensional modeling of the target is performed, multiple groups of pictures containing point clouds of the equipment in the substation can be obtained, such as Figure 6 As shown, the image can be preprocessed, and after the preprocessing is completed, the image can be subjected to phase correlation correction. After the phase correlation correction is completed, the data about the point cloud in the image can be optimized. After the optimization is completed, a three-dimensional model can be generated according to the optimized point cloud data. This modeling method can accurately perform three-dimensional modeling on the target.

[0022] In one embodiment of the present invention, the point cloud can be acquired by scanning with a terrestrial laser scanner or an airborne laser scanner.

[0023] In one embodiment of the present invention, Figure 2 As shown, the process of preprocessing the image may include: In step S6, multiple groups of pictures containing point clouds of equipment in the substation are obtained.

[0024] In step S7, the point cloud in the image is obtained.

[0025] In step S8, the position of the point cloud is obtained, and the image containing all the point clouds is divided into multiple small blocks.

[0026] In step S9, the result of dividing the number of point clouds in each small block by the space it occupies is calculated.

[0027] In step S10, point clouds in small blocks whose results are smaller than a preset threshold are removed.

[0028] In the present invention, after obtaining multiple pictures of the target, the pictures can be preprocessed to obtain a more streamlined point cloud image. During preprocessing, multiple groups of pictures containing point clouds of the equipment in the substation can be obtained first, and then the point clouds in the pictures can be obtained. After obtaining the point cloud, the position of the point cloud can be obtained, and the picture containing all the point clouds can be divided into multiple small blocks, and then the number of point clouds in each small block is divided by the space they occupy to obtain the average number of point clouds. After obtaining the result of dividing the number of point clouds by the space they occupy, that is, the average number of point clouds, the point clouds in the small blocks whose average number of point clouds is less than a preset threshold can be removed. At this time, the point cloud may be a flying point, so it can be removed to avoid affecting subsequent modeling calculations.

[0029] In one embodiment of the present invention, Figure 3 As shown, the registration process may include: In step S11, a pre-processed image containing a point cloud is obtained.

[0030] In step S12, Fourier transform is performed on the image to extract phase information of the image.

[0031] In step S13, a picture is selected, and the phase differences between the remaining pictures and the selected picture are calculated.

[0032] In step S14, according to the calculated phase difference, the remaining pictures are translated, rotated or scaled so as to be aligned with the selected picture.

[0033] In the present invention, after processing the pictures containing the point cloud, the multiple pictures can be registered. During the registration, the pictures can be Fourier transformed so that the phase information of the pictures can be extracted. Then, one picture can be selected, and the phase difference between the remaining pictures and the selected picture can be calculated, and the multiple pictures can be registered according to the phase difference.

[0034] In one embodiment of the present invention, Figure 4 As shown, the process of point cloud screening may include: In step S15, the registered image is obtained.

[0035] In step S16, data about the point cloud in the image is obtained, and the point cloud in the image is divided into multiple areas.

[0036] In step S17, a point cloud region in one image is selected, and corresponding point cloud regions are matched in the remaining images.

[0037] In step S18, the intersection of the matching point cloud regions in the multiple images is performed to obtain a determined point cloud region.

[0038] In step S19, all determined point cloud regions are merged to obtain a determined point cloud image.

[0039] In the present invention, after obtaining the registered image, the data about the point cloud in the image can be obtained, and then the point cloud in the image can be divided into multiple regions. A point cloud region in one image is selected, and then the corresponding point cloud region can be matched in the remaining images. After the matching is completed, the matching point cloud regions in multiple images can be intersected to obtain a determined point cloud region, and then all the determined point cloud regions can be merged to obtain a determined point cloud image, which can be the final point cloud image after processing.

[0040] In one embodiment of the present invention, Figure 5 As shown, the process of generating a three-dimensional model may include: In step S20, a point cloud image is obtained.

[0041] In step S21 , the point cloud in the determined point cloud image is voxelized to be converted into voxels.

[0042] In step S22 , a surface reconstruction algorithm is performed based on the voxels to obtain a surface representation of the object.

[0043] In step S23, after obtaining the surface representation of the object, it is smoothed and optimized to obtain the final three-dimensional model.

[0044] In the present invention, after obtaining a certain point cloud image, the point cloud in the certain point cloud image can be voxelized into voxels. After obtaining the voxels, a surface reconstruction algorithm can be executed according to the voxels to obtain the surface of the object. After obtaining the surface of the object, it can be smoothed and optimized to obtain the final three-dimensional model.

[0045] On the other hand, the present invention also provides a modeling system based on a three-dimensional point cloud, the system comprising: a point cloud acquisition module and a background operation module. The point cloud acquisition module acquires a picture of a target. The background operation module is connected to the point cloud acquisition module to acquire the picture and execute a modeling method based on a three-dimensional point cloud as described above.

[0046] On the other hand, the present invention further provides a processor for running a program, wherein the program, when being run, is used to execute a three-dimensional point cloud-based modeling method as described above.

[0047] Through the above technical solution, the present invention provides a modeling method, system and processor based on three-dimensional point cloud, which obtains multiple groups of pictures containing point clouds of equipment in the substation, and can pre-process the pictures. After the pre-processing is completed, the pictures can be phase-correlation corrected. After the phase-correlation correction is completed, the data about the point cloud in the picture can be optimized. After the optimization is completed, a three-dimensional model can be generated based on the optimized point cloud data. This modeling method can accurately perform three-dimensional modeling on the target.

[0048] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0049] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0050] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0051] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0052] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0053] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0054] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0055] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity 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, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0056] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A modeling method based on three-dimensional point cloud, characterized in that: The modeling method comprises: Get multiple sets of pictures containing point clouds of equipment in the substation; Preprocessing the image; After preprocessing, the image is subjected to phase correlation correction; After phase correlation correction, optimizing the data on the point cloud in the image; Generate a 3D model based on the optimized point cloud data.

2. The modeling method according to claim 1, characterized in that: The point cloud is obtained by scanning with a ground laser scanner or an airborne laser scanner.

3. The modeling method according to claim 1, characterized in that: The image is further preprocessed, including: Get multiple sets of pictures containing point clouds of equipment in the substation; Obtaining a point cloud in the image; Obtain the position of the point cloud, and divide the image containing all the point clouds into multiple small blocks; Calculate the number of point clouds in each patch divided by the space it occupies; Remove the point clouds in small blocks whose results are smaller than a preset threshold.

4. The modeling method according to claim 1, characterized in that: After preprocessing, the image is subjected to phase correlation correction, including: Get the preprocessed image containing the point cloud; Performing Fourier transform on the image to extract phase information of the image; Select one of the pictures, and calculate the phase difference between the remaining pictures and the selected picture; According to the calculation of the phase difference, the remaining images are translated, rotated or scaled so as to be aligned with the selected image.

5. The modeling method according to claim 4, characterized in that: After the phase correlation correction, the data on the point cloud in the image is optimized, including: Get the registered image; Acquire data about a point cloud in the image, and divide the point cloud in the image into a plurality of regions; Select a point cloud area in one image and match the corresponding point cloud area in the remaining images; The regions of the matched point clouds in the multiple images are intersected to obtain a certain point cloud region; All the determined point cloud areas are merged to obtain a determined point cloud image.

6. The modeling method according to claim 5, characterized in that: Generate a 3D model based on the optimized point cloud data, including: Get the confirmed point cloud image; voxelize the point cloud in the determined point cloud image to convert it into voxels; Based on the voxels, a surface reconstruction algorithm is performed to obtain a surface representation of the object; After obtaining the surface representation of the object, it is smoothed and optimized to obtain a three-dimensional model.

7. A modeling system based on three-dimensional point cloud, characterized in that: The system comprises: LiDAR camera, to obtain images of the target; A background computing module is connected to the laser radar camera to obtain the image and execute a three-dimensional point cloud-based modeling method as described in any one of claims 1-6.

8. A processor, characterized in that: Used to run a program, wherein the program, when run, is used to execute a three-dimensional point cloud-based modeling method as described in any one of claims 1-6.

Images