A method and system for identifying and locating substation equipment
By obtaining the left and right views of the substation equipment for feature extraction and pyramid matching model processing, the problem of inaccurate positioning of fire robots in the substation is solved, and accurate equipment identification and positioning is achieved.
Patent Information
- Application Number
- CN202411656728.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-19
- Publication Date
- 2025-04-04
AI Technical Summary
Existing firefighting robots are inaccurate when identifying targets in substations, making it difficult to achieve accurate identification and positioning.
By obtaining the left and right views of the device in the substation, feature extraction is performed, feature maps are obtained, and sent to the pyramid matching model, the fusion matching feature map is obtained, and the device positioning is determined by the disparity value.
It realizes accurate identification and positioning of substation equipment, and improves the operation accuracy of firefighting robots in substations.
Smart Images
Figure CN119762580A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of target identification, and in particular to a method and system for identifying and locating substation equipment. Background Art
[0002] A substation is a device used to convert high-voltage electricity into low-voltage electricity, and is usually used in power systems in cities or industrial areas. Substations are mainly used for the transmission and distribution of electric energy, and can convert electricity from high-voltage transmission lines to low voltage for access to different areas of electricity consumption. Firefighting in substations is an important matter. Due to the special circumstances of substations, conventional fire-fighting equipment cannot be used, and the staff also need to take great risks when extinguishing fires. Therefore, some substations are equipped with firefighting robots, which can identify fire situations and move to the vicinity of the fire point to extinguish fires. However, existing firefighting robots have defects in image recognition, and sometimes they are not accurate in positioning when identifying targets. Therefore, a substation equipment identification and positioning method is needed to accurately identify and locate targets. Summary of the invention
[0003] The purpose of the embodiments of the present invention is to provide a method and system for identifying and locating substation equipment, which can accurately identify and locate a target.
[0004] In order to achieve the above object, an embodiment of the present invention provides a substation equipment identification and positioning method, the identification and positioning method comprising: Get left and right views of equipment in a substation; Extracting features from the left and right views of the substation to obtain corresponding feature maps; The feature map is sent into the pyramid matching model, so as to obtain the corresponding fused matching feature map; The corresponding disparity value is obtained through the fusion matching feature map, and the location of the equipment in the substation is determined according to the disparity value.
[0005] Optionally, left and right views of the equipment in the substation are acquired through a binocular camera.
[0006] Optionally, the feature map is fed into a pyramid matching model, so as to obtain a corresponding fused matching feature map, including: Obtaining characteristic graphs of left and right views in the substation; Dividing the feature maps of the left and right views into a plurality of blocks, each of which has the same size; Selecting blocks in one of the feature maps of the left and right views one by one, and comparing it with all blocks in the other feature map; A block having the greatest similarity to the selected block is selected from another feature map and matched.
[0007] Optionally, the feature map is fed into a pyramid matching model, so as to obtain a corresponding fused matching feature map, including: Obtaining feature maps of the left and right views after matching; Downsampling the feature maps of the left and right views, so as to obtain a size feature map of each level; Extracting features from the size feature map; The size feature map obtained after feature extraction is fused according to the corresponding matching blocks to obtain a fused matching feature map.
[0008] Optionally, the feature map is fed into a pyramid matching model, so as to obtain a corresponding fused matching feature map, including: Obtain the feature map of each level after fusion based on matching; Assign different weights to the fused feature maps at each level; According to the weight corresponding to each level, the feature map of each level is multiplied by the corresponding weight and then added to obtain the fused matching feature map.
[0009] Optionally, obtaining a corresponding disparity value through the fused matching feature map, and determining the location of the equipment in the substation according to the disparity value includes: Acquire the fusion matching feature map; According to the fused matching feature map, obtaining each pixel in the fused matching feature map; The grayscale value of the pixel is obtained, and a corresponding disparity value is calculated according to the grayscale value, and the location of the device in the substation is determined according to the disparity value.
[0010] On the other hand, the present invention also provides a substation equipment identification and positioning system, the identification and positioning system comprising: An image acquisition module, which acquires left and right views of substation equipment; A computing module is provided for acquiring the left and right views and executing a method for identifying and locating substation equipment as described in any one of claims 1 to 6.
[0011] Through the above technical solution, the present invention provides a substation equipment identification and positioning method and system, which can obtain left and right views of the equipment in the substation, and then extract features from the left and right views in the substation, so as to obtain a corresponding feature map. After obtaining the feature map, the feature map can be sent to the pyramid matching model, so as to obtain a corresponding fused matching feature map. After obtaining the fused matching feature map, the corresponding disparity value can be obtained through the fused matching feature map, and then the positioning of the equipment in the substation can be determined according to the disparity value. This identification and positioning method can accurately identify and locate the target.
[0012] 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
[0013] 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 method for identifying and locating substation equipment according to an embodiment of the present invention; Figure 2 A first flow chart of obtaining a fusion matching feature map of a method for identifying and locating substation equipment according to an embodiment of the present invention; Figure 3 A second flow chart of obtaining a fusion matching feature map of a method for identifying and locating substation equipment according to an embodiment of the present invention; Figure 4 A third flow chart of obtaining a fusion matching feature map of a method for identifying and locating substation equipment according to an embodiment of the present invention; Figure 5 The present invention is a flowchart of obtaining a disparity value in a method for identifying and locating substation equipment according to an embodiment of the present invention. DETAILED DESCRIPTION
[0014] 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.
[0015] Figure 1 1 is a flow chart of a method for identifying and locating substation equipment according to an embodiment of the present invention. In the present invention, the process of the identification and locating method may include: In step S1 , left and right views of equipment are acquired in a substation.
[0016] In step S2, feature extraction is performed on the left and right views in the substation to obtain corresponding feature maps.
[0017] In step S3, the feature map is fed into the pyramid matching model, so that the corresponding fused matching feature map can be obtained.
[0018] In step S4, the corresponding disparity value is obtained by fusing the matching feature map, and the location of the equipment in the substation is determined according to the disparity value.
[0019] In the present invention, when positioning the equipment in the substation, the left and right views of the equipment can be obtained in the substation, and then the left and right views in the substation can be feature extracted, so that the corresponding feature map can be obtained. After the feature map is obtained, the feature map can be sent to the pyramid matching model, so that the corresponding fused matching feature map can be obtained. After the fused matching feature map is obtained, the corresponding disparity value can be obtained through the fused matching feature map, and then the positioning of the equipment in the substation can be determined according to the disparity value. The recognition and positioning method can accurately identify and locate the target.
[0020] In the present invention, the left and right views of the equipment in the substation can be obtained by a binocular camera.
[0021] In one embodiment of the present invention, Figure 2 As shown, the first process of obtaining the fused matching feature map may include: In step S5, characteristic graphs of the left and right views in the substation are obtained.
[0022] In step S6, the feature maps of the left and right views are divided into a plurality of blocks, and each block has the same size.
[0023] In step S7, blocks in one of the feature maps of the left and right views are selected one by one, and compared with all blocks in the other feature map.
[0024] In step S8, a block having the greatest similarity to the selected block is selected from another feature map and matched.
[0025] In the present invention, after obtaining the feature graphs of the left and right views of the equipment in the substation, the feature graphs of the left and right views can be divided into a plurality of blocks. When dividing the blocks, the size of each block can be the same, so that subsequent matching can be facilitated. After the division is completed, the blocks in one of the two feature graphs in the left and right views can be selected one by one, and then compared with all the blocks in the other feature graph. During the comparison process, the similarity of the comparison can be defined, and then the block in the other feature graph with the greatest similarity to the selected block can be selected, so that the blocks in the two feature graphs can be matched. The matching can be a preliminary matching of the left and right features.
[0026] In one embodiment of the present invention, Figure 3 As shown, the second process of obtaining the fused matching feature map may include: In step S9, the feature maps of the matched left and right views are obtained.
[0027] In step S10, the feature maps of the left and right views are downsampled, so that the size feature map of each level can be obtained.
[0028] In step S11, a size feature map of each level is obtained.
[0029] In step S12, the size feature map is fused according to the corresponding matching blocks to obtain a fused matching feature map.
[0030] In the present invention, after completing the preliminary matching, the feature maps of the matched left and right views can be obtained, and then the feature maps of the left and right views are downsampled, so that the size feature map of each level can be obtained. After the size feature map is obtained, the size feature map can be fused according to the corresponding matching blocks, so that a fused matching feature map can be obtained.
[0031] In one embodiment of the present invention, Figure 4 As shown, the third process of obtaining the fused matching feature map may include: In step S13, the feature maps of each level are obtained after fusion based on matching.
[0032] In step S14, different weights are assigned to the fused feature maps at each level.
[0033] In step S15, according to the weight corresponding to each level, the feature map of each level is multiplied by the corresponding weight and then added to obtain a fused matching feature map.
[0034] In the present invention, after obtaining the feature map of each level after fusion according to the matching, different weights can be assigned to the fused feature map of each level, and then the feature map of each level can be multiplied and added with the corresponding weight according to the weight of each level, so as to obtain a fused matching feature map. The fused matching feature map can be the final feature map.
[0035] In one embodiment of the present invention, Figure 5 As shown, the process of obtaining the disparity value may include: In step S16, a fused matching feature map is obtained.
[0036] In step S17, each pixel in the fused matching feature map is obtained according to the fused matching feature map.
[0037] In step S18, the grayscale value of the pixel is obtained, and the corresponding disparity value is calculated according to the grayscale value, and the location of the equipment in the substation is determined according to the disparity value.
[0038] In the present invention, after obtaining the fused matching feature map, each pixel in the fused matching feature map can be obtained according to the fused matching feature map. The gray value of the pixel is obtained and the disparity can be calculated according to the gray value. The location of the equipment in the substation can be determined according to the disparity value.
[0039] On the other hand, the present invention also provides a substation equipment identification and positioning system, the identification and positioning system comprising: an image acquisition module and a calculation module. The image acquisition module is used to obtain left and right views of the substation. The calculation module can obtain the left and right views to execute a substation equipment identification and positioning method as described above.
[0040] Through the above technical solution, the present invention provides a substation equipment identification and positioning method and system, which can obtain left and right views of the equipment in the substation, and then extract features from the left and right views in the substation, so as to obtain a corresponding feature map. After obtaining the feature map, the feature map can be sent to the pyramid matching model, so as to obtain a corresponding fused matching feature map. After obtaining the fused matching feature map, the corresponding disparity value can be obtained through the fused matching feature map, and then the positioning of the equipment in the substation can be determined according to the disparity value. This identification and positioning method can accurately identify and locate the target.
[0041] 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.
[0042] 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.
[0043] 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 including 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.
[0044] 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 A step that specifies a function in one or more boxes.
[0045] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0046] 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.
[0047] 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.
[0048] 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.
[0049] 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 method for identifying and locating substation equipment, characterized in that: The identification and positioning method comprises: Get left and right views of equipment in a substation; Extracting features from the left and right views of the substation to obtain corresponding feature maps; The feature map is sent into the pyramid matching model, so as to obtain the corresponding fused matching feature map; The corresponding disparity value is obtained through the fusion matching feature map, and the location of the equipment in the substation is determined according to the disparity value.
2. The identification and positioning method according to claim 1, characterized in that: The left and right views of the equipment in the substation are obtained through a binocular camera.
3. The identification and positioning method according to claim 1, characterized in that: The feature map is sent to the pyramid matching model, so that the corresponding fused matching feature map can be obtained, including: Obtaining characteristic graphs of left and right views in the substation; Dividing the feature maps of the left and right views into a plurality of blocks, each of which has the same size; Selecting blocks in one of the feature maps of the left and right views one by one, and comparing it with all blocks in the other feature map; A block having the greatest similarity to the selected block is selected from another feature map and matched.
4. The identification and positioning method according to claim 3, characterized in that: The feature map is sent to the pyramid matching model, so that the corresponding fused matching feature map can be obtained, including: Obtaining feature maps of the left and right views after matching; Downsampling the feature maps of the left and right views, so as to obtain a size feature map of each level; Obtaining the size feature map of each level; The size feature map obtained after feature extraction is fused according to the corresponding matching blocks to obtain a fused matching feature map.
5. The identification and positioning method according to claim 4, characterized in that: The feature map is sent to the pyramid matching model, so that the corresponding fused matching feature map can be obtained, including: Obtain the feature map of each level after fusion based on matching; Assign different weights to the fused feature maps at each level; According to the weight corresponding to each level, the feature map of each level is multiplied by the corresponding weight and then added to obtain the fused matching feature map.
6. The identification and positioning method according to claim 5, characterized in that: Obtaining a corresponding disparity value through the fused matching feature map, and determining the location of the equipment in the substation according to the disparity value, including: Acquire the fusion matching feature map; According to the fused matching feature map, obtaining each pixel in the fused matching feature map; The grayscale value of the pixel is obtained, and a corresponding disparity value is calculated according to the grayscale value, and the location of the device in the substation is determined according to the disparity value.
7. A substation equipment identification and positioning system, characterized in that: The identification and positioning system comprises: An image acquisition module, which acquires left and right views of substation equipment; A computing module is provided for acquiring the left and right views and executing a method for identifying and locating substation equipment as described in any one of claims 1 to 6.