Power supply cable laying scene identification system
By designing a power supply cable laying scenario identification system, using convolutional neural network model and sequential processing technology, intelligently identifying the shortest physical distance between the power supply cable and the tram track, solving the problem that cannot be identified in the existing technology and achieving dangerous distances Reliable judgment of status.
Patent Information
- Application Number
- CN202410465095.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-04-18
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2044-04-18
AI Technical Summary
The prior art cannot intelligently identify the shortest physical distance between the power supply cable and the tram track based on visual data, resulting in the inability to perform a judgment on whether the shortest physical distance is in a dangerous distance that is less than the set spacing threshold.
Design a power supply cable laying scenario identification system, using a convolutional neural network model, based on the depth of field and coordinate values of pixel points of the imaging sub-image of the power supply cable and the tram track, combined with the sequential processing of the image data, intelligently identifying the between the two Minimum physical distance and send corresponding safety or red flags through the spacing alarm device.
Reliable intelligent identification of the shortest physical distance between the power supply cable and the tram track is realized, ensuring that it can be judged whether it is in a dangerous distance state that is less than the set spacing threshold, and improving safety.
Smart Images

Figure CN118314460B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of power supply cables, and in particular to a power supply cable laying scene identification system. Background Art
[0002] Artificial intelligence is an important part of the intelligent discipline. It attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a similar way to human intelligence. Research in this field includes robots, language recognition, image recognition, natural language processing and expert systems. Since the birth of artificial intelligence, the theory and technology have become increasingly mature, and the application field has continued to expand. It can be imagined that the technological products brought by artificial intelligence in the future will be the "container" of human wisdom. Artificial intelligence can simulate the information process of human consciousness and thinking. Artificial intelligence is not human intelligence, but it can think like humans and may also exceed human intelligence.
[0003] However, the popularity of artificial intelligence in the existing technology is still not widespread enough. For example, it is impossible to intelligently identify the shortest physical distance between the power supply cable and the tram track based on various visual data of the power supply cable and the tram track, resulting in the inability to perform intelligent judgment on whether the subsequent shortest physical distance is in a dangerous distance state less than the set distance threshold. Summary of the invention
[0004] In order to solve the technical problems in the related fields, the present invention provides a power supply cable laying scene identification system, which can apply a convolutional neural network model to intelligently identify the shortest physical distance between the power supply cable and the tram track based on the depth of field values corresponding to each pixel point of the imaging sub-image occupied by the power supply cable, the horizontal coordinate values and the vertical coordinate values corresponding to each pixel point of the imaging sub-image occupied by the power supply cable, the depth of field values corresponding to each pixel point of the imaging sub-image occupied by the tram track, the horizontal coordinate values and the vertical coordinate values corresponding to each pixel point of the imaging sub-image occupied by the tram track, and the total number of pixels occupied by sequentially processed images, thereby facilitating the subsequent judgment of whether the shortest physical distance is in a dangerous spacing state less than a set spacing threshold.
[0005] According to the present invention, a power supply cable laying scenario identification system is provided, the system comprising:
[0006] A content capture mechanism, used for performing a visual content capture operation facing a parallel laying scene of power supply cables and tram tracks, so as to obtain and output a corresponding laying scene picture;
[0007] A sequential processing mechanism, connected to the content capture mechanism and comprising a data interpolation device, a clarity processing device and a signal sharpening device, for sequentially performing nearest neighbor interpolation processing, geometric mean filtering processing and spatial differential method sharpening processing on the received laying scene pictures, so as to obtain and output a corresponding sequentially processed image;
[0008] A model building mechanism, for performing multiple learning actions on a convolutional neural network to obtain a convolutional neural network after completing the multiple learning actions and outputting the convolutional neural network model as a convolutional neural network model, wherein the number of learning actions of the convolutional neural network is monotonically positively correlated with the maximum noise amplitude of the sequentially processed images;
[0009] a signal identification device, connected to the model building mechanism and the sequential processing mechanism, respectively, for detecting the imaging sub-image occupied by the power supply cable in the sequential processing image based on the grayscale value range corresponding to the power supply cable, and obtaining the depth of field values corresponding to the pixel points of the imaging sub-image occupied by the power supply cable; detecting the imaging sub-image occupied by the tram track in the sequential processing image based on the grayscale value range corresponding to the tram track, and obtaining the depth of field values corresponding to the pixel points of the imaging sub-image occupied by the tram track; applying the convolutional neural network model based on the depth of field values corresponding to the pixel points of the imaging sub-image occupied by the power supply cable, the horizontal coordinate values and the vertical coordinate values corresponding to the pixel points of the imaging sub-image occupied by the power supply cable, the depth of field values corresponding to the pixel points of the imaging sub-image occupied by the tram track, the horizontal coordinate values and the vertical coordinate values corresponding to the pixel points of the imaging sub-image occupied by the tram track, and the total number of pixel points occupied by the sequential processing image to intelligently identify the shortest physical distance between the power supply cable and the tram track;
[0010] a spacing alarm device connected to the signal identification device, and configured to send out a dangerous spacing identification signal when the shortest physical distance between the power supply cable and the tram track intelligently identified by the signal identification device is less than a set spacing threshold;
[0011] The distance alarm device is also used to send a safe distance identification signal when the shortest physical distance between the power supply cable and the tram track intelligently identified by the signal identification device is greater than or equal to the set distance threshold.
[0012] It can be seen that the present invention has at least the following three main inventive concepts:
[0013] Firstly, the visual content is captured for the parallel laying scene of the power supply cable and the tram track to obtain the laying scene picture, and the customized optimization processing of the nearest neighbor interpolation processing, geometric mean filtering processing and spatial differential method sharpening processing is sequentially performed on the laying scene picture to obtain a sequentially processed image with better image quality, thereby providing more reliable reference information for the subsequent scene intelligent identification;
[0014] Secondly: based on the grayscale value range corresponding to the power supply cable, the imaging sub-image occupied by the power supply cable in the image is sequentially processed, and each depth of field value corresponding to each pixel point of the imaging sub-image occupied by the power supply cable is obtained; based on the grayscale value range corresponding to the tram track, the imaging sub-image occupied by the tram track in the image is sequentially processed, and each depth of field value corresponding to each pixel point of the imaging sub-image occupied by the tram track is obtained, thereby obtaining various basic data of the convolutional neural network model for performing intelligent identification;
[0015] Again: the convolutional neural network model is applied to intelligently identify the shortest physical distance between the power supply cable and the tram track based on the depth of field values corresponding to each pixel point of the imaging sub-image occupied by the power supply cable, the horizontal coordinate values and the vertical coordinate values corresponding to each pixel point of the imaging sub-image occupied by the power supply cable, the depth of field values corresponding to each pixel point of the imaging sub-image occupied by the tram track, the horizontal coordinate values and the vertical coordinate values corresponding to each pixel point of the imaging sub-image occupied by the tram track, and the total number of pixels occupied by the sequentially processed images, so as to facilitate the subsequent judgment of whether the shortest physical distance is in a dangerous spacing state less than the set spacing threshold. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] The embodiments of the present invention will be described below with reference to the accompanying drawings, wherein:
[0017] Figure 1 It is a structural block diagram of a power supply cable laying scenario identification system according to the primary embodiment of the present invention.
[0018] Figure 2 It is a structural block diagram of a power supply cable laying scenario identification system according to a secondary embodiment of the present invention.
[0019] Figure 3 The present invention is a structural block diagram of a power supply cable laying scenario identification system according to another embodiment of the present invention. DETAILED DESCRIPTION
[0020] The embodiment of the power supply cable laying scene identification system of the present invention will be described in detail below with reference to the accompanying drawings.
[0021] Figure 1The structure block diagram of the power supply cable laying scene identification system according to the primary embodiment of the present invention is shown, and the system includes:
[0022] A content capture mechanism, used for performing a visual content capture operation facing a parallel laying scene of power supply cables and tram tracks, so as to obtain and output a corresponding laying scene picture;
[0023] A sequential processing mechanism, connected to the content capture mechanism and comprising a data interpolation device, a clarity processing device and a signal sharpening device, for sequentially performing nearest neighbor interpolation processing, geometric mean filtering processing and spatial differential method sharpening processing on the received laying scene pictures, so as to obtain and output a corresponding sequentially processed image;
[0024] Specifically, a PAL device may be selected to implement the sequential processing mechanism, which is connected to the content capture mechanism and includes a data interpolation device, a clarity processing device, and a signal sharpening device, and is used to sequentially perform nearest neighbor interpolation processing, geometric mean filtering processing, and spatial differential method sharpening processing on the received laying scene pictures to obtain and output corresponding sequentially processed images;
[0025] A model building mechanism, for performing multiple learning actions on a convolutional neural network to obtain a convolutional neural network after completing the multiple learning actions and outputting the convolutional neural network model as a convolutional neural network model, wherein the number of learning actions of the convolutional neural network is monotonically positively correlated with the maximum noise amplitude of the sequentially processed images;
[0026] a signal identification device, connected to the model building mechanism and the sequential processing mechanism, respectively, for detecting the imaging sub-image occupied by the power supply cable in the sequential processing image based on the grayscale value range corresponding to the power supply cable, and obtaining the depth of field values corresponding to the pixel points of the imaging sub-image occupied by the power supply cable; detecting the imaging sub-image occupied by the tram track in the sequential processing image based on the grayscale value range corresponding to the tram track, and obtaining the depth of field values corresponding to the pixel points of the imaging sub-image occupied by the tram track; applying the convolutional neural network model based on the depth of field values corresponding to the pixel points of the imaging sub-image occupied by the power supply cable, the horizontal coordinate values and the vertical coordinate values corresponding to the pixel points of the imaging sub-image occupied by the power supply cable, the depth of field values corresponding to the pixel points of the imaging sub-image occupied by the tram track, the horizontal coordinate values and the vertical coordinate values corresponding to the pixel points of the imaging sub-image occupied by the tram track, and the total number of pixel points occupied by the sequential processing image to intelligently identify the shortest physical distance between the power supply cable and the tram track;
[0027] a spacing alarm device connected to the signal identification device, and configured to send out a dangerous spacing identification signal when the shortest physical distance between the power supply cable and the tram track intelligently identified by the signal identification device is less than a set spacing threshold;
[0028] Wherein, the distance alarm device is also used to send out a safe distance identification signal when the shortest physical distance between the power supply cable and the tram track intelligently identified by the signal identification device is greater than or equal to the set distance threshold;
[0029] Wherein, the content capture mechanism is used to perform a visual content capture operation facing the parallel laying scene of the power supply cable and the tram track to obtain and output the corresponding laying scene picture, including: the content capture mechanism includes a photoelectric sensor, a directional lens and a flexible circuit board;
[0030] Wherein, the spacing alarm device is connected to the signal identification device and is used to send a dangerous spacing identification signal when the shortest physical distance between the power supply cable and the tram track intelligently identified by the signal identification device is less than a set spacing threshold, including: the set spacing threshold is 2 meters;
[0031] Among them, the application of the convolutional neural network model to intelligently identify the shortest physical distance between the power supply cable and the tram track based on the depth of field values corresponding to the pixels of the imaging sub-image occupied by the power supply cable, the horizontal coordinate values and the vertical coordinate values corresponding to the pixels of the imaging sub-image occupied by the power supply cable, the depth of field values corresponding to the pixels of the imaging sub-image occupied by the tram track, the horizontal coordinate values and the vertical coordinate values corresponding to the pixels of the imaging sub-image occupied by the tram track, and the total number of pixels occupied by the sequentially processed images includes: synchronously inputting the depth of field values corresponding to the pixels of the imaging sub-image occupied by the power supply cable, the horizontal coordinate values and the vertical coordinate values corresponding to the pixels of the imaging sub-image occupied by the power supply cable, the depth of field values corresponding to the pixels of the imaging sub-image occupied by the tram track, the horizontal coordinate values and the vertical coordinate values corresponding to the pixels of the imaging sub-image occupied by the tram track, and the total number of pixels occupied by the sequentially processed images into the convolutional neural network model.
[0032] Figure 2 It is a structural block diagram of a power supply cable laying scenario identification system according to a secondary embodiment of the present invention.
[0033] Compared to Figure 1 , Figure 2 The power supply cable laying scenario identification system may also include:
[0034] A wireless router device, wirelessly connected to the signal identification device, the data interpolation device, the clarity processing device and the signal sharpening device, respectively, for providing the signal identification device, the data interpolation device, the clarity processing device and the signal sharpening device with the wireless routing services they need;
[0035] The wireless router device is wirelessly connected to the signal identification device, the data interpolation device, the clarity processing device and the signal sharpening device respectively, and is used to provide the signal identification device, the data interpolation device, the clarity processing device and the signal sharpening device with the required wireless routing services respectively, including: the wireless router device connects the signal identification device, the data interpolation device, the clarity processing device and the signal sharpening device to the nearest WIFI network respectively;
[0036] The wireless router device connects the signal identification device, the data interpolation device, the clarity processing device and the signal sharpening device to the nearest WIFI network respectively, including: the wireless router device provides different IP addresses for the signal identification device, the data interpolation device, the clarity processing device and the signal sharpening device respectively, so as to respectively connect the signal identification device, the data interpolation device, the clarity processing device and the signal sharpening device to the nearest WIFI network by using the different IP addresses;
[0037] The wireless router device connects the signal identification device, the data interpolation device, the clarity processing device and the signal sharpening device to the nearest WIFI network respectively, including: the wireless router device detects and compares the signal strength of each WIFI network near the signal identification device, the data interpolation device, the clarity processing device and the signal sharpening device;
[0038] Among them, the wireless router device detects and compares the signal strengths of various WIFI networks near the signal identification device, the data interpolation device, the clarity processing device and the signal sharpening device, including: the wireless router device uses the WIFI network with the highest signal strength among the various WIFI networks near the signal identification device, the data interpolation device, the clarity processing device and the signal sharpening device as the WIFI network closest to the signal identification device, the data interpolation device, the clarity processing device and the signal sharpening device.
[0039] Figure 3 It is a structural block diagram of a power supply cable laying scenario identification system according to a secondary embodiment of the present invention.
[0040] Compared to Figure 1 , Figure 3 The power supply cable laying scenario identification system may also include:
[0041] An ultra-high-definition camera device is arranged near the signal identification device, the data interpolation device, the clarity processing device and the signal sharpening device, and is used to collect ultra-high-definition images of the working scenes of the signal identification device, the data interpolation device, the clarity processing device and the signal sharpening device;
[0042] Among them, the ultra-high-definition camera device is arranged near the signal identification device, the data interpolation device, the clarity processing device and the signal sharpening device, and is used to collect ultra-high-definition images of the working scenes of the signal identification device, the data interpolation device, the clarity processing device and the signal sharpening device, including: the ultra-high-definition camera device has a built-in photoelectric sensor unit and an ultra-high-definition lens, which is used to collect ultra-high-definition images of the working scenes of the signal identification device, the data interpolation device, the clarity processing device and the signal sharpening device;
[0043] Among them, the ultra-high-definition camera equipment has a built-in photoelectric sensor unit and an ultra-high-definition lens, which is used to capture ultra-high-definition images of the working scenes of the signal identification device, the data interpolation device, the clarity processing device and the signal sharpening device, including: the photoelectric sensor unit is a CMOS sensor unit or a CCD sensor unit.
[0044] In addition, in the power supply cable laying scene identification system, the convolutional neural network model is used to intelligently identify the shortest physical distance between the power supply cable and the tram track based on the depth of field values corresponding to each pixel point of the imaging sub-image occupied by the power supply cable, the horizontal coordinate values and the vertical coordinate values corresponding to each pixel point of the imaging sub-image occupied by the power supply cable, the depth of field values corresponding to each pixel point of the imaging sub-image occupied by the tram track, the horizontal coordinate values and the vertical coordinate values corresponding to each pixel point of the imaging sub-image occupied by the tram track, and the total number of pixels occupied by the sequentially processed images, and also includes: executing the convolutional neural network model to obtain the shortest physical distance between the power supply cable and the tram track output by the convolutional neural network model.
[0045] The power supply cable laying scene identification system of the present invention addresses the technical problem that the prior art lacks a reliable identification mechanism for the shortest physical distance between the power supply cable and the tram track. By establishing a convolutional neural network model with a customized structure and applying the convolutional neural network model, the shortest physical distance between the power supply cable and the tram track is intelligently identified based on various visual data of the power supply cable and the tram track, thereby facilitating the subsequent judgment of whether the shortest physical distance is in a dangerous spacing state less than a set spacing threshold.
[0046] It is to be understood that, although the present invention has been disclosed as a preferred embodiment, the above embodiment is not intended to limit the present invention. For any technician familiar with the art, without departing from the scope of the technical solution of the present invention, the technical content disclosed above can be used to make many possible changes and modifications to the technical solution of the present invention, or modified into equivalent embodiments of equivalent changes. Therefore, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention without departing from the content of the technical solution of the present invention still falls within the scope of protection of the technical solution of the present invention.
Claims
1. A power supply cable laying scene identification system, characterized in that: The system comprises: A content capture mechanism, used for performing a visual content capture operation facing a parallel laying scene of power supply cables and tram tracks, so as to obtain and output a corresponding laying scene picture; A sequential processing mechanism, connected to the content capture mechanism and comprising a data interpolation device, a clarity processing device and a signal sharpening device, for sequentially performing nearest neighbor interpolation processing, geometric mean filtering processing and spatial differential method sharpening processing on the received laying scene pictures, so as to obtain and output a corresponding sequentially processed image; A model building mechanism, for performing multiple learning actions on a convolutional neural network to obtain a convolutional neural network after completing the multiple learning actions and outputting the convolutional neural network model as a convolutional neural network model, wherein the number of learning actions of the convolutional neural network is monotonically positively correlated with the maximum noise amplitude of the sequentially processed images; a signal identification device, connected to the model building mechanism and the sequential processing mechanism, respectively, for detecting the imaging sub-image occupied by the power supply cable in the sequential processing image based on the grayscale value range corresponding to the power supply cable, and obtaining the depth of field values corresponding to the pixel points of the imaging sub-image occupied by the power supply cable; detecting the imaging sub-image occupied by the tram track in the sequential processing image based on the grayscale value range corresponding to the tram track, and obtaining the depth of field values corresponding to the pixel points of the imaging sub-image occupied by the tram track; applying the convolutional neural network model based on the depth of field values corresponding to the pixel points of the imaging sub-image occupied by the power supply cable, the horizontal coordinate values and the vertical coordinate values corresponding to the pixel points of the imaging sub-image occupied by the power supply cable, the depth of field values corresponding to the pixel points of the imaging sub-image occupied by the tram track, the horizontal coordinate values and the vertical coordinate values corresponding to the pixel points of the imaging sub-image occupied by the tram track, and the total number of pixel points occupied by the sequential processing image to intelligently identify the shortest physical distance between the power supply cable and the tram track; a spacing alarm device connected to the signal identification device, and configured to send out a dangerous spacing identification signal when the shortest physical distance between the power supply cable and the tram track intelligently identified by the signal identification device is less than a set spacing threshold; The distance alarm device is also used to send a safe distance identification signal when the shortest physical distance between the power supply cable and the tram track intelligently identified by the signal identification device is greater than or equal to the set distance threshold.
2. The power supply cable laying scene identification system according to claim 1, characterized in that: The content capture mechanism is used to perform a visual content capture operation facing a parallel laying scene of a power supply cable and a tram track to obtain and output a corresponding laying scene picture, including: the content capture mechanism includes a photoelectric sensor, a directional lens, and a flexible circuit board; Wherein, the spacing alarm device is connected to the signal identification device and is used to send a dangerous spacing identification signal when the shortest physical distance between the power supply cable and the tram track intelligently identified by the signal identification device is less than a set spacing threshold, including: the set spacing threshold is 2 meters; Among them, the application of the convolutional neural network model to intelligently identify the shortest physical distance between the power supply cable and the tram track based on the depth of field values corresponding to the pixels of the imaging sub-image occupied by the power supply cable, the horizontal coordinate values and the vertical coordinate values corresponding to the pixels of the imaging sub-image occupied by the power supply cable, the depth of field values corresponding to the pixels of the imaging sub-image occupied by the tram track, the horizontal coordinate values and the vertical coordinate values corresponding to the pixels of the imaging sub-image occupied by the tram track, and the total number of pixels occupied by the sequentially processed images includes: synchronously inputting the depth of field values corresponding to the pixels of the imaging sub-image occupied by the power supply cable, the horizontal coordinate values and the vertical coordinate values corresponding to the pixels of the imaging sub-image occupied by the power supply cable, the depth of field values corresponding to the pixels of the imaging sub-image occupied by the tram track, the horizontal coordinate values and the vertical coordinate values corresponding to the pixels of the imaging sub-image occupied by the tram track, and the total number of pixels occupied by the sequentially processed images into the convolutional neural network model.
3. The power supply cable laying scene identification system according to claim 2, characterized in that: The system further comprises: A wireless router device, wirelessly connected to the signal identification device, the data interpolation device, the clarity processing device and the signal sharpening device, respectively, for providing the signal identification device, the data interpolation device, the clarity processing device and the signal sharpening device with the wireless routing services they need; Among them, the wireless router device is wirelessly connected to the signal identification device, the data interpolation device, the clarity processing device and the signal sharpening device respectively, and is used to provide the signal identification device, the data interpolation device, the clarity processing device and the signal sharpening device with the wireless routing services they need respectively, including: the wireless router device connects the signal identification device, the data interpolation device, the clarity processing device and the signal sharpening device to the nearest WIFI network respectively.
4. The power supply cable laying scene identification system according to claim 3, characterized in that: The wireless router device connects the signal identification device, the data interpolation device, the clarity processing device and the signal sharpening device to the nearest WIFI network respectively, including: the wireless router device provides different IP addresses for the signal identification device, the data interpolation device, the clarity processing device and the signal sharpening device respectively, so as to use the different IP addresses to connect the signal identification device, the data interpolation device, the clarity processing device and the signal sharpening device to the nearest WIFI network respectively.
5. The power supply cable laying scene identification system according to claim 4, characterized in that: The wireless router device connects the signal identification device, the data interpolation device, the clarity processing device and the signal sharpening device to the nearest WIFI network respectively, including: the wireless router device detects and compares the signal strength of each WIFI network near the signal identification device, the data interpolation device, the clarity processing device and the signal sharpening device.
6. The power supply cable laying scene identification system according to claim 5, characterized in that: The wireless router device detects and compares the signal strengths of various WIFI networks near the signal identification device, the data interpolation device, the clarity processing device and the signal sharpening device, including: the wireless router device uses the WIFI network with the highest signal strength among the various WIFI networks near the signal identification device, the data interpolation device, the clarity processing device and the signal sharpening device as the WIFI network closest to the signal identification device, the data interpolation device, the clarity processing device and the signal sharpening device.
7. The power supply cable laying scene identification system according to claim 2, characterized in that: The system further comprises: The ultra-high-definition camera device is arranged near the signal identification device, the data interpolation device, the clarity processing device and the signal sharpening device, and is used to capture ultra-high-definition images of the working scenes of the signal identification device, the data interpolation device, the clarity processing device and the signal sharpening device.
8. The power supply cable laying scene identification system according to claim 7, characterized in that: An ultra-high-definition camera device is arranged near the signal identification device, the data interpolation device, the clarity processing device and the signal sharpening device, and is used to capture ultra-high-definition images of the working scenes of the signal identification device, the data interpolation device, the clarity processing device and the signal sharpening device. The ultra-high-definition camera device includes a built-in photoelectric sensor unit and an ultra-high-definition lens, which are used to capture ultra-high-definition images of the working scenes of the signal identification device, the data interpolation device, the clarity processing device and the signal sharpening device.
9. The power supply cable laying scene identification system according to claim 8, characterized in that: The ultra-high-definition camera device has a built-in photoelectric sensor unit and an ultra-high-definition lens, which is used to capture ultra-high-definition images of the working scenes of the signal identification device, the data interpolation device, the clarity processing device and the signal sharpening device, including: the photoelectric sensor unit is a CMOS sensor unit or a CCD sensor unit.
