A power transmission line icing monitoring method and system based on infrared imaging

Abstract

The present application relates to a kind of power transmission line icing monitoring method and system based on infrared imaging, belong to circuit image monitoring technical field.Wherein, the method includes obtaining power transmission line infrared imaging data, by adaptive fogging enhancement processing power transmission line infrared imaging data to obtain fogging power transmission line image;Through power transmission line hybrid domain super-resolution network processing the fogging power transmission line image to obtain high-resolution fogging power transmission line image;Through icing defect detection processing the high-resolution fogging power transmission line image to obtain power transmission line icing information;According to the power transmission line icing information output power transmission line visual inspection report, according to the power transmission line visual inspection report generates power transmission line alarm information, realizes the imaging quality improvement under the condition of rain, snow and ice, to effectively solve the problem of power transmission line remote centralized monitoring and inspection under extreme weather.

Description

Technical Field

[0001] This invention belongs to the field of circuit image monitoring technology, and in particular relates to a method and system for monitoring icing of transmission lines based on infrared imaging. Background Technology

[0002] As the zero-degree line shifts northward due to global climate change, the spatial and temporal distribution of rain, snow, and freezing disasters is changing significantly, and their frequency and extreme nature pose a severe threat to power grid safety. Against the backdrop of lean management and centralized monitoring and maintenance of transmission equipment, traditional inspection methods are struggling to cope with complex conditions such as line icing and water mist interference under severe weather conditions. In rain, snow, and freezing environments, existing visual monitoring technologies are often greatly affected by water mist, resulting in loss of detail, low contrast and clarity, and drastically reduced imaging quality, making it difficult to assess line conditions and conductor icing.

[0003] Therefore, it is urgent to break through the bottleneck of fog-penetrating imaging technology under extreme weather conditions and to study a new method and system for monitoring icing on power transmission lines, so as to improve the imaging quality under rain, snow and ice conditions and effectively solve the problem of remote centralized monitoring and inspection of power transmission lines under extreme weather conditions. Summary of the Invention

[0004] To address the aforementioned problems in the existing technology, this invention proposes a method and system for monitoring icing on power transmission lines based on infrared imaging.

[0005] The objective of this invention can be achieved through the following technical solutions: A method for monitoring icing on transmission lines based on infrared imaging, comprising: S1: Acquire infrared imaging data of the transmission line, and obtain a fog-penetrated transmission line image by adaptive fog-penetrating enhancement processing of the infrared imaging data of the transmission line; S2: The fog-penetrating transmission line image is processed by a hybrid domain super-resolution network to obtain a high-resolution fog-penetrating transmission line image; S3: Obtain icing information of the transmission line by processing the high-resolution fog-penetrating transmission line image through icing defect detection; S4: Output a visual inspection report of the transmission line based on the icing information of the transmission line, and generate alarm information of the transmission line based on the visual inspection report of the transmission line.

[0006] Preferably, the adaptive fog penetration enhancement process in step S1 is as follows: S102-1: Obtain an initial fog-penetrating transmission line image by adaptively processing the infrared imaging data of the transmission line through fog concentration; S102-2: Obtain a fog-penetrating transmission line image by performing multi-scale enhancement processing on the initial fog-penetrating transmission line image.

[0007] Preferably, the process of generating the initial fog-penetrating transmission line image in step S102-1 is as follows: S102-11: Obtain a dark channel map of the transmission line by reconstructing the infrared imaging data of the transmission line through the dark channel; S102-12: The infrared imaging data of the transmission line is processed by dynamic fog concentration weighting to obtain a fog concentration weighting map of the transmission line; S102-13: The transmittance field of the transmission line is obtained by smoothing and optimizing the dark channel map and fog concentration weight map of the transmission line through transmittance field optimization. S102-14: Based on the transmittance field of the transmission line, the infrared imaging data of the transmission line are inverted using an atmospheric scattering model to obtain an initial fog-penetrating transmission line image.

[0008] Preferably, the process of generating the fog-penetrating transmission line image in step S102-2 is as follows: S102-21: The initial fog-penetrating transmission line image is processed by Gaussian pyramid decomposition to obtain the low-frequency layer and detail layer of the initial fog-penetrating transmission line; S102-22: An enhanced fog-penetrating transmission line low-frequency layer is obtained by performing low-frequency enhancement processing on the initial fog-penetrating transmission line low-frequency layer; S102-23: The initial fog-penetrating transmission line detail layer is processed by detail layer gain to obtain an enhanced fog-penetrating transmission line detail layer; S102-24: The low-frequency layer and detail layer of the enhanced fog-penetrating transmission line are processed by hybrid radiometric fusion reconstruction to obtain a radiometrically consistent fog-penetrating transmission line image; S102-25: Obtain a fog-penetrating transmission line image by processing the radiation-consistent fog-penetrating transmission line image with an unsharpened mask.

[0009] Preferably, the processing procedure of the hybrid domain super-resolution network for transmission lines in step S2 is as follows: S201: The hybrid domain super-resolution network of the transmission line receives the fog-penetrating transmission line image and obtains the fog-penetrating transmission line standard image through data normalization processing. S202: The standard image of the fog-penetrating transmission line is input to the temperature domain branch and the texture domain branch. The macroscopic temperature gradient features of the transmission line are obtained by extracting the temperature-constrained residual block, and the texture features of the transmission line are obtained by extracting the texture channel attention block. S203: Obtain a fog-permeable transmission line feature map by gating and fusing the macroscopic temperature gradient features and texture features of the transmission line; S204: A high-resolution image of the fog-penetrating transmission line is obtained by processing the feature map of the fog-penetrating transmission line through subpixel convolution upsampling and normalized value inverse mapping.

[0010] Preferably, the process of detecting and processing icing defects in step S3 is as follows: S301: The high-resolution fog-penetrating transmission line image is processed by a fog perception enhancement network to obtain a defogging high-contrast transmission line image; S302: Output conductor area positioning information by processing the high-resolution fog-penetrating power transmission line image through key component positioning detection; S303: Generate a pixel-level wire mask by processing the wire region positioning information through a lightweight instance segmentation network; S304: Output an icing probability heatmap by processing the pixel-level conductor mask and the defogging high-contrast transmission line image through a multi-scale U-Net network; S305: Obtain ice thickness distribution data by processing the ice probability heatmap and the pixel-level wire mask through ice thickness distribution calculation; S306: The ice thickness distribution data is processed by a lightweight residual network to output the transmission line defect location data.

[0011] Preferably, the process of generating the ice thickness distribution data in step S305 is as follows: S305-1: Preset wire diameter parameters and camera calibration parameters; S305-2: Based on the conductor diameter parameters and the camera calibration parameters, the icing probability heatmap and the pixel-level conductor mask are processed using geometric morphology methods to obtain the conductor contour expansion amount; S305-3: The expansion of the conductor profile is processed by inversion using a spatial projection model to generate icing thickness distribution data.

[0012] An infrared imaging-based transmission line icing monitoring system, the system being applied to the aforementioned transmission line icing monitoring method, includes an adaptive fog penetration enhancement module, a super-resolution reconstruction module, an icing detection module, and an icing monitoring alarm module; The adaptive fog penetration enhancement module is used to acquire infrared imaging data of the transmission line and to obtain a fog-penetrated transmission line image by adaptive fog penetration enhancement processing of the infrared imaging data of the transmission line. The super-resolution reconstruction module is used to process the fog-penetrating transmission line image through a hybrid domain super-resolution network to obtain a high-resolution fog-penetrating transmission line image. The icing detection module is used to process the high-resolution fog-penetrating transmission line image through icing defect detection to obtain icing information of the transmission line; The icing monitoring and alarm module is used to output a visual inspection report of the transmission line based on the icing information of the transmission line, and to generate alarm information of the transmission line based on the visual inspection report of the transmission line.

[0013] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described method for monitoring icing of power transmission lines.

[0014] A storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform the aforementioned transmission line icing monitoring method.

[0015] The beneficial effects of this invention are as follows: By adaptively enhancing the fog penetration of the infrared imaging data of the transmission line, fog-penetrating images of the transmission line are obtained, thereby improving the quality and optimizing the effect of the visualization fog-penetrating imaging under harsh conditions such as rain, snow, and ice.

[0016] High-resolution images of the fog-penetrating transmission line are obtained by processing the fog-penetrating transmission line images using a hybrid domain super-resolution network, which significantly improves the resolution of infrared imaging of the transmission line and provides a foundation for subsequent refined detection.

[0017] (3) The high-resolution fog-penetrating transmission line image is processed by icing defect detection to obtain icing information of the transmission line and output the transmission line visualization inspection report and transmission line alarm information. The lightweight model is used for detection, which improves the real-time processing capability of detection while achieving high detection accuracy. The fusion of infrared temperature data and visible light texture features solves the limitations of a single sensor in complex environments, forming a complete closed loop of "detection-visualization-alarm", improving the transmission line's ability to resist rain, snow and ice disasters, improving extreme weather response strategies, and ensuring power supply safety. Attached Figure Description

[0018] To facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings.

[0019] Figure 1 This is a flowchart illustrating a method for monitoring icing on power transmission lines based on infrared imaging, according to the present invention. Detailed Implementation

[0020] To further illustrate the technical means and effects of the present invention in achieving its intended purpose, the following detailed description of the specific implementation methods, structures, features, and effects of the present invention, in conjunction with the accompanying drawings and preferred embodiments, is provided.

[0021] Please see Figure 1 A method for monitoring icing on transmission lines based on infrared imaging, comprising: S1: Acquire infrared imaging data of the transmission line, and obtain a fog-penetrated transmission line image by adaptive fog-penetrating enhancement processing of the infrared imaging data of the transmission line; S2: The fog-penetrating transmission line image is processed by a hybrid domain super-resolution network to obtain a high-resolution fog-penetrating transmission line image; S3: Obtain icing information of the transmission line by processing the high-resolution fog-penetrating transmission line image through icing defect detection; S4: Output a visual inspection report of the transmission line based on the icing information of the transmission line, and generate alarm information of the transmission line based on the visual inspection report of the transmission line.

[0022] Example 1 In this embodiment, the acquisition of infrared imaging data of the transmission line and the obtaining of a fog-penetrated transmission line image through adaptive fog-penetrating enhancement processing of the infrared imaging data of the transmission line are specifically implemented through the following steps: S101: Acquire infrared imaging data of power transmission lines using a long-wave uncooled infrared sensor; Specifically, the long-wave uncooled infrared sensor operates in the 8µm~12µm band, has a pixel size of 12µm*12µm, a resolution of 384*288, and an image frame rate of 50Hz.

[0023] S102: The adaptive fog penetration enhancement process is as follows: S102-1: Obtain an initial fog-penetrating transmission line image by adaptively processing the infrared imaging data of the transmission line through fog concentration; S102-11: Obtain a dark channel map of the transmission line by reconstructing the infrared imaging data of the transmission line through the dark channel; S102-12: The infrared imaging data of the transmission line is processed by dynamic fog concentration weighting to obtain a fog concentration weighting map of the transmission line; S102-13: The transmittance field of the transmission line is obtained by smoothing and optimizing the dark channel map and fog concentration weight map of the transmission line through transmittance field optimization. S102-14: Based on the transmittance field of the transmission line, the infrared imaging data of the transmission line are inverted using an atmospheric scattering model to obtain an initial fog-penetrating transmission line image.

[0024] S102-2: Obtain a fog-penetrating transmission line image by performing multi-scale enhancement processing on the initial fog-penetrating transmission line image.

[0025] S102-21: The initial fog-penetrating transmission line image is processed by Gaussian pyramid decomposition to obtain the low-frequency layer and detail layer of the initial fog-penetrating transmission line; S102-22: An enhanced fog-penetrating transmission line low-frequency layer is obtained by performing low-frequency enhancement processing on the initial fog-penetrating transmission line low-frequency layer; S102-23: The initial fog-penetrating transmission line detail layer is processed by detail layer gain to obtain an enhanced fog-penetrating transmission line detail layer; S102-24: The low-frequency layer and detail layer of the enhanced fog-penetrating transmission line are processed by hybrid radiometric fusion reconstruction to obtain a radiometrically consistent fog-penetrating transmission line image; S102-25: Obtain a fog-penetrating transmission line image by processing the radiation-consistent fog-penetrating transmission line image with an unsharpened mask.

[0026] In this embodiment, the process of obtaining a high-resolution image of a fog-penetrating transmission line by processing the image through a hybrid domain super-resolution network is specifically implemented through the following steps: The processing procedure of the hybrid domain super-resolution network for the transmission line is as follows: S201: The hybrid domain super-resolution network of the transmission line receives the fog-penetrating transmission line image and obtains the fog-penetrating transmission line standard image through data normalization processing. S202: The standard image of the fog-penetrating transmission line is input to the temperature domain branch and the texture domain branch. The macroscopic temperature gradient features of the transmission line are obtained by extracting the temperature-constrained residual block, and the texture features of the transmission line are obtained by extracting the texture channel attention block. S203: Obtain a fog-permeable transmission line feature map by gating and fusing the macroscopic temperature gradient features and texture features of the transmission line; S204: A high-resolution image of the fog-penetrating transmission line is obtained by processing the feature map of the fog-penetrating transmission line through subpixel convolution upsampling and normalized value inverse mapping.

[0027] It should be noted that the gating weights are calculated from the temperature gradient magnitude.

[0028] In this embodiment, the process of obtaining icing information of the transmission line by detecting icing defects in the high-resolution fog-penetrating transmission line image is specifically implemented through the following steps: The icing information of the transmission line includes icing thickness distribution data and transmission line defect location data; S301: The high-resolution fog-penetrating transmission line image is processed by a fog perception enhancement network to obtain a defogging high-contrast transmission line image; S302: Output conductor area positioning information by processing the high-resolution fog-penetrating power transmission line image through key component positioning detection; S303: Generate a pixel-level wire mask by processing the wire region positioning information through a lightweight instance segmentation network; S304: Output an icing probability heatmap by processing the pixel-level conductor mask and the defogging high-contrast transmission line image through a multi-scale U-Net network; S305: Obtain ice thickness distribution data by processing the ice probability heatmap and the pixel-level wire mask through ice thickness distribution calculation; S305-1: Preset wire diameter parameters and camera calibration parameters; S305-2: Based on the conductor diameter parameters and the camera calibration parameters, the icing probability heatmap and the pixel-level conductor mask are processed using geometric morphology methods to obtain the conductor contour expansion amount; S305-3: The expansion of the conductor profile is processed by inversion using a spatial projection model to generate icing thickness distribution data.

[0029] S306: The ice thickness distribution data is processed by a lightweight residual network to output the transmission line defect location data.

[0030] In this embodiment, the power transmission line visual inspection report includes a power transmission line temperature heat map, a power transmission line icing warning area, and power transmission line defect markings.

[0031] Example 2 An infrared imaging-based transmission line icing monitoring system includes an adaptive fog penetration enhancement module, a super-resolution reconstruction module, an icing detection module, and an icing monitoring and alarm module. The adaptive fog penetration enhancement module is used to acquire infrared imaging data of the transmission line and to obtain a fog-penetrated transmission line image by adaptive fog penetration enhancement processing of the infrared imaging data of the transmission line. The super-resolution reconstruction module is used to process the fog-penetrating transmission line image through a hybrid domain super-resolution network to obtain a high-resolution fog-penetrating transmission line image. The icing detection module is used to process the high-resolution fog-penetrating transmission line image through icing defect detection to obtain icing information of the transmission line; The icing monitoring and alarm module is used to output a visual inspection report of the transmission line based on the icing information of the transmission line, and to generate alarm information of the transmission line based on the visual inspection report of the transmission line.

[0032] Example 3 The computer storage medium of this invention can be any combination of one or more computer-readable media. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. Computer-readable storage media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0033] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0034] The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof. The computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages—such as Java, Smalltalk, and C++—and conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0035] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A method for monitoring icing on transmission lines based on infrared imaging, characterized in that, include: S1: Acquire infrared imaging data of the transmission line, and obtain a fog-penetrated transmission line image by adaptive fog-penetrating enhancement processing of the infrared imaging data of the transmission line; S2: The fog-penetrating transmission line image is processed by a hybrid domain super-resolution network to obtain a high-resolution fog-penetrating transmission line image; S3: Obtain icing information of the transmission line by processing the high-resolution fog-penetrating transmission line image through icing defect detection; S4: Output a visual inspection report of the transmission line based on the icing information of the transmission line, and generate alarm information of the transmission line based on the visual inspection report of the transmission line.

2. The method for monitoring icing on transmission lines according to claim 1, characterized in that, The adaptive fog penetration enhancement process in step S1 is as follows: S102-1: Obtain an initial fog-penetrating transmission line image by adaptively processing the infrared imaging data of the transmission line through fog concentration; S102-2: Obtain a fog-penetrating transmission line image by performing multi-scale enhancement processing on the initial fog-penetrating transmission line image.

3. The method for monitoring icing on transmission lines according to claim 2, characterized in that, The process of generating the initial fog-penetrating transmission line image in step S102-1 is as follows: S102-11: Obtain a dark channel map of the transmission line by reconstructing the infrared imaging data of the transmission line through the dark channel; S102-12: The infrared imaging data of the transmission line is processed by dynamic fog concentration weighting to obtain a fog concentration weighting map of the transmission line; S102-13: The transmittance field of the transmission line is obtained by smoothing and optimizing the dark channel map and fog concentration weight map of the transmission line through transmittance field optimization. S102-14: Based on the transmittance field of the transmission line, the infrared imaging data of the transmission line are inverted using an atmospheric scattering model to obtain an initial fog-penetrating transmission line image.

4. The method for monitoring icing on transmission lines according to claim 2, characterized in that, The process of generating the fog-penetrating transmission line image in step S102-2 is as follows: S102-21: The initial fog-penetrating transmission line image is processed by Gaussian pyramid decomposition to obtain the low-frequency layer and detail layer of the initial fog-penetrating transmission line; S102-22: An enhanced fog-penetrating transmission line low-frequency layer is obtained by performing low-frequency enhancement processing on the initial fog-penetrating transmission line low-frequency layer; S102-23: The initial fog-penetrating transmission line detail layer is processed by detail layer gain to obtain an enhanced fog-penetrating transmission line detail layer; S102-24: The low-frequency layer and detail layer of the enhanced fog-penetrating transmission line are processed by hybrid radiometric fusion reconstruction to obtain a radiometrically consistent fog-penetrating transmission line image; S102-25: Obtain a fog-penetrating transmission line image by processing the radiation-consistent fog-penetrating transmission line image with an unsharpened mask.

5. The method for monitoring icing on transmission lines according to claim 1, characterized in that, The processing procedure for the hybrid domain super-resolution network of the transmission line in step S2 is as follows: S201: The hybrid domain super-resolution network of the transmission line receives the fog-penetrating transmission line image and obtains the fog-penetrating transmission line standard image through data normalization processing. S202: The standard image of the fog-penetrating transmission line is input to the temperature domain branch and the texture domain branch. The macroscopic temperature gradient features of the transmission line are obtained by extracting the temperature-constrained residual block, and the texture features of the transmission line are obtained by extracting the texture channel attention block. S203: Obtain a fog-permeable transmission line feature map by gating and fusing the macroscopic temperature gradient features and texture features of the transmission line; S204: A high-resolution image of the fog-penetrating transmission line is obtained by processing the feature map of the fog-penetrating transmission line through subpixel convolution upsampling and normalized value inverse mapping.

6. The method for monitoring icing on transmission lines according to claim 1, characterized in that, The process of detecting and processing icing defects in step S3 is as follows: S301: The high-resolution fog-penetrating transmission line image is processed by a fog perception enhancement network to obtain a defogging high-contrast transmission line image; S302: Output conductor area positioning information by processing the high-resolution fog-penetrating power transmission line image through key component positioning detection; S303: Generate a pixel-level wire mask by processing the wire region positioning information through a lightweight instance segmentation network; S304: Output an icing probability heatmap by processing the pixel-level conductor mask and the defogging high-contrast transmission line image through a multi-scale U-Net network; S305: Obtain ice thickness distribution data by processing the ice probability heatmap and the pixel-level wire mask through ice thickness distribution calculation; S306: The ice thickness distribution data is processed by a lightweight residual network to output the transmission line defect location data.

7. The method for monitoring icing on transmission lines according to claim 6, characterized in that, The process of generating ice thickness distribution data in step S305 is as follows: S305-1: Preset wire diameter parameters and camera calibration parameters; S305-2: Based on the conductor diameter parameters and the camera calibration parameters, the conductor contour expansion is obtained by processing the icing probability heatmap and the pixel-level conductor mask using a geometric morphology method. S305-3: The expansion of the conductor profile is processed by inversion using a spatial projection model to generate icing thickness distribution data.

8. A transmission line icing monitoring system based on infrared imaging, wherein the system is applied to the transmission line icing monitoring method as described in any one of claims 1-7, characterized in that, It includes an adaptive fog penetration enhancement module, a super-resolution reconstruction module, an icing detection module, and an icing monitoring and alarm module; The adaptive fog penetration enhancement module is used to acquire infrared imaging data of the transmission line and to obtain a fog-penetrated transmission line image by adaptive fog penetration enhancement processing of the infrared imaging data of the transmission line. The super-resolution reconstruction module is used to process the fog-penetrating transmission line image through a hybrid domain super-resolution network to obtain a high-resolution fog-penetrating transmission line image. The icing detection module is used to process the high-resolution fog-penetrating transmission line image through icing defect detection to obtain icing information of the transmission line; The icing monitoring and alarm module is used to output a visual inspection report of the transmission line based on the icing information of the transmission line, and to generate alarm information of the transmission line based on the visual inspection report of the transmission line.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the transmission line icing monitoring method as described in any one of claims 1-7.

10. A storage medium containing computer-executable instructions, characterized in that, The computer-executable instructions, when executed by a computer processor, are used to perform the transmission line icing monitoring method as described in any one of claims 1-7.

Images