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] The application belongs to the technical field of circuit image monitoring, and particularly relates to a power transmission line icing monitoring method and system based on infrared imaging. BACKGROUND

[0002] With the zero line northward migration caused by global climate change, the spatio-temporal distribution of rain, snow and freezing disasters presents significant changes, and its frequent occurrence and extremity pose a serious threat to power grid safety. Under the background of lean management of power transmission equipment and transformation of centralized monitoring and inspection mode, traditional inspection methods are difficult to cope with complex working conditions such as line icing and water mist interference under adverse weather conditions: under the rain, snow and freezing environment, the existing visual monitoring technology is usually greatly affected by water mist, and there are situations such as loss of details, low contrast and clarity, and imaging effect is greatly reduced, making it difficult to view the line environment and conductor icing conditions.

[0003] Therefore, it is urgent to break through the haze imaging technology bottleneck under extreme weather conditions, and to research a new power transmission line icing monitoring method and system to improve the imaging quality under rain, snow and freezing conditions, so as to effectively solve the problem of remote centralized monitoring and inspection of power transmission lines under extreme weather conditions. SUMMARY

[0004] To solve the above problems existing in the prior art, the application provides a power transmission line icing monitoring method and system based on infrared imaging.

[0005] The purpose of the application can be achieved by the following technical solutions:

[0006] A power transmission line icing monitoring method based on infrared imaging, comprising:

[0007] S1: acquiring power transmission line infrared imaging data, and obtaining a haze power transmission line image by adaptively processing the power transmission line infrared imaging data through haze enhancement processing;

[0008] S2: obtaining a high-resolution haze power transmission line image by processing the haze power transmission line image through a power transmission line hybrid domain super-resolution network;

[0009] S3: obtaining power transmission line icing information by processing the high-resolution haze power transmission line image through icing defect detection processing;

[0010] S4: outputting a power transmission line visual inspection report according to the power transmission line icing information, and generating power transmission line alarm information according to the power transmission line visual inspection report.

[0011] Preferably, the adaptive haze enhancement processing process in step S1 is:

[0012] S102-1: obtaining an initial de-fogged transmission line image by performing a fog concentration self-adaptive processing on the transmission line infrared imaging data;

[0013] S102-2: obtaining a de-fogged transmission line image by performing a multi-scale enhancement processing on the initial de-fogged transmission line image.

[0014] Preferably, the process of generating the initial de-fogged transmission line image in step S102-1 is as follows:

[0015] S102-11: obtaining a transmission line dark channel image by performing a dark channel reconstruction on the transmission line infrared imaging data;

[0016] S102-12: obtaining a transmission line fog concentration weight image by performing a dynamic fog concentration weight calculation processing on the transmission line infrared imaging data;

[0017] S102-13: obtaining a transmission line transmittance field by performing a transmittance field smoothing optimization processing on the transmission line dark channel image and the transmission line fog concentration weight image;

[0018] S102-14: obtaining an initial de-fogged transmission line image by performing an atmospheric scattering model inversion processing on the transmission line infrared imaging data according to the transmission line transmittance field.

[0019] Preferably, the process of generating the de-fogged transmission line image in step S102-2 is as follows:

[0020] S102-21: obtaining an initial de-fogged transmission line low-frequency layer and an initial de-fogged transmission line detail layer by performing a Gaussian pyramid detail decomposition extraction processing on the initial de-fogged transmission line image;

[0021] S102-22: obtaining an enhanced de-fogged transmission line low-frequency layer by performing a low-frequency enhancement processing on the initial de-fogged transmission line low-frequency layer;

[0022] S102-23: obtaining an enhanced de-fogged transmission line detail layer by performing a detail layer gain processing on the initial de-fogged transmission line detail layer;

[0023] S102-24: obtaining a radiance-consistent de-fogged transmission line image by performing a hybrid radiation fusion reconstruction processing on the enhanced de-fogged transmission line low-frequency layer and the enhanced de-fogged transmission line detail layer;

[0024] S102-25: obtaining a de-fogged transmission line image by performing a non-sharpening mask processing on the radiance-consistent de-fogged transmission line image.

[0025] Preferably, the processing process of the transmission line hybrid domain super-resolution network in step S2 is as follows:

[0026] S201: The power line mixed domain super network receives the foggy power line image, and obtains a foggy power line standard image by data normalization processing the foggy power line image;

[0027] S202: The foggy power line standard image is input into a temperature domain branch and a texture domain branch, a power line macro temperature gradient feature is obtained by temperature constraint residual block extraction, and a power line texture feature is obtained by texture channel attention block extraction;

[0028] S203: The power line macro temperature gradient feature and the power line texture feature are fused by a gate to obtain a foggy power line feature map;

[0029] S204: The foggy power line feature map is processed by sub-pixel convolution upsampling and normalized value inverse mapping to obtain a high-resolution foggy power line image.

[0030] Preferably, the process of the ice defect detection processing in step S3 is:

[0031] S301: The high-resolution foggy power line image is processed by a haze perception enhancement network to obtain a defogging high-contrast power line image;

[0032] S302: The high-resolution foggy power line image is processed by key component positioning detection to output conductor region positioning information;

[0033] S303: The conductor region positioning information is processed by a lightweight instance segmentation network to generate a pixel-level conductor mask;

[0034] S304: The pixel-level conductor mask and the defogging high-contrast power line image are processed by a multi-scale U-Net network to output an ice probability heat map;

[0035] S305: The ice probability heat map and the pixel-level conductor mask are processed by ice thickness distribution calculation to obtain ice thickness distribution data;

[0036] S306: The ice thickness distribution data is processed by a lightweight residual network to output power line defect positioning data.

[0037] Preferably, the process of generating the ice thickness distribution data in step S305 is:

[0038] S305-1: Preset a conductor diameter parameter and a camera calibration parameter;

[0039] S305-2: According to the conductor diameter parameter and the camera calibration parameter, the ice probability heat map and the pixel-level conductor mask are processed by a geometric morphology method to obtain a conductor contour inflation amount;

[0040] S305-3: generating icing thickness distribution data by inversely processing the wire profile inflation amount through a spatial projection model.

[0041] An infrared imaging-based power transmission line icing monitoring system, which is applied to the power transmission line icing monitoring method described above, comprises an adaptive haze enhancement module, a super-resolution reconstruction module, an icing detection module, and an icing monitoring alarm module.

[0042] The adaptive haze enhancement module is configured to acquire power transmission line infrared imaging data, and obtain a haze-free power transmission line image by performing adaptive haze enhancement processing on the power transmission line infrared imaging data.

[0043] The super-resolution reconstruction module is configured to obtain a high-resolution haze-free power transmission line image by processing the haze-free power transmission line image through a power transmission line hybrid domain super-resolution network.

[0044] The icing detection module is configured to obtain power transmission line icing information by performing icing defect detection processing on the high-resolution haze-free power transmission line image.

[0045] The icing monitoring alarm module is configured to output a power transmission line visual inspection report according to the power transmission line icing information, and generate power transmission line alarm information according to the power transmission line visual inspection report.

[0046] An electronic device comprises a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor implements the power transmission line icing monitoring method described above when executing the computer program.

[0047] A storage medium comprising computer executable instructions for executing the power transmission line icing monitoring method described above when executed by a computer processor.

[0048] The beneficial effects of the present application are as follows:

[0049] The haze-free power transmission line image is obtained by performing adaptive haze enhancement processing on the power transmission line infrared imaging data, thereby improving and optimizing the visual haze-free imaging quality under adverse conditions such as rain, snow, and freezing.

[0050] The high-resolution haze-free power transmission line image is obtained by processing the haze-free power transmission line image through the power transmission line hybrid domain super-resolution network, thereby significantly improving the resolution of the power transmission line infrared imaging and providing a basis for subsequent fine detection.

[0051] (3) The icing information of the power transmission line is obtained by processing the high-resolution and misty power transmission line image through the icing defect detection, and a visual inspection report of the power transmission line and an alarm information of the power transmission line are output, a lightweight model is used for detection, high detection accuracy is realized, real-time processing capability is improved, the limitation of a single sensor in a complex environment is solved through fusion of infrared temperature data and visible light texture features, a complete closed loop of “detection-visualization-alarm” is formed, the ability of the power transmission line to resist snow and ice disasters is improved, the extreme weather coping strategy is improved, and the power supply safety is ensured. BRIEF DESCRIPTION OF DRAWINGS

[0052] In order to facilitate the understanding of those skilled in the art, the present application will be further described below in conjunction with the drawings.

[0053] Figure 1 The flowchart of the power transmission line icing monitoring method based on infrared imaging is shown. DETAILED DESCRIPTION

[0054] In order to further illustrate the technical means and effects adopted by the present application to achieve the predetermined object, the specific embodiments, structures, features and effects according to the present application are described in detail below in conjunction with the drawings and preferred embodiments.

[0055] Please refer to Figure 1 A power transmission line icing monitoring method based on infrared imaging, comprising:

[0056] S1: acquiring infrared imaging data of a power transmission line, and obtaining a misty power transmission line image by adaptively enhancing the infrared imaging data of the power transmission line;

[0057] S2: obtaining a high-resolution misty power transmission line image by processing the misty power transmission line image through a power transmission line hybrid domain super-resolution network;

[0058] S3: obtaining power transmission line icing information by processing the high-resolution misty power transmission line image through icing defect detection;

[0059] S4: outputting a visual inspection report of the power transmission line according to the power transmission line icing information, and generating an alarm information of the power transmission line according to the visual inspection report of the power transmission line.

[0060] Embodiment 1

[0061] In this embodiment, the acquisition of the infrared imaging data of the power transmission line and the obtaining of the misty power transmission line image by adaptively enhancing the infrared imaging data of the power transmission line are implemented by the following steps:

[0062] S101: acquiring infrared imaging data of a power transmission line through a long-wave uncooled infrared sensor;

[0063] Specifically, the working waveband of the long-wave uncooled infrared sensor is 8um~12um, the pixel size is 12um*12um, the resolution is 384*288, and the image frame frequency is 50Hz.

[0064] S102: The process of the adaptive haze enhancement processing is:

[0065] S102-1: An initial haze-penetrating transmission line image is obtained by haze concentration adaptive processing of the transmission line infrared imaging data;

[0066] S102-11: A transmission line dark channel image is obtained by dark channel reconstruction of the transmission line infrared imaging data;

[0067] S102-12: A transmission line haze concentration weight image is obtained by dynamic haze concentration weight calculation processing of the transmission line infrared imaging data;

[0068] S102-13: A transmission line transmittance field is obtained by transmittance field smoothing optimization processing of the transmission line dark channel image and the transmission line haze concentration weight image;

[0069] S102-14: An initial haze-penetrating transmission line image is obtained by atmospheric scattering model inversion processing of the transmission line infrared imaging data according to the transmission line transmittance field.

[0070] S102-2: A haze-penetrating transmission line image is obtained by multi-scale enhancement processing of the initial haze-penetrating transmission line image.

[0071] S102-21: An initial haze-penetrating transmission line low-frequency layer and an initial haze-penetrating transmission line detail layer are obtained by Gaussian pyramid detail decomposition extraction processing of the initial haze-penetrating transmission line image;

[0072] S102-22: An enhanced haze-penetrating transmission line low-frequency layer is obtained by low-frequency enhancement processing of the initial haze-penetrating transmission line low-frequency layer;

[0073] S102-23: An enhanced haze-penetrating transmission line detail layer is obtained by detail layer gain processing of the initial haze-penetrating transmission line detail layer;

[0074] S102-24: A radiation-consistent haze-penetrating transmission line image is obtained by hybrid radiation fusion reconstruction processing of the enhanced haze-penetrating transmission line low-frequency layer and the enhanced haze-penetrating transmission line detail layer;

[0075] S102-25: A haze-penetrating transmission line image is obtained by non-sharpening mask processing of the radiation-consistent haze-penetrating transmission line image.

[0076] In the embodiment, the high-resolution transmission line image obtained by processing the transmission line image through the transmission line mixed domain super-resolution network is specifically implemented by the following steps:

[0077] The processing procedure of the transmission line mixed domain super-resolution network is as follows:

[0078] S201: The transmission line mixed domain super-resolution network receives the transmission line image, and processes the transmission line image through data normalization to obtain a transmission line standard image;

[0079] S202: The transmission line standard image is input into a temperature domain branch and a texture domain branch, macroscopic temperature gradient features of the transmission line are extracted through a temperature constraint residual block, and texture features of the transmission line are extracted through a texture channel attention block;

[0080] S203: The macroscopic temperature gradient features of the transmission line and the texture features of the transmission line are fused through a gate to obtain a transmission line feature map;

[0081] S204: The transmission line feature map is processed through sub-pixel convolution upsampling and normalized value inverse mapping to obtain a high-resolution transmission line image.

[0082] It should be noted that the gate weight is calculated from the temperature gradient amplitude.

[0083] In the embodiment, the transmission line icing information obtained by processing the high-resolution transmission line image through the icing defect detection is specifically implemented by the following steps:

[0084] The transmission line icing information includes icing thickness distribution data and transmission line defect positioning data;

[0085] S301: The high-resolution transmission line image is processed through a haze perception enhancement network to obtain a dehazed high-contrast transmission line image;

[0086] S302: The high-resolution transmission line image is processed through key component positioning detection to output conductor region positioning information;

[0087] S303: The conductor region positioning information is processed through a lightweight instance segmentation network to generate a pixel-level conductor mask;

[0088] S304: The pixel-level conductor mask and the dehazed high-contrast transmission line image are processed through a multi-scale U-Net network to output an icing probability heat map;

[0089] S305: The icing probability heat map and the pixel-level conductor mask are processed through icing thickness distribution calculation to obtain icing thickness distribution data;

[0090] S305-1: presetting a conductor diameter parameter and a camera calibration parameter;

[0091] S305-2: processing the icing probability thermal map and the pixel-level conductor mask through a geometric morphology method according to the conductor diameter parameter and the camera calibration parameter to obtain a conductor contour inflation amount;

[0092] S305-3: generating icing thickness distribution data by inversely processing the conductor contour inflation amount through a spatial projection model.

[0093] S306: outputting power transmission line defect positioning data by processing the icing thickness distribution data through a lightweight residual network.

[0094] In the embodiment, the power transmission line visual inspection report includes a power transmission line temperature thermal map, a power transmission line icing early warning area, and a power transmission line defect mark.

[0095] Embodiment 2

[0096] A power transmission line icing monitoring system based on infrared imaging includes an adaptive fog enhancement module, a super-resolution reconstruction module, an icing detection module, and an icing monitoring alarm module.

[0097] The adaptive fog enhancement module is configured to acquire power transmission line infrared imaging data, and process the power transmission line infrared imaging data through adaptive fog enhancement to obtain a foggy power transmission line image.

[0098] The super-resolution reconstruction module is configured to process the foggy power transmission line image through a power transmission line mixed domain super-resolution network to obtain a high-resolution foggy power transmission line image.

[0099] The icing detection module is configured to process the high-resolution foggy power transmission line image through icing defect detection to obtain power transmission line icing information.

[0100] The icing monitoring alarm module is configured to output a power transmission line visual inspection report according to the power transmission line icing information, and generate power transmission line alarm information according to the power transmission line visual inspection report.

[0101] Embodiment 3

[0102] The computer storage medium of the embodiments of the present application can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination thereof. More specific examples (non-exhaustive list) of the computer-readable storage medium include an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus, or device.

[0103] The computer-readable signal medium can include a data signal propagated in a baseband or propagated as a carrier wave in a propagation medium, in which the computer-readable program code is contained. Such propagated data signal can take a variety of forms, including but not limited to electro-magnetic, optical, or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable medium that is not a storage medium and that can be used to carry or propagate program code that is used by or in connection with an instruction execution system, apparatus, or device.

[0104] The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wire line, optical fiber, RF, etc., or any suitable combination of the above. The computer program code for carrying out operations of the present application can be written in one or more programming languages or combinations of languages including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages such as "C" or the like. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider). The present application is not limited to a particular programming language or computer system.

[0105] The above merely describes the preferred embodiments of the present application, and is not intended to limit the present application in any form. Although the present application has been disclosed with the preferred embodiments as above, it is not intended to limit the present application. Any person skilled in the art can make some changes or modifications to the above disclosed technical content to obtain equivalent embodiments with equivalent changes, as long as the changes or modifications do not deviate from the technical solution of the present application. Any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present application still belongs to the scope of the technical solution of the present application.

Claims

1. A method for monitoring icing on a power transmission line based on infrared imaging, characterized in that, The method comprises the following steps: S1: acquiring infrared imaging data of a power transmission line, and processing the infrared imaging data of the power transmission line through adaptive haze enhancement to obtain a haze-free power transmission line image; S2: processing the haze-free power transmission line image through a power transmission line mixed domain super-resolution network to obtain a high-resolution haze-free power transmission line image; S3: processing the high-resolution haze-free power transmission line image through an icing defect detection process to obtain power transmission line icing information; The process of the icing defect detection process in step S3 is as follows: S301: processing the high-resolution haze-free power transmission line image through a haze perception enhancement network to obtain a haze-free high-contrast power transmission line image; S302: processing the high-resolution haze-free power transmission line image through a key component positioning detection process to output conductor region positioning information; S303: processing the conductor region positioning information through a lightweight instance segmentation network to generate a pixel-level conductor mask; S304: processing the pixel-level conductor mask and the haze-free high-contrast power transmission line image through a multi-scale U-Net network to output an icing probability heat map; S305: processing the icing probability heat map and the pixel-level conductor mask through an icing thickness distribution calculation process to obtain icing thickness distribution data; S306: processing the icing thickness distribution data through a lightweight residual network to output power transmission line defect positioning data; S4: outputting a power transmission line visual inspection report according to the power transmission line icing information, and generating power transmission line alarm information according to the power transmission line visual inspection report.

2. The method of claim 1, wherein, The process of the adaptive haze enhancement process in step S1 is as follows: S102-1: processing the infrared imaging data of the power transmission line through haze concentration adaptive processing to obtain an initial haze-free power transmission line image; S102-2: processing the initial haze-free power transmission line image through multi-scale enhancement to obtain a haze-free power transmission line image.

3. The method of claim 2, wherein the step of determining the ice accretion on the power line comprises: The process of generating the initial haze-free power transmission line image in step S102-1 is as follows: S102-11: reconstructing the infrared imaging data of the power transmission line through a dark channel to obtain a power transmission line dark channel image; S102-12: processing the infrared imaging data of the power transmission line through dynamic haze concentration weight calculation to obtain a power transmission line haze concentration weight image; S102-13: processing the power transmission line dark channel image and the power transmission line haze concentration weight image through transmittance field smoothing optimization to obtain a power transmission line transmittance field; S102-14: processing the infrared imaging data of the power transmission line through an atmospheric scattering model inversion according to the power transmission line transmittance field to obtain an initial haze-free power transmission line image.

4. The method of claim 2, wherein The process of generating the haze-free power transmission line image in step S102-2 is as follows: S102-21: processing the initial haze-free power transmission line image through Gaussian pyramid detail decomposition extraction to obtain an initial haze-free power transmission line low-frequency layer and an initial haze-free power transmission line detail layer; S102-22: processing the initial haze-free power transmission line low-frequency layer through low-frequency enhancement to obtain an enhanced haze-free power transmission line low-frequency layer; S102-23: processing the initial haze-free power transmission line detail layer through a detail layer gain to obtain an enhanced haze-free power transmission line detail layer; S102-24: obtaining a radiation-consistent transmission line image by fusing and reconstructing the enhanced transmission line low-frequency layer and the enhanced transmission line detail layer through mixed radiation; S102-25: obtaining a transmission line image by processing the radiation-consistent transmission line image through a non-sharpening mask.

5. The method of claim 1, wherein, The processing process of the transmission line mixed domain super-resolution network in step S2 is as follows: S201: The transmission line mixed domain super-resolution network receives the transmission line image, and obtains a transmission line standard image by processing the transmission line image through data normalization; S202: The transmission line standard image is input into a temperature domain branch and a texture domain branch, and a transmission line macroscopic temperature gradient feature is obtained by temperature constraint residual block extraction, and a transmission line texture feature is obtained by texture channel attention block extraction; S203: The transmission line macroscopic temperature gradient feature and the transmission line texture feature are fused through a gate to obtain a transmission line feature map; S204: The transmission line feature map is processed through sub-pixel convolution up-sampling and normalized value inverse mapping to obtain a high-resolution transmission line image.

6. The method of claim 1, wherein, The generation process of the ice thickness distribution data in step S305 is as follows: S305-1: presetting a conductor diameter parameter and a camera calibration parameter; S305-2: processing the ice probability thermal image and the pixel-level conductor mask through a geometric morphology method according to the conductor diameter parameter and the camera calibration parameter to obtain a conductor contour inflation amount; S305-3: generating ice thickness distribution data by processing the conductor contour inflation amount through a spatial projection model inversion.

7. An infrared imaging-based transmission line icing monitoring system, the system being applied to the transmission line icing monitoring method according to any one of claims 1 to 6, characterized in that, The adaptive transmission enhancement module, the super-resolution reconstruction module, the ice detection module, and the ice monitoring and alarming module are included. The adaptive transmission enhancement module is configured to obtain transmission line infrared imaging data, and obtain a transmission line image by processing the transmission line infrared imaging data through adaptive transmission enhancement; The super-resolution reconstruction module is configured to obtain a high-resolution transmission line image by processing the transmission line image through a transmission line mixed domain super-resolution network; The ice detection module is configured to obtain transmission line ice information by processing the high-resolution transmission line image through ice defect detection; The ice monitoring and alarming module is configured to output a transmission line visual inspection report according to the transmission line ice information, and generate transmission line alarm information according to the transmission line visual inspection report.

8. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the transmission line ice monitoring method of any one of claims 1-6.

9. A storage medium containing computer-executable instructions, wherein: The computer executable instructions, when executed by the computer processor, are configured to execute the transmission line ice monitoring method of any one of claims 1-6.

Images