Unlock instant, AI-driven research and patent intelligence for your innovation.

A Method and System for Identifying Environmental Hazards of Power Transmission Channels Based on Satellite Remote Sensing Images

A technology for satellite remote sensing images and power transmission channels, which is applied in the field of identification of potential environmental hazards in power transmission channels, can solve the problems that restrict the application of deep learning methods and cannot support the classification and identification of hidden dangers in complex environments of power transmission channels, and achieves the goal of promoting system construction, improving accuracy and The effect of efficiency

Active Publication Date: 2021-12-21
CHINA ELECTRIC POWER RES INST
View PDF14 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, relevant research has used methods such as harmonic analysis, object-oriented and deep learning to realize satellite remote sensing inspection of transmission lines. In general, harmonic analysis and object-oriented methods extract relatively few features and focus on normalization Several features such as vegetation index (NDVI) or texture cannot support the classification and identification of hidden dangers in the complex environment of transmission channels; deep learning methods, as a very popular technology in recent years, are restricted by the need for a large number of sample sets. Hidden dangers of the line environment include 10 major categories such as buildings, construction work areas, mining-affected areas, floating objects, tall plants, etc. At present, there is no suitable and sufficient sample set for training at home and abroad, which restricts the deep learning method Application in Satellite Remote Sensing Inspection of Power Transmission Channel

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A Method and System for Identifying Environmental Hazards of Power Transmission Channels Based on Satellite Remote Sensing Images
  • A Method and System for Identifying Environmental Hazards of Power Transmission Channels Based on Satellite Remote Sensing Images
  • A Method and System for Identifying Environmental Hazards of Power Transmission Channels Based on Satellite Remote Sensing Images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0066] This embodiment provides a method for identifying hidden dangers in the transmission channel environment, such as figure 1 shown, including:

[0067] S1 acquires satellite remote sensing images containing power transmission channels;

[0068] S2 Input the satellite remote sensing image into the pre-built support vector machine classifier to obtain the type of environmental hazards of the transmission channel;

[0069] The support vector machine classifier is trained based on the environmental hazards in historical satellite remote sensing images, and the classifier is optimized by using particle swarm algorithm and genetic algorithm.

[0070] It is necessary to optimize and iterate the parameters of the support vector machine classifier before identifying the hidden dangers of the transmission channel environment. The specific steps include:

[0071] Step 1: Build the training set

[0072] Step 1.1: Preprocessing historical satellite remote sensing images

[0073] O...

Embodiment 2

[0156] This embodiment provides a system for identifying hidden dangers in the transmission channel environment such as figure 2 shown, including:

[0157] An image acquisition module, used to acquire satellite remote sensing images containing power transmission channels;

[0158] The image classification module is used to input the satellite remote sensing image into the pre-built support vector machine classifier to obtain the environmental hidden danger type of the power transmission channel;

[0159] The support vector machine classifier is trained based on the environmental hazards in historical satellite remote sensing images, and the classifier is optimized by using particle swarm algorithm and genetic algorithm.

[0160] Further, the system also includes an optimization module, which is used to optimize the parameters of the support vector machine classifier by using the particle swarm optimization algorithm and the genetic algorithm.

[0161] Further, optimization ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The present invention provides a method and system for identifying hidden dangers in the power transmission channel environment, comprising: obtaining satellite remote sensing images containing power transmission channels; inputting the satellite remote sensing images into a pre-built support vector machine classifier to obtain the environment of the power transmission channel hidden danger type; the support vector machine classifier is trained based on the environmental hidden dangers in historical satellite remote sensing images, and the classifier is optimized by using particle swarm optimization and genetic algorithm. The present invention adopts the cooperative mode of particle swarm algorithm and genetic algorithm Training the parameters of the support vector machine classifier improves the accuracy and efficiency of the support vector machine classifier in identifying environmental hazards, and promotes the construction of a three-dimensional sky-ground inspection system for transmission lines using high-resolution satellite remote sensing images.

Description

technical field [0001] The invention belongs to the technical field of power transmission tower monitoring, and in particular relates to a method and system for identifying hidden dangers in a power transmission channel environment. Background technique [0002] In recent years, extreme weather conditions have intensified, and transmission lines, as the core infrastructure strategic facilities, are facing increased risks of safe operation. Not only is it reflected in the impact of natural disasters such as strong winds, geological disasters, and floods on the line, but at the same time, the process of urbanization has led to increasingly precious land resources, and more human activities in the power transmission channel protection area, including but not limited to: illegal buildings, High pole economic plants, agricultural greenhouses and other floating objects, construction work areas / mining areas, etc. This poses a huge human safety hazard to the transmission line. The...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G06K9/62G06N3/00G06N3/12
CPCG06N3/006G06N3/126G06V20/13G06F18/2411G06F18/214
Inventor 杨知刘毅赵斌滨欧文浩李闯马潇费香泽刘彬
Owner CHINA ELECTRIC POWER RES INST