Power transmission line wire defect detection method based on machine vision

Abstract

The invention discloses a power transmission line wire defect detection method based on machine vision, and the method comprises the steps: obtaining field image data, and making a training data set;constructing and training an instance segmentation network to obtain a prediction model; deducing an input picture by the model to obtain a rectangular region image and a binarized mask image of the wire; adopting a skeleton algorithm to extract a wire skeleton, calculating the average width of the wire, and reconstructing a binarized mask image; adopting a homomorphic filtering algorithm to eliminate the influence of uneven illumination of the rectangular area image, and combining a reconstructed binarization mask image to extract a segmented wire area image; generating a large number of rectangular frames on the wire area for screening; making a classification training data set, constructing and training a shallow classification network, and obtaining a classification prediction model; inputting the lead section area picture into the classification prediction model, and counting the defect type and defect proportion of the lead section state. The method can accurately segment the wire, detect the state of the wire in a segmented manner, and judge the defect type and defect degree of the wire.

Description

technical field [0001] The invention relates to the technical field of defect detection of transmission line conductors, in particular to a method for detecting defects of transmission line conductors based on machine vision. Background technique [0002] The safety of transmission line conductors is related to whether the power can be transmitted normally. The conductors are equivalent to the blood vessels of the power grid system and are used to transmit and distribute power. However, in outdoor scenarios, wires are easily affected by erosion and external force damage, resulting in defects such as corrosion, wear, and wire breakage, which will cause great hidden dangers to the normal operation of transmission lines. Some current methods for wire detection are mainly based on Hough transform and morphological image processing methods. On the one hand, it is difficult to be universal for changing shooting angles and scenes in outdoor scenes, and on the other hand, there is n...

AI Technical Summary

Problems solved by technology

However, in outdoor scenarios, wires are easily affected by erosion and external damage, resulting in defects such as corrosion, wear, and wire breakage, which will cause great hidden dangers to the normal operation of transmission lines.

Some current methods for wire detection are mainly based on Hough transform and morphological image processing methods. On the one hand, it is difficult to be universal for changing shooting angles and scenes in outdoor scenes, and on the other hand, there is no segmentation for non-linear wires. and detection capabilities

Images