Vision-based power transmission line recognition and foreign matter invasion online detection method

Abstract

The invention relates to a vision-based power transmission line recognition and foreign matter invasion online detection method, and belongs to the field of image processing and power transmission line detection. The method comprises the steps of preprocessing an image; extracting line segment features by using an EDLines algorithm; performing angle interval classification on the obtained line segment features, extracting parallel line segment groups of the power transmission line, and fusing the parallel line segment groups meeting a preset line segment connection standard; searching and delimiting a target area of the power transmission line according to the shape and spectral characteristic characteristics of the power transmission line, and marking a suspected area according to foreignmatter characteristics; and calculating optical flow distribution of the power transmission line target area in the adjacent frame images, and performing threshold segmentation, morphological operation and filtering processing on the optical flow images. And comparing the optical flow velocity mean values of the suspected area and the background area to realize foreign matter detection of the power transmission line. The effect of the method is not limited by illumination and complex backgrounds, and the method is high in robustness, high in universality, high in real-time performance and suitable for various electric power inspection environments.

Description

technical field [0001] The invention relates to a vision-based transmission line identification and foreign object intrusion online detection method, in particular to a transmission line identification and foreign object intrusion online detection method based on the combination of EDLines (Edge Drawing Lines) and optical flow method, which belongs to image processing and power transmission Line detection field. Background technique [0002] In the maintenance work of power grid transmission lines, the foreign object intrusion fault analysis of transmission lines is a very important direction. Foreign objects hanging on high-voltage transmission lines may cause short-circuit tripping of transmission lines and substations, causing great harm and directly affecting the safe and stable operation of the power grid. [0003] The traditional manual inspection method has the problems of high risk, low efficiency and low reliability. With its advantages of low cost, high efficienc...

AI Technical Summary

Problems solved by technology

This technology has low computational cost, but it is easily affected by factors such as illumination and complex background, resulting in false detection and missed detection; one type is a method that combines moving target detection and feature point tracking

However, there is a problem of large amount of calculation in feature point tracking, which makes it difficult to meet the real-time requirements of drone inspections; another category is to use deep learning technology to identify foreign objects, but due to insufficient training samples, the detection rate of foreign object defects is low.

Images