Identification method of transmission line ice thickness based on UAV binocular parallax image

Abstract

The invention discloses a method for identifying the ice thickness of a power transmission line based on a binocular parallax image of an unmanned aerial vehicle, and belongs to the technical field of image processing. Including related information collection, ice image acquisition, disparity map calculation, disparity map preprocessing, image binarization, contour extraction, ice thickness calculation and other steps. The invention extracts the ice-covered contour by processing the parallax image, uses the distance information to separate the foreground and the background, and has good separation effect. The disparity image is preprocessed according to the similarity of the gray values ​​in the adjacent intervals of the disparity image, so that the gray level distribution of the image is more uniform. A binarization threshold calculation method is proposed to automatically determine the binarization threshold, and the method has strong adaptability. The ice thickness is calculated by calculating the ratio of the number of pixels contained in the outline of the ice-coated conductor to the number of pixels contained in the outline of the uniced conductor within a fixed column interval, which reduces the possibility of large measurement errors due to changes in the shape of the ice. The method has strong adaptability and high precision.

Description

technical field [0001] The patent of the present invention relates to the technical field of image processing, and in particular to a method for identifying the ice thickness of transmission lines based on binocular parallax images of drones. Background technique [0002] In recent years, power line failure events caused by icing on transmission lines have occurred frequently. Accidents such as transmission line flashover, disconnection, insulator damage, tower collapse, and wire deicing dance caused by icing have seriously endangered the operation of the power system, resulting in Huge economic loss. Therefore, it is of great significance to carry out real-time online monitoring of transmission lines, find faults in time, and prevent and treat them in time. [0003] At present, the inspection of transmission lines is mostly manual inspection, but manual inspection requires a great deal of personnel investment and high cost, and for some mountainous areas with inconvenient ...

AI Technical Summary

Problems solved by technology

However, this method only considers the situation of uniform icing, and it is difficult to achieve a more accurate detection of uneven icing thickness.

In addition, in the image processing process, the influence of different backgrounds on image processing is not considered. The actual image processing process is prone to calculation errors due to the influence of complex environmental factors, and the threshold of binarization is artificially set, which is difficult for different environments. Intelligent processing of images of ice-coated transmission lines

Images