Transmission line icing thickness identification method based on unmanned aerial vehicle binocular parallax image

Abstract

The invention discloses a transmission line icing thickness identification method based on an unmanned aerial vehicle binocular parallax image and belongs to the field of image processing technology.The method comprises the steps of relevant information collection, icing image acquisition, parallax image solving, parallax image preprocessing, image binarization, contour extraction, icing thickness calculation, etc. According to the method, an icing image is processed to extract icing contours, a foreground and a background are separated by use of distance information, and therefore the separation effect is good; the icing image is preprocessed according to the characteristic that adjacent intervals of the icing image have approximate gray values, so that image gray levels are distributedmore uniformly; a binary threshold calculation method is proposed, a binary threshold is automatically determined, and therefore the method has high adaptability; and icing thickness is calculated bycalculating the specific value of the quantity of pixels contained in an iced wire contour to the quantity of pixels contained in a non-iced wire contour within a fixed column interval range, the possibility that a large measurement error is generated due to an icing shape change is reduced, and therefore the method is high in adaptability and 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