Clue defect detection method, terminal equipment and computer storage medium

Abstract

The invention discloses a clue defect detection method, terminal equipment and a computer storage medium. The clue defect detection method comprises the following steps: acquiring a prediction probability graph of clues in a to-be-detected image; determining a fitting straight line segment of the clue based on the prediction probability graph; generating a plurality of to-be-detected sub-images from the to-be-detected image based on segmentation operation on the fitted straight line segment; and performing defect detection on the plurality of to-be-detected sub-graphs to obtain defect information of the clues. According to the method and the device, straight line fitting is performed on the clue through the prediction probability result, the to-be-detected sub-graph is generated by utilizing the segmentation operation on the fitted straight line segment, and the defect condition of the clue is comprehensively evaluated through the defect detection result of the to-be-detected sub-graph, so that the accuracy of clue defect detection can be effectively improved.

Description

technical field [0001] The present application relates to the technical field of defect detection applications, and in particular to a method for detecting defect detection of clues, a terminal device and a computer storage medium. Background technique [0002] At present, my country's high-speed electrified railway strategy is being steadily promoted and implemented. As one of the key components of electrified railway, high-speed railway catenary, its reliability and safety are becoming more and more important. If the catenary of the high-speed rail breaks down, it will cause economic losses due to train delays, or it will threaten the lives of train passengers. Among them, the structural stability of the catenary suspension device has a great influence on the driving safety of the train, so it must be maintained and managed regularly. In order to improve the maintenance efficiency of the device, the catenary suspension state detection system (4C system) came into being. ...

AI Technical Summary

Problems solved by technology

There are various types of clue structures in the catenary, including contact wires, load-bearing cables, compensation ropes and various additional wires, etc., which are mainly responsible for important functions such as power supply, support and force, etc. They are large in number, slender in shape, and have defects The size of the defect is often relatively small, and the defect area occupies a small pixel area in the image. If the defect detection and analysis are performed manually one by one, the efficiency is low and it is easy to cause missed detection.

Images