Sleeper defect detection method based on step-by-step deep learning and storage medium

Abstract

The invention discloses a sleeper defect detection method based on step-by-step deep learning and a storage medium. The method comprises the steps: obtaining a track image, and carrying out the preprocessing of the track image to obtain a sleeper region; inputting the sleeper area into a trained sleeper damage detection model to obtain a detection result of the track image; the training method ofthe sleeper damage detection model comprises the steps that a sleeper training set is constructed, and the network structure and the network input channel number of a YOLO V3 network are adjusted; training the migrated YOLO V3 network by adopting the sleeper training set to obtain a sleeper positioning model; adopting a sleeper positioning model to intercept sleeper areas of the pictures in the training set a to train the Darknet-53 network; adopting a defect feature extraction model to extract sleeper features of the pictures in the training set a to train an SVM classifier to obtain a classification model; wherein the sleeper positioning model, the defect feature extraction model and the classification model which are connected in sequence are used as a sleeper damage detection model.

Description

technical field [0001] The invention relates to a track defect detection technology, in particular to a sleeper defect detection method based on step-by-step deep learning. Background technique [0002] The sleepers not only support the rails and maintain the position of the rails, but also disperse the huge pressure transmitted from the rails to the track bed, which plays an important role in ensuring the safe operation of the train. Sleeper defect detection is one of the main tasks of track maintenance work. Up to now, the track maintenance work in our country is still dominated by manual inspection, which has the disadvantages of low work efficiency, high cost, and high risk factor. Therefore, with the continuous development of my country's rail transit industry, there is an urgent need for a fast, efficient, and low-cost automatic detection method. [0003] At present, in the field of rail transit, there are more and more relevant reports about intelligent rail inspect...

AI Technical Summary

Problems solved by technology

[0004] In view of the above-mentioned deficiencies in the prior art, the sleeper defect detection method and storage medium based on step-by-step deep learning provided by the present invention solve the problem of low defect detection efficiency of the traditional sleeper area positioning method

Images