Subway tunnel disease detection method based on deep learning

Abstract

The invention discloses a subway tunnel disease detection method based on deep learning, and mainly solves the problems that the subway tunnel detection amount is large, and the existing detection algorithm is low in efficiency and large in missing detection amount. The method specifically comprises the following steps: making a to-be-detected subway tunnel image database, including a subway tunnel normal region picture database and a subway tunnel disease region database; based on an improved Faster R-CNN target detection algorithm, carrying out target positioning and accurate identification and classification on the subway tunnel diseases; detecting a disease state in the to-be-detected area by adopting a deep learning-based method; and finally, inputting a to-be-tested image into the detection model to obtain a tunnel disease detection result. The solution thought of the traditional algorithm is image-preprocessing-artificial feature extraction-classification. According to the method, the problems existing in current subway tunnel disease detection are solved by utilizing the thought of deep learning, namely image-feature extraction network-classification and regression.

Description

technical field [0001] The invention relates to the fields of image processing and deep learning, in particular to a method for detecting subway tunnel defects based on deep learning. Background technique [0002] The vigorous development and expansion of urban rail transit has further promoted the rise of China's urban rail operation and maintenance market. The existing tunnel safety maintenance has low labor efficiency, high operation intensity, short window time, high maintenance cost, poor effectiveness, and overall planning. Problems such as weak capabilities and insufficient connection with operations have put forward higher requirements for tunnel safety detection methods. With the continuous development of deep learning technology, breakthroughs have been made in many fields, such as AlphaGo defeating the international Go champion, real-time "machine translation" in the call video, recognizing information in pictures or videos like humans, etc. . In view of the sho...

AI Technical Summary

Problems solved by technology

In view of the shortcomings of slow, time-consuming and inefficient manual inspection in subway tunnel inspection, machine learning algorithms can be used for visual inspection to solve the problem of low maintenance efficiency of workers. The traditional machine learning algorithm SVM is currently used for visual inspection, but its Efficiency and accuracy still have a lot to be improved

Images