Research on Recognition for Subway Track Based on Canny Edge Detection and Hough Transformation

In recent years, line foreign bodies have led to many major safety incidents on urban rail transit lines, posing a huge potential risk to line operation safety. In this paper, a fast and accurate Hough transform technique is applied to identify two rails, followed by establishing a detection window of suitable size with two rails as the reference. Before detection, the original image also needs to be grayed out and filtered, and finally the improved Canny operator is used to extract the edge feature information of the image to make it easy for the next step of training recognition. In the process of implementation, this paper adopts a multi-frame Hough transform method to detect foreign objects, first extracting the feature information of steel rails with the original image, and then using the improved Canny operator to extract the image edge features. Through experiments, it is proved that the method can quickly and accurately detect foreign objects of steel rails, and it has achieved good results in engineering applications.