Automatic Recognition of Tram Tracks Based on Machine Vision

In recent years, modern trams have been developing rapidly in major cities. But affected by right-of-way issues, accidents related to trams are gradually becoming a new hot spot in traffic accidents. Among them, the line foreign body intrusion of trams is prone to major safety accidents, which brings a major hidden danger to the safety of tram line operation. In this paper, a fast and accurate Hough transform technique is used to identify the steel rails, and the improved Canny operator is used to extract the edge feature information of the image for the next training recognition. Through experiments, it is proved that the method can quickly and accurately detect the foreign objects of steel rails, and it has achieved good results in engineering applications.