We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Detection Method of Obstacles of Medium-low Speed Train in Transit Based on YOLOv3 Algorithm.
- Authors
Wang Chuanwen; Wang Lei; Huang Renhuan; Qin Rui
- Abstract
In this paper, an obstacle detection method based on YOLOV3 algorithm is proposed for obstacle detection of medium-low speed trains in transit. First, the deep learning algorithm is used to eff ectively identify obstacles in the scene. Then, the edge detection algorithm based on Freeman chain code is used to extract the edge of the train track, so as to determine whether the obstacles aff ect the traffi c and give a warning to the driver. At the same time, the YOLOV3 network data set is expanded by means of transfer learning, so as to achieve the purpose of improving the target obstacle recognition accuracy by use of this method in a specifi c scene. The experimental results show that this method has high applicability and is a convenient and effi cient obstacle detection method for trains in transit.
- Publication
Railway Signalling & Communication Engineering, 2021, Vol 18, Issue 7, p86
- ISSN
1673-4440
- Publication type
Article
- DOI
10.3969/j.issn.1673-4440.2021.07.020