1. Obstacle detection in front of a railway vehicle using an onboard stereo camera (Evaluation with scaled model experimental vehicle)
- Author
-
Takumi SHIBATA and Yohei MICHITSUJI
- Subjects
railway ,automatic operation ,obstacle detection ,stereo camera ,image processing ,Mechanical engineering and machinery ,TJ1-1570 ,Engineering machinery, tools, and implements ,TA213-215 - Abstract
In the railway sector, efforts are being made to improve the efficiency of operations. One of these is the automatic operation of trains. To keep the train running safely, it is necessary to make sure that there are no obstacles in front of the railway vehicle. Therefore, automatic train operation requires obstacle detection system in front of the railway vehicle. In recent years, some railway operators have introduced onboard cameras as drive recorders in order to understand the situation at the time of an accident and to investigate the cause. In addition, efforts are being made in the railway sector to improve operational efficiency through the use of onboard cameras. In this paper, we propose an obstacle detection method using an onboard stereo camera. The proposed system can be divided into three parts. First, the center position of the track is estimated using RGB images, and the search area for obstacle detection is set. Second, proposed system checks for the presence of objects within the set search area and creates a candidate area of obstacle. Finally, the area of each neighboring candidate area of obstacle is calculated, and if the area is greater than a certain value, the object is determined to be an obstacle. Furthermore, the proposed system is verified by using a 1/10 scale model experimental vehicle. Validation results show that the proposed system is capable of detecting obstacles in front of railway vehicles.
- Published
- 2023
- Full Text
- View/download PDF