Railway obstacle detection based on radar and image data fusion

Abstract

In order to improve the poor adaptability of a single sensor in detection and further improve the train’s ability to perceive the running environment ahead, a railway obstacle detection method based on the fusion of microwave radar and image data was proposed. The environment in front of the train collected by the radar is preprocessed to eliminate false and out-of-bounds target signals, and the target within the safety limit is retained. At the same time, the frame difference method is used to detect the obstacles in the image sequence captured by the vehicle camera. The detection results of radar and camera are fused at the decision level. The experimental results show that this method can effectively realize the joint detection of obstacles by microwave radar and machine vision, which makes up for the deficiency of single sensor in obstacle detection.