Mine track obstacle detection method based on information fusion

Abstract

Abstract As an important part of the coal mine transportation system, coal mine underground rail transportation undertakes the core transportation task of coal mine underground. Its safe and efficient operation is directly related to the efficiency of coal mine production and transportation. In view of this, this paper proposes a mine track environmental obstacle detection system which integrates camera and Lidar information to realize real-time automatic detection of obstacles in front of the underground track mine cart. The specific research results are as follows: first of all, a point cloud clustering algorithm for the mine environment is designed to extract the obstacle information, and then the YOLOv5 algorithm is used to identify the obstacle information in the image. Finally obstacle information from image and point cloud are fused at the decision-level. The obstacle detection method proposed in this paper can be successfully identified to meet the requirements of the obstacle object detection function of the rail vehicle.