Roadside Perception System Based on LiDAR and Millimeter-wave Radar Fusion in Mining Area

Abstract

In view of the shortcomings of the current onboard perception system in mining areas and the limitations of single sensor sensing, this paper analyzes the feasibility of using roadside perception system to provide additional sensing information for transportation monitoring system on the basis of studying roadside perception technology in mining areas. In view of the multi-sensor fusion technology of LiDAR and millimeter-wave radar and its advantages, a tracking algorithm based on Kalman filter and interactive multi-model (IMM) is proposed. Kalman filtering uses linear system state equation and input and output observation data to estimate system state optimally. IMM fuses local sensor tracks using specific algorithm, uses obstacle information by sensors,combines complementary and redundant information effectively by the algorithm. Hence, the tracking accuracy is increased, and false detection and missing detection of obstacles are avoided. The algorithm was tested in Shenyan Xiwan mining area and the result demonstrated that the motion feature of objects at intersection was detected effectively.

Keywords

• roadside perception system
• multi-sensor fusion
• LiDAR
• millimeter-wave radar
• Kalman filter
• interactive multi-model (IMM)
• mining area