Research on multi-target tracking method based on multi-sensor fusion

Purpose Intelligent and connected vehicle technology is in the ascendant. High-level autonomous driving places more stringent requirements on accuracy reliability of environmental perception. Existing research works multitarget tracking based multisensor fusion mostly focuses perspective, but limited by principal defects sensor platform, it difficult to comprehensively accurately describe surrounding environment information. Design/methodology/approach In this paper, a method roadside proposed, including measurement noise adaptive Kalman filtering, global nearest neighbor data association gate, Track life cycle management M/N logic rules. Findings Compared with fixed-size gates, gates proposed paper can improve performance process. single measurement, improves position estimation 13.5% velocity 22.2%. control method, 23.8% 8.9%. Originality/value A filtering realize adjustment noise. gate gate.