IMM-EKF를 통한 물체 추적 기법 및 센서 융합 방법

초록

This paper proposes a method for detecting and tracking objects by fusing LiDAR and Radar sensors for automatic parking systems(APS). The point cloud of the LiDAR sensor creates an Occupancy Grid Map (OGM) and uses it as an input to the detection network. Subsequently, the object is tracked using the Interacting Multiple Model-Extended Kalman Filter (IMM-EKF) by fusing the network output with the point cloud of the Radar sensor. Furthermore, we propose an object tracking method with probabilities based on the reliability of LiDAR and Radar sensors. The proposed method can be used to fuse sensors efficiently without complex algorithms, and experimental results show that the proposed method tracks objects in parking situations. We show the results on the performance of IMM-EKF and the probability according to the reliability of the sensor.

키워드