2P1-O06 Tracking and Identification of Moving Objects using Cluster Based SJPDAFs(Digital Human)
Naotaka Hatao, Youichi TOKITA, Satoshi Kagami · The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec) · 2012
This paper describes a method for tracking and identification of moving objects with horizontal laser range finders. As the proposed method tracks moving objects with frameworks of SJPDAFs (Sample-based Joint Probabilistic Data Association Filters), it is robust against occlusions or false segmentations. The proposed method can classify moving objects as a car, a group of pedestrians, and a false positive. In addition, it is applied to tracking of pedestrians who pass through doors.