RFID and vision based person tracking of a mobile robot using improved compressive tracking

This paper presents a person detection and tracking method for a mobile robot by fusing the data from Radio Frequency Identification (RFID) and stereo camera. The RFID system detects a person wearing an ID tag and a course position estimate of the person is obtained. The stereo camera is used for person detection based on the compressive sensing theory. Less Haar-like features are extracted from compressed domain to represent the person by a sparse measurement matrix. Furthermore, an improved Bayesian classifier is presented to handle appearance changes caused by illumination, pose, occlusion and motion in the tracking process. The detections from the RFID and the stereo camera are fused to obtain the final position which will be passed onto the controller of the robot. An Intelligent Gear Shift Control strategy is presented to adjust the robot´s linear velocity and turning radius automatically to follow the detected person. The experimental results show that the presented method performs well in terms of robustness and efficiency.