Vision Data Fusion for Target Tracking

This paper proposes a novel approach and a system for object detection and tracking using video sensors. Optical Flow technique is used to derive the dynamic scene properties from the image sequences captured from stereo CCD cameras. Here, it is proposed to use the K-means clustering algorithm along with a template matching algorithm to identify the target from the 2D optical flow fields. Visual depth information of the interested target is calculated based on the disparity of the stereo image. The proposed target-tracking algorithm fuses different optical features to identify the relative position and speed of the target with respect to the camera system. An Extended Kalman Filter is used to track the target in the image sequence. In order to test the performance of the proposed algorithm, an experiment is conducted using stereo image sequences of a moving object. This paper presents the vision based target identification and tracking algorithm used in mobile robot navigation for a target tracking and following mission. This paper also discusses the potential applications of this algorithm in mobile robotics.