A study on object tracking for mobile robot using image and distance information

In this paper, we are suggested the best tracking algorithm for mobile robot fusing both image and distance information. Proposed tracking algorithm is a kind of improved CAMSHIFT algorithm combined with SURF, Optical Flow and Ultra-Sonic data, to enhance the tracking capability. Since CAMSHIFT algorithm is based HSV color space model, it is vulnerable to the lighting, brightness and speed of the object. Also, CAMSHIFT doesn't consider the object's moving direction and velocity information when it sets the search window for tracking. The proposed algorithm fuses the information of SURF, optical flow and ultra-sonic data to set a searching window for tracking. Experimental tests prove the improved efficiency performance compared with CAMSHIFT only.