Mono vision particle filter based object tracking with a mobile robot

This paper proposes a new mono vision, particle filter based object tracking method that predicts a moving object´s position within an image, and computes the corresponding real-world position relative to a mobile robot. Accordingly, the mobile robot moves toward the moving object to keep it at the central field of view. Experimental results show that the proposed method allows our mobile robot to track a target moving at a moderate speed.