Active shift attention based object tracking system
Aisha Ajmal, Christopher Hollitt, Marcus R. Frean · 2017
Multiple object tracking is a challenging research problem in which the path of multiple objects must be estimated from image sequences. We have developed a visual saliency based object tracker that alternates attention from one target to another using a measure of current uncertainty and the Kalman filter. We present results showing the effectiveness of the tracker in reducing the mean square error. By taking the measurements of the location, the tracker using the Kalman filter drives the uncertainty to a low level when it pays attention to an object. The uncertainty of the object grows to a high level when the tracker shifts attention to another object having high uncertainty from the previous frame. Our proposed tracking approach is tested with different scenarios and shows effective performance in shifting attention to the region that represents a scene.