Target tracking using multiple classifier systems and statistical process control

Target tracking or identification from sensing images is a common task for many applications. In order to improve the performance of target identification, multiple classifier combination is used and the performance of several multiple classifier systems is demonstrated and evaluated in terms of their ability to correctly classify an agent's success or failure in relation to multisensory target tracking and detection. Experiments show that a statistical process control and multiple classifier combination can improve the performance of image classification and target identification, with boosting and bagging achieving higher accuracy rates. Accordingly, good performance is consistently derived from dynamic classier learning in terms of process control.