Support Vector Machines Based Target Tracking Techniques

This paper addresses the problem of aplying powerful statistical pattern classification algorithms based on kernels to target tracking. Rather than directly adapting a recognizer, we develop a localizer directly using the regression form of the Support Vector Machines (SVM). The proposed approach considers using dynamic model together as feature vectors and makes the hyperplane and the support vectors follow the changes in these features. The performance of the tracker is demostrated in a sensor network scenario with a moving target in a polynomial route.