A Multiple Hypothesis Tracking Method for Extended Target Tracking

Abstract

This paper presents a multiple hypothesis tracking (MHT) method for tracking extended targets. Measurements of extended target can provide much new information such as the shape and the size of the target, as well as the kinematic state. The new proposed MHT method can make use of the extra information, especially the target extent, to evaluate the tracks. We demonstrate the performance of the method in the case of tracking an extended target whose shape is modeled as an ellipse. The new proposed method has better performance than the conventional MHT.