Energy Association Filter for Online Data Association with Missing Data

Abstract

Data association problem is of crucial importance to improve online object tracking performance in many difficult visual environments. Usually, association effectiveness is based on prior information and observation category. However, some problems can arise when objects are quite similar. Therefore, neither the color nor the shape could be helpful informations to achieve the task of data association. Likewise, a problem can also arise when tracking deformable objects, under the constraint of missing data, with complex motions. Such restriction, i.e. the lack in prior information, limit the association performance. To remedy, we propose a novel method for data association, inspired from the evolution of the object dynamic model, and based on a global minimization of an energy. The main idea is to measure the absolute geometric accuracy between features. Parameterless constitutes the main advantage of our energy minimization approach. Only one information, the position, is used as input to our algorithm. We have tested our approach on several sequences to show its effectiveness.