Object Tracking Using Finite Element Method and Branching Filter

Abstract

Abstract

We present an approach to robustly track the object behavior that turns over time from a set of input points from a single viewpoint. The distortions considered are caused by applying forces to known Harris function on the object’s surface. Our method combines the use of prior information on the geometry of the object modeled by a smooth template and the use of a finite element method to predict the distortion. This allows the accurate reconstruction of both the observed and the unobserved sides of the object. We present tracking results for noisy low-quality point clustering acquired by a stereo camera and a kinetic method, and simulations with point clustering corrupted by different error terms. Branching particle filtering is used for background extraction which is later subtracted from the motion frames for object detection. We show that our method is also applicable to large non-linear object behavior detection.

Keywords: Object behavior, STIP, branching particle filter, FEM, K-mean, Harris

Cite this Article

Neetu Gupta, Munish Vashishath, Rajiv Kapoor. Object Tracking Using Finite Element Method and Branching Filter. Current Trends in Signal Processing. 2017; 7(3): 35–40p.