Deformable Contour Tracking using Hidden Markov Models

I. INTRODUCTION Object tracking is useful in many applications, and it is an active research area of computer vision. It is commonly used in human computer interaction and visual surveillance systems. Conventional methods such as background subtraction and mode seeking have been widely used, while many new approaches involving active shape models and graphical models were proposed over the past few years. However, these approaches usually use a pre-defined template for matching, which allows very little deformation. In this project, we focused on object tracking using contours. Specifically, we attempt to track objects that may deform substantially. Where this can be useful is for image segmenta-tion and general object tracking. We formulate the contour as a Hidden Markov Model, which was proposed by Huang [1]. In each new frame, we allow the states (locations along the boundary) to adapt to new observations of edge detection and NCC score against a patch centered at their location along the previous frame, while constraining smoothness of neighboring transitions as well. To do this, the forward-backward algorithm is used to find the global optimum set of contour landmark points in the new frame.