Free-Form Planar Curve Tracking Using Related Points
B. Yondem, M. Unel, A. Ercil
Proceedings of 13th European Signal Processing Conference (EUSIPCO 2005)
their boundaries in real-time is not feasible due to the compu-tational burden of fitting algorithms. In this paper, we pro-pose to do fitting only for certain frames in an image se-quence and fill in the missing ones using Kalman filtering technique. An algorithm is presented to track a free-form shaped object, moving along an unknown trajectory, within the camera’s field of view (FOV). A discrete steady-state Kalman filter is used to estimate the future positions and ori-entation of the target object. Kalman filter uses the “related points” extracted from the decomposition of implicit poly-nomials of target’s boundary curves and measured position of target’s centroid. Related points undergo the same motion with the curve, hence could be used to estimate the orienta-tion of the target. The resulting algorithm is verified with simulations.