Efficient planar object tracking and parameter estimation using compactly represented cubic B-Spline curves

In this paper, we consider the problem of matching tno-dimensional (2-D) pl anar object curves from a database, and tracking moving object curves throu gh an image sequence, The first part of the paper describes a curve data co mpression method using B-spline curve approximation. We present a new const rained active B-spline curie model based on the minimum mean square error ( MMSE) criterion, and an iterative algorithm for selecting the "best" segmen t border points for each B-spline curve, The second part of the paper descr ibes a method for simultaneous object tracking and affine parameter estimat ion using the approximate curves and profiles, We propose a novel B-spline point assignment algorithm which incorporates the significant corners for i nterpolating corresponding paints on the two curves to be compared. A gradi ent-based algorithm is presented for simultaneously tracking object curl es , and estimating the associated translation, rotation and scaling parameter s. The performance of each proposed method is evaluated using still images and image sequences containing simple objects.