Video object segmentation using active contour modelling with global relaxation

摘要

A system (10) for image object tracking and segmentation, includes (i) a modified adaptive resonance theory - 2 (M-ART2) model (12) for detecting changes of scenes, (ii) a two-dimensional correlative autopredicitve search (2D CAPS) method (14/46) for object tracking, (iii) a derivation (16/50) of contour energy for use in modelling an object edge, and (iv) an active contour model (18/52) with global relaxation for defining optimal image object boundaries. The modelled object boundary is derived from an edge potential energy calculation and a set of current edge points (176). For each edge point, several candidate data points (186-189) are also selected. Rather than calculate an energy value for each potential contours, a solution is achieved by comparing energy differences along a travel path. The selected contour is built in steps. An optimal path is selected from the potential paths.