Joint Appearance and Deformable Shape for Nonparametric Segmentation

This paper deals with region-of-interest (ROI) segmentation in video sequences. The goal is to determine in one frame the region which best matches, in terms of a similarity measure, a ROI defined in a reference frame. A similarity measure can combine color histograms and geometry information into a joint PDF. Geometric information are basically interior region coordinates. We propose a system of shape coordinates constant under shape deformations. High-dimensional colorgeometry PDF estimation being a difficult problem, measures based on these PDF distances may lead to an incorrect match. Instead, we use an estimator for Kullback-Leibler divergence efficient for high dimensional PDFs. The distance is expressed from the samples using the kth-nearest neighbor framework (kNN). We plugged this distance into active contour framework using shape derivative. Segmentation results on both rigid and articulated objects showed promising results.

• Type: Conference
• Year: 2007
• Where: HUMO
• Authors: Sylvain Boltz, Eric Debreuve, Michel Barlaud
• Keywords: Computer Animation, HUMO 2007, Interior Region Coordinates, Shape Coordinates, Similarity Measure