Probabilistic Occlusion Boundary Detection on Spatio-Temporal Lattices

M.E. Sargin, L. Bertelli, B.S. Manjunath and K. Rose,
Department of Electrical and Computer Engineering,
University of California, Santa Barbara,
msargin [at] ece.ucsb.edu

Abstract

In this paper, we present an algorithm for occlusion boundary detection. The main contribution is a probabilistic detection framework defined on spatio-temporal lattices, which enables joint analysis of image frames. For this purpose, we introduce two complementary cost functions for creating the spatio-temporal lattice and for performing global inference of the occlusion boundaries, respectively. In addition, a novel combination of low-level occlusion features is discriminatively learnt in the detection framework. Simulations on the CMU Motion Dataset provide ample evidence that proposed algorithm outperforms the leading existing methods.
[PDF] [BibTex]
M.E. Sargin, L. Bertelli, B.S. Manjunath and K. Rose,
12th IEEE International Conference on Computer Vision,, Kyoto, Japan, Oct. 2009.
Node ID: 534 , DB ID: 341 , Lab: VRL , Target: Conference
Subject: [Image and Video Segmentation] « Look up more