Publication #341

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@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.

[BibTex]

M.E. Sargin, L. Bertelli, B.S. Manjunath and K. Rose,
"Probabilistic Occlusion Boundary Detection on Spatio-Temporal Lattices"
12th IEEE International Conference on Computer Vision,, Kyoto, Japan, Oct. 2009.

DB ID: 341, Lab: VRL, Target: Conference, Status: Printed
Grants: [NSF ITR-0331697] « Look-up more
Subject: [Segmentation] « Look-up more
Project: [ITR] « Look-up more

» More: Advanced search