Level-Set Person Segmentation and Tracking with Multi-Region Appearance Models and Top-Down Shape Information

Esther Horbert, Konstantinos Rematas, Bastian Leibe
International Conference on Computer Vision (ICCV'11). (Poster)

In this paper, we address the problem of segmentationbased tracking of multiple articulated persons. We propose two improvements to current level-set tracking formulations. The first is a localized appearance model that uses additional level-sets in order to enforce a hierarchical subdivision of the object shape into multiple connected regions with distinct appearance models. The second is a novel mechanism to include detailed object shape information in the form of a per-pixel figure/ground probability map obtained from an object detection process. Both contributions are seamlessly integrated into the level-set framework. Together, they considerably improve the accuracy of the tracked segmentations. We experimentally evaluate our proposed approach on two challenging sequences and demonstrate its good performance in practice.

» Show BibTeX

author = {Esther Horbert and
Konstantinos Rematas and
Bastian Leibe},
title = {Level-set person segmentation and tracking with multi-region appearance
models and top-down shape information},
booktitle = {{IEEE} International Conference on Computer Vision, {ICCV} 2011, Barcelona,
Spain, November 6-13, 2011},
pages = {1871--1878},
year = {2011},
crossref = {DBLP:conf/iccv/2011},
url = {http://dx.doi.org/10.1109/ICCV.2011.6126455},
doi = {10.1109/ICCV.2011.6126455},
timestamp = {Thu, 19 Jan 2012 18:05:15 +0100},
biburl = {http://dblp.uni-trier.de/rec/bib/conf/iccv/HorbertRL11},
bibsource = {dblp computer science bibliography, http://dblp.org}

Disclaimer Home Visual Computing institute RWTH Aachen University