M2Tracker: A Multi-view Approach to Segmenting and Tracking People in a Cluttered Scene Using Region-Based Stereo

Abstract

We present a system that is capable of segmenting, detecting and tracking multiple people in a cluttered scene using multiple synchronized cameras located far from each other. The system improves upon existing systems in many ways including: (1) We do not assume that a foreground connected component belongs to only one object; rather, we segment the views… (More)
DOI: 10.1007/3-540-47969-4_2

Topics

9 Figures and Tables

Statistics

0102030'03'05'07'09'11'13'15'17
Citations per Year

175 Citations

Semantic Scholar estimates that this publication has 175 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@inproceedings{Mittal2002M2TrackerAM, title={M2Tracker: A Multi-view Approach to Segmenting and Tracking People in a Cluttered Scene Using Region-Based Stereo}, author={Anurag Mittal and Larry S. Davis}, booktitle={ECCV}, year={2002} }