107
Copyright © 2010, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited.
Chapter 6
Multi-Scale People Detection
and Motion Analysis for
Video Surveillance
YingLi Tian
The City College of City University of New York, USA
Rogerio Feris
IBM T. J. Watson Research Center, USA
Lisa Brown
IBM T. J. Watson Research Center, USA
Daniel Vaquero
University of California, Santa Barbara, USA
Yun Zhai
IBM T. J. Watson Research Center, USA
Arun Hampapur
IBM T. J. Watson Research Center, USA
ABStrAct
Visual processing of people, including detection, tracking, recognition, and behavior interpretation, is a
key component of intelligent video surveillance systems. Computer vision algorithms with the capability
of “looking at people” at multiple scales can be applied in different surveillance scenarios, such as far-
feld people detection for wide-area perimeter protection, mid-feld people detection for retail/banking
applications or parking lot monitoring, and near-feld people/face detection for facility security and
access. In this chapter, we address the people detection problem in different scales as well as human
tracking and motion analysis for real video surveillance applications including people search, retail
loss prevention, people counting, and display effectiveness.
DOI: 10.4018/978-1-60566-900-7.ch006