Paper Info
Title
Tracking Humans from a Moving Platform
Abstract
Research at the Computer Vision Laboratory at the University of Maryland has focused on developing algorithms and systems that can look at humans and recognize their activities in near real-time. Our earlier implementation (theW4 system) while quite successful was restricted to applications with a fixed camera. In this paper, we present some recent work that removes this restriction. Such systems are required for machine vision from moving platforms such as robots, intelligent vehicles, and unattended large field of regard cameras with a small field of view. Our approach is based on the use of a deformable shape model for humans coupled with a novel variant of the Condensation algorithm that uses quasi-random sampling for efficiency. This allows the use of simple motion models, which results in algorithm robustness, enabling us to handle unknown camera/human motion with unrestricted camera viewing angles. We present the details of our human tracking algorithms and some examples from pedestrian tracking and automated surveillance.
Year
DOI
Venue
2000
10.1109/ICPR.2000.902889
ICPR
Keywords
Field
DocType
human motion,fixed camera,tracking humans,human tracking algorithm,unknown camera,simple motion model,regard camera,condensation algorithm,algorithm robustness,unrestricted camera viewing angle,pedestrian tracking,computer vision,random sampling,monte carlo methods,real time systems,field of view,near real time,application software,machine vision,object recognition
Field of view,Computer vision,Pedestrian,Machine vision,Computer science,Smart camera,Artificial intelligence,Robot,Application software,Condensation algorithm,Cognitive neuroscience of visual object recognition
Conference
ISSN
Citations 
PageRank 
1051-4651
22
3.88
References 
Authors
8
3
Name
Order
Citations
PageRank
Larry S. Davis1142012690.83
Vasanth Philomin240993.18
Ramani Duraiswami31721161.98