Share Email Print
cover

Proceedings Paper

Detection-based particle filtering for real-time multiple-head tracking applications
Author(s): Wei Qu; Dan Schonfeld
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

We present a novel detection based particle filtering framework for real-time multi-object tracking (MOT). It integrates object detection and motion information with particle filter detecting and tracking the multiple objects dynamically and simultaneously. To demonstrate the approach, we concentrate on the complex multi-head tracking while the framework is general for any kind of objects. Three novel contributions are made: 1) Distinct with the conventional particle filter which generates particles from the prior density, we propose a novel importance function based on up to date detection and motion observation which is much closer to the desired posterior. 2) By integrating detection, the tracker can do the initialization automatically, handle new object appearance and hard occlusion for MOT. By using motion estimation, it can track fast motion activities. 3) Hybrid observations including color and detection information are used to calculate the likelihood which makes the approach more stable. The proposed method is superior to the available tracking methods for multi-head tracking and can handle not only the changes of scale, lighting, zooming, and orientation, but also fast motion, appearance, and hard occlusion.

Paper Details

Date Published: 14 March 2005
PDF: 8 pages
Proc. SPIE 5685, Image and Video Communications and Processing 2005, (14 March 2005); doi: 10.1117/12.584594
Show Author Affiliations
Wei Qu, Univ. of Illinois/Chicago (United States)
Dan Schonfeld, Univ. of Illinois/Chicago (United States)


Published in SPIE Proceedings Vol. 5685:
Image and Video Communications and Processing 2005
Amir Said; John G. Apostolopoulos, Editor(s)

© SPIE. Terms of Use
Back to Top