ARGMode - Activity Recognition using Graphical Models

This paper presents a new framework for tracking and recognizing complex multi-agent activities using probabilistic tracking coupled with graphical models for recognition. We employ statistical feature based particle filter to robustly track multiple objects in cluttered environments. Both color and...

Full description

Saved in:
Bibliographic Details
Published in2003 Conference on Computer Vision and Pattern Recognition Workshop Vol. 4; p. 38
Main Authors Hamid, Raffay, Huang, Yan, Essa, Irfan
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2003
Subjects
Conferences
Feature extraction
Hidden Markov models
Histograms
Image color analysis
Robustness
Shape
Online AccessGet full text
ISBN0769519008
9780769519005
ISSN1063-6919
1063-6919
DOI10.1109/CVPRW.2003.10039

Cover

More Information
Summary:This paper presents a new framework for tracking and recognizing complex multi-agent activities using probabilistic tracking coupled with graphical models for recognition. We employ statistical feature based particle filter to robustly track multiple objects in cluttered environments. Both color and shape characteristics are used to differentiate and track different objects so that low level visual information can be reliably extracted for recognition of complex activities. Such extracted spatio-temporal features are then used to build temporal graphical models for characterization of these activities. We demonstrate through examples in different scenarios, the generalizability and robustness of our framework.
ISBN:0769519008
9780769519005
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPRW.2003.10039