Share Email Print
cover

Proceedings Paper

Relational graph matching for human detection and posture recognition
Author(s): Ibrahim Burak Ozer; Wayne H. Wolf; Ali Naci Akansu
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

This paper describes a relational graph matching with model-based segmentation for human detection. The matching result is used for the decision of human presence in the image as well as for posture recognition. We extend our previous work for rigid object detection in still images and video frames by modeling parts with superellipses and by using multi-dimensional Bayes classification in order to determine the non-rigid body parts under the assumption that the unary and binary (relational) features belonging to the corresponding parts are Gaussian distributed. The major contribution of the proposed method is to create automatically semantic segments from the combination of low level edge or region based segments using model-based segmentation. The generality of the reference model part attributes allows detection of human with different postures while the conditional rule generation decreases the rate of false alarms.

Paper Details

Date Published: 11 October 2000
PDF: 12 pages
Proc. SPIE 4210, Internet Multimedia Management Systems, (11 October 2000); doi: 10.1117/12.403798
Show Author Affiliations
Ibrahim Burak Ozer, New Jersey Institute of Technology (United States)
Wayne H. Wolf, Princeton Univ. (United States)
Ali Naci Akansu, New Jersey Institute of Technology (United States)


Published in SPIE Proceedings Vol. 4210:
Internet Multimedia Management Systems
John R. Smith; Chinh Le; Sethuraman Panchanathan; C.-C. Jay Kuo, Editor(s)

© SPIE. Terms of Use
Back to Top