Share Email Print

Proceedings Paper

Multitarget tracking system using texture
Author(s): Jun Geun Jeon; Young Ho Kim; Goo Man Park; Kyu Tae Park
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

A new method to detect and track non-rigid moving objects against a moving background is presented. In order to discriminate objects from background optical flow based segmentation methods are not appropriate for the case of non-rigid as they have non-uniform optical flow. The proposed method uses optical flow nd texture similarity to discriminate objects from the background. A well-known algorithm from neural networks, Kohonen's self-organizing maps, was adapted to measure the texture similarity.

Paper Details

Date Published: 10 January 1997
PDF: 8 pages
Proc. SPIE 3024, Visual Communications and Image Processing '97, (10 January 1997); doi: 10.1117/12.263234
Show Author Affiliations
Jun Geun Jeon, Yonsei Univ. (South Korea)
Young Ho Kim, Yonsei Univ. (South Korea)
Goo Man Park, Honam Univ. (South Korea)
Kyu Tae Park, Yonsei Univ. (South Korea)

Published in SPIE Proceedings Vol. 3024:
Visual Communications and Image Processing '97
Jan Biemond; Edward J. Delp III, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?