By Topic

Using shape feature matching to track moving objects in image sequences

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

5 Author(s)
Hsu, D. ; Univ. of Southern California, Los Angeles, CA, USA ; Leu, J. ; Chen, S. ; Chang, W.
more authors

The paper develops a methodology to track moving objects in image sequences. The methodologies in tracking moving objects are influenced by the natural environment and motion characteristics. This paper introduces an algorithm to track moving objects under a natural environment (high noise ratio background). This algorithm can be applied from low noise ratio background to high noise ratio background. It also provides adjustable parameters to fit into different situations. It makes this algorithm flexible. The algorithm extracts moving objects by the difference between consecutive image frames and analyzes the shape features of moving objects. After shape analysis, the different moving objects are distinguished based on different shape feature characteristics including motion coordinate, speed, and direction. The original moving path can be found by coordinate transform. Some restrictions are applied. The moving object has to be a rigid body. The moving path has to be uni-directional. One camera is used which has to be stationary to take image sequences

Published in:

Multimedia and Expo, 2000. ICME 2000. 2000 IEEE International Conference on  (Volume:2 )

Date of Conference: