Share Email Print

Proceedings Paper

A model updating algorithm based on moving area analyze
Author(s): Wei-ning Liu
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Model correlation matching with real time image is the main way in target tracking. The algorithm calculates the best matching position between the model and real-time image. The advantage of the algorithm is it has better matching result when the target model and real-time image are similar. The common updating algorithm based on matching degree of target which can be affected by target block or the speed change of target. And the matching results are badly affected by image background when the target is only a small part in the model which usually induce mismatch.A related area updating model algorithm is presented in this paper which combines the motion area analyze, image matching and the least cost estimation. A life parameter is set for every model. The life parameter is consumed according to the new moving area occurred in its neighborhood. The active model is matched to current image frame and its life parameter is set to max threshold Tmax. The algorithm is tested in video image sequences in which the max threshold Tmax of life parameter is set to 50. Good tracking effects are obtained in these tests.

Paper Details

Date Published: 21 August 2013
PDF: 6 pages
Proc. SPIE 8908, International Symposium on Photoelectronic Detection and Imaging 2013: Imaging Sensors and Applications, 89081A (21 August 2013); doi: 10.1117/12.2033238
Show Author Affiliations
Wei-ning Liu, Changchun Institute of Optics, Fine Mechanics and Physics (China)

Published in SPIE Proceedings Vol. 8908:
International Symposium on Photoelectronic Detection and Imaging 2013: Imaging Sensors and Applications
Jun Ohta; Nanjian Wu; Binqiao Li, Editor(s)

© SPIE. Terms of Use
Back to Top