Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/22964
Title: New block-based motion estimation for sequences with illumination variation and its application to video mosaicking
Authors: Cheung, HK
Siu, WC 
Feng, D
Issue Date: 2005
Source: Proceedings - IEEE International Symposium on Circuits and Systems, 2005, 1465234, p. 2903-2906 How to cite?
Journal: Proceedings - IEEE International Symposium on Circuits and Systems 
Abstract: A new block-based local motion estimator independent from illumination variation is presented in this paper. Conventional motion estimator relies on an assumption that the difference between images is solely resulted from the motions activities. This hypothesis ignores another possibility that variation in the contents of image can be a result of the variation of the lighting condition. In this paper, a local motion estimator which is independent of the adverse influence of the distinct illumination condition is presented. The search space of the estimator is effectively restricted to dimension two which is identical to the conventional block-based motion estimation. To show the accuracy of our proposed estimator, it was applied to sprite generation which is relatively sensitive to the accuracy of the motion estimator. Experimental results show that our proposed system gives a better quality reconstructed images in terms of PSNR as compared with the system using conventional PDS estimator. Our estimator is particularly suitable in handling video sequences involving a strong variation of lighting conditions and is suitable for sprite coding application in MPEG-4.
Description: IEEE International Symposium on Circuits and Systems 2005, ISCAS 2005, Kobe, 23-26 May 2005
URI: http://hdl.handle.net/10397/22964
ISSN: 0271-4310
DOI: 10.1109/ISCAS.2005.1465234
Appears in Collections:Conference Paper

Access
View full-text via PolyU eLinks SFX Query
Show full item record

SCOPUSTM   
Citations

1
Last Week
0
Last month
0
Citations as of Jul 23, 2017

Page view(s)

24
Last Week
1
Last month
Checked on Jul 9, 2017

Google ScholarTM

Check

Altmetric



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.