DocumentCode :
3428721
Title :
Robust KLT tracking with Gaussian and Laplacian of Gaussian weighting functions
Author :
Singh, Meghna ; Mandal, Mrinal ; Basu, Anup
Author_Institution :
Dept. of Electr. & Comput. Eng., Alberta Univ., Edmonton, Alta., Canada
Volume :
4
fYear :
2004
fDate :
23-26 Aug. 2004
Firstpage :
661
Abstract :
Object tracking algorithms extensively found in literature are either constrained with assumptions or are overly sensitive to noise. We propose and successfully test two new weighting functions for a feature-based object tracker to achieve superior tracking performance and noise immunity. The paper also presents a mechanism for image based optimal weighting function determination.
Keywords :
Gaussian processes; Karhunen-Loeve transforms; image processing; tracking; Gaussian weighting function; KLT tracking; Laplacian weighting function; image processing; object tracking algorithm; Clustering algorithms; Computer vision; Feature extraction; Humans; Iterative algorithms; Karhunen-Loeve transforms; Laplace equations; Motion analysis; Robustness; Tracking;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Pattern Recognition, 2004. ICPR 2004. Proceedings of the 17th International Conference on
ISSN :
1051-4651
Print_ISBN :
0-7695-2128-2
Type :
conf
DOI :
10.1109/ICPR.2004.1333859
Filename :
1333859
Link To Document :
بازگشت