Gowramma Y.P.1*, RaviKumar C.N.2*
1Dept. of CSE, Kalpataru Institute of Tech, Tiptur-572202, Karnataka, India
2Dept of CSE, SJ college of Engineering ,Mysore ,Karnataka, India
* Corresponding Author : kumarcnr@yahoo.co.in
Received : - Accepted : - Published : 15-06-2010
Volume : 1 Issue : 1 Pages : 7 - 12
J Signal Image Process 1.1 (2010):7-12
This paper presents an algorithm to identify the correspondence of objects in the flickering or fluctuating environment for the dynamic image analysis. The correspondence is the matching of the similar data sets or entities or the features such as the points, corners, edges between a set of images. The correspondence of the features between the set of images is the central crucial fundamental evergreen open key problem in the Computer Vision (CV) and Pattern Recognition (PR) domain. The Correspondence of the dynamic images in the flickering environment and the flickering object is a highly challenging problem. In this domain Correspondence of features is a high dimensional NP-hard problem, because of their exhaustive search for the features in the sequence of image frames. The current algorithm works on the successive frame difference based segmentation, threshold based binary conversion and 2 dimensional 8-connectivity based correspondence. This work proposes the tracking window, generated dynamically which depends on the size of the object in the current frame. Here we have considered every element present in the segmented region as the features. The experiment is carried out on image sequence having multiple objects moving independently. This experiment is carried out on the gray scale dynamic image sequence, RGB color image sequence and on the binary image sequence. This correspondence algorithm is especially suitable for tracking in indoor images illuminated by unconstrained multiple light sources, objects in the varying illumination environment, noisy image sequence, video surveillance and slow moving dynamic image sequence for indoor scenes of the constant background.
[1] Payman Moallem, Karim Faez (2001)
VMV 2001,Stutgart, Germany
» CrossRef » Google Scholar » PubMed » DOAJ » CAS » Scopus
[2] Liu Hao, ZHANG Wen-jun, CAI Jun
Journal of Zhejiang University
Science
» CrossRef » Google Scholar » PubMed » DOAJ » CAS » Scopus
[3] Zhou Wang, Yinglin Yu and David
Zhang (1998) IEEE Transaction on
IP, 7(7), 1057-1061
» CrossRef » Google Scholar » PubMed » DOAJ » CAS » Scopus
[4] Steven M. Seitz, Charles R. Dyer
(1995) Proc.Fifth Int.Conf.On
Computer Vision, Cambridge MA,
330-337
» CrossRef » Google Scholar » PubMed » DOAJ » CAS » Scopus
[5] Banon and SergioDonizete Faria
(2001) Proc 8th ECS and Image
Analysis,Bordeaux, France, 573-
577
» CrossRef » Google Scholar » PubMed » DOAJ » CAS » Scopus
[6] Tham J.Y., Ranganath S., Ranganath
M. and Kasa A.A. (1998)
IEEETrans.CircuitsSyst.Technol.,
8(4), 369-377
» CrossRef » Google Scholar » PubMed » DOAJ » CAS » Scopus
[7] Cheung C.H. and Po L.M. (2002) IEEE
Circuits Syst.Video Technol.,
12(12).
» CrossRef » Google Scholar » PubMed » DOAJ » CAS » Scopus
[8] Cheung C.H. and Po L.M. (2002)
Proc.IEEE ICIP
» CrossRef » Google Scholar » PubMed » DOAJ » CAS » Scopus
[9] Yao Nie, Kai-Kuang Ma (2002) IEEE
Trans. Image processing 11, 1442-
1449
» CrossRef » Google Scholar » PubMed » DOAJ » CAS » Scopus
[10] Anastasios Hamosfakidis, Yakup Paker
(2002) EURASIP Journal on Applied
Signal Processing, 6,595-600
» CrossRef » Google Scholar » PubMed » DOAJ » CAS » Scopus
[11] RaviKumar C.N. and Gowramma Y.P.
(2001) NCMCM-2001, 339-344
» CrossRef » Google Scholar » PubMed » DOAJ » CAS » Scopus
[12] Ravi Kumar C.N. and Gowramma Y.P.
(2002) NCAC-2002, 231-238
» CrossRef » Google Scholar » PubMed » DOAJ » CAS » Scopus
[13] Gowramma Y.P. and Ravi Kumar C.N.
(2006) ADCOM-2006, 263-266
» CrossRef » Google Scholar » PubMed » DOAJ » CAS » Scopus