DocumentCode :
3199836
Title :
Target Tracking Using Mean Shift and Dynamic Directional Gradient Vector Flow
Author :
Babaeean, Amir ; Tashk, Alireza Bayesteh ; Barzin, Farzad ; Hosseini, Seyed Mohsen
Author_Institution :
Amirkabir Univ. of Technol., Tehran
fYear :
2008
fDate :
16-18 March 2008
Firstpage :
366
Lastpage :
370
Abstract :
In this paper, a new method for contour tracking of mobile target in low quality video sequence is presented. Proposed method helps to track variety of targets exactly while the camera is moving. In this study, a new type of active contour is used with a way for estimating motion model of the target. Estimating motion model of the target uses color and location information together. This information would cause our method not to be sensitive of aspect change. Our method is compared with two other methods: tracking via simple active contour and estimating motion model by using affine transform. Experimental results illustrate our method to outperform the prior ones.
Keywords :
affine transforms; gradient methods; image sequences; motion estimation; target tracking; affine transform; dynamic directional gradient vector flow; low quality video sequence; mean shift; mobile target contour tracking; motion estimation; target tracking; Active contours; Automotive engineering; Cameras; Face detection; Histograms; Humans; Motion estimation; Target tracking; Vehicle dynamics; Video sequences; Contour Tracking; DDGVF Model; Mean Shift;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
System Theory, 2008. SSST 2008. 40th Southeastern Symposium on
Conference_Location :
New Orleans, LA
ISSN :
0094-2898
Print_ISBN :
978-1-4244-1806-0
Electronic_ISBN :
0094-2898
Type :
conf
DOI :
10.1109/SSST.2008.4480256
Filename :
4480256
Link To Document :
بازگشت