A Robust Video Object Tracking by Using Active Contours

In this paper, we propose a novel object tracking algorithm in video sequences. The formulation of our tracking model is based on variational calculus, where region and boundary information cooperate for object boundary localization by using active contours. In the approach, only the segmentation of...

Full description

Saved in:
Bibliographic Details
Main Authors: Allili, M.S., Ziou, D.
Format: Conference Proceeding
Language:English
Subjects:
Active contours
Application software
Calculus
Computer vision
Level set
Object detection
Robustness
Tracking
Video sequences
Video surveillance
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, we propose a novel object tracking algorithm in video sequences. The formulation of our tracking model is based on variational calculus, where region and boundary information cooperate for object boundary localization by using active contours. In the approach, only the segmentation of the objects in the first frame is required for initialization. The evolution of the object contours on a current frame aims to find the boundary of the objects by minimizing the Kullback-Leibler distance of the region features distribution in the vicinity of the contour to the objects versus the background respectively. We show the effectiveness of the approach on examples of object tracking performed on real video sequences.
ISSN:2160-7508
2160-7516
DOI:10.1109/CVPRW.2006.20