By Topic

An Adaptive Implementation of the Kernel-Based Object Tracking Method

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Weng Muyun ; Sch. of Electron. & Inf., Northwestern Polytech. Univ., Xi''an ; He Mingyi ; Zhang Yifan

Object tracking is one of the critical tasks in computer vision. The kernel-based object tracking (KBOT), employed an isotropic kernel to spatially mask the feature histogram-based target representations, is attractive for its ability toward to a real-time object tracking. In this paper, an adaptive dynamic updating principle of target model is proposed to improve the algorithm. Experiment results in implementation of the improved algorithm shown that the new method can improve the performance of the KBOT. Not only can it successfully cope with camera motion, background clutter, and target partial occlusions, rotation, scale variations, but also can be applied to rigid objects as well as nonrigid objects in visual tracking

Published in:

Innovative Computing, Information and Control, 2006. ICICIC '06. First International Conference on  (Volume:2 )

Date of Conference:

Aug. 30 2006-Sept. 1 2006