Paper Info
Title
Adaptive visual tracking with reacquisition ability for arbitrary objects
Abstract
This paper introduces a novel tracking framework for robots that can adapt various appearance changes of object and also owns the ability of reacquisition after drift. Two classifiers, LaRank and Online Random Ferns, are adopted to realize this tracking algorithm. The former one maintains the adaptive tracking using a Condensation-based method with an online support vector machine (SVM) as observation model, which also provides the reliable image patch samples to detector for updating. The other one is in charge of the task of detection in order to redetect the object when the target drifts. We also present a refinement strategy to improve the tracker's performance by discarding the support vector corresponding to possible wrong updates by a matching template after re-initialization. The experiments on benchmark dataset compare our tracking method with several other state-of-the-art algorithms, demonstrating a promising performance of the proposed framework.
Year
DOI
Venue
2013
10.1109/ICRA.2013.6631254
ICRA
Keywords
Field
DocType
reacquisition ability,image matching,robots,matching template,online random ferns,online support vector machine,arbitrary objects,mobile robots,svm,reliable image patch samples,larank,image classification,observation model,object tracking,adaptive visual tracking,classifiers,refinement strategy,condensation-based method,support vector machines,robot vision,tv,reliability
Computer vision,Pattern recognition,Computer science,Image matching,Support vector machine,Eye tracking,Video tracking,Artificial intelligence,Contextual image classification,Robot,Detector,Mobile robot
Conference
Volume
Issue
ISSN
null
null
1050-4729
ISBN
Citations 
PageRank 
978-1-4673-5641-1
0
0.34
References 
Authors
14
4
Name
Order
Citations
PageRank
Tianyu Yang141.06
Baopu Li234830.88
Chao Hu300.34
Max Q.-H. Meng41477202.72