Please use this identifier to cite or link to this item: http://hdl.handle.net/2440/108099
Citations
Scopus Web of Science® Altmetric
?
?
Type: Journal article
Title: Online metric-weighted linear representations for robust visual tracking
Author: Li, X.
Shen, C.
Dick, A.
Zhang, Z.
Zhuang, Y.
Citation: IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016; 38(5):931-950
Publisher: IEEE
Issue Date: 2016
ISSN: 0162-8828
1939-3539
Statement of
Responsibility: 
Xi Li, Chunhua Shen, Anthony Dick, Zhongfei (Mark) Zhang and Yueting Zhuang
Abstract: In this paper, we propose a visual tracker based on a metric-weighted linear representation of appearance. In order to capture the interdependence of different feature dimensions, we develop two online distance metric learning methods using proximity comparison information and structured output learning. The learned metric is then incorporated into a linear representation of appearance. We show that online distance metric learning significantly improves the robustness of the tracker, especially on those sequences exhibiting drastic appearance changes. In order to bound growth in the number of training samples, we design a time-weighted reservoir sampling method. Moreover, we enable our tracker to automatically perform object identification during the process of object tracking, by introducing a collection of static template samples belonging to several object classes of interest. Object identification results for an entire video sequence are achieved by systematically combining the tracking information and visual recognition at each frame. Experimental results on challenging video sequences demonstrate the effectiveness of the method for both inter-frame tracking and object identification.
Keywords: Visualization; reservoirs; robustness; tracking; correlation; optimization; visual tracking; linear representation; structured metric learning; reservoir sampling
Rights: © 2015 IEEE.
RMID: 0030047804
DOI: 10.1109/TPAMI.2015.2469276
Appears in Collections:Computer Science publications

Files in This Item:
File Description SizeFormat 
RA_hdl_108099.pdfRestricted Access2.9 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.