Spatio-Temporal Auxiliary Particle Filtering With l(1)-Norm-Based Appearance Model Learning for Robust Visual Tracking

Kim, D and Jeon, M 2013, 'Spatio-Temporal Auxiliary Particle Filtering With l(1)-Norm-Based Appearance Model Learning for Robust Visual Tracking', IEEE Transactions on Image Processing, vol. 22, no. 2, pp. 511-522.


Document type: Journal Article
Collection: Journal Articles

Title Spatio-Temporal Auxiliary Particle Filtering With l(1)-Norm-Based Appearance Model Learning for Robust Visual Tracking
Author(s) Kim, D
Jeon, M
Year 2013
Journal name IEEE Transactions on Image Processing
Volume number 22
Issue number 2
Start page 511
End page 522
Total pages 12
Publisher Institute of Electrical and Electronics Engineers
Abstract In this paper, we propose an efficient and accurate visual tracker equipped with a new particle filtering algorithm and robust subspace learning-based appearance model. The proposed visual tracker avoids drifting problems caused by abrupt motion changes and severe appearance variations that are well-known difficulties in visual tracking. The proposed algorithm is based on a type of auxiliary particle filtering that uses a spatio-temporal sliding window. Compared to conventional particle filtering algorithms, spatio-temporal auxiliary particle filtering is computationally efficient and successfully implemented in visual tracking. In addition, a real-time robust principal component pursuit (RRPCP) equipped with l 1 -norm optimization has been utilized to obtain a new appearance model learning block for reliable visual tracking especially for occlusions in object appearance. The overall tracking framework based on the dual ideas is robust against occlusions and out-of-plane motions because of the proposed spatio-temporal filtering and recursive form of RRPCP. The designed tracker has been evaluated using challenging video sequences, and the results confirm the advantage of using this tracker.
Subject Image Processing
Keyword(s) Particle filtering
Subspace learning
Visual tracking
DOI - identifier 10.1109/TIP.2012.2218824
Copyright notice © 2012 IEEE.
ISSN 1057-7149
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 12 times in Thomson Reuters Web of Science Article | Citations
Scopus Citation Count Cited 0 times in Scopus Article
Altmetric details:
Access Statistics: 6 Abstract Views  -  Detailed Statistics
Created: Thu, 31 Jan 2019, 11:26:00 EST by Catalyst Administrator
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us