Skip to main content

Research Repository

Advanced Search

Fast and robust appearance-based tracking

Liwicki, Stephan; Zafeiriou, Stefanos; Tzimiropoulos, Georgios; Pantic, Maja


Stephan Liwicki

Stefanos Zafeiriou

Georgios Tzimiropoulos

Maja Pantic


We introduce a fast and robust subspace-based approach to appearance-based object tracking. The core of our approach is based on Fast Robust Correlation (FRC), a recently proposed technique for the robust estimation of large translational displacements. We show how the basic principles of FRC can be naturally extended to formulate a robust version of Principal Component Analysis (PCA) which can be efficiently implemented incrementally and therefore is particularly suitable for robust real-time appearance-based object tracking. Our experimental results demonstrate that the proposed approach outperforms other state-of-the-art holistic appearance-based trackers on several popular video sequences.


Liwicki, S., Zafeiriou, S., Tzimiropoulos, G., & Pantic, M. (2011). Fast and robust appearance-based tracking

Conference Name 2011 IEEE International Conference on Automatic Face & Gesture Recognition (FG 2011)
End Date Mar 25, 2011
Publication Date Mar 1, 2011
Deposit Date Feb 1, 2016
Publicly Available Date Feb 1, 2016
Peer Reviewed Peer Reviewed
Keywords Correlation methods, Estimation theory, Image sequences, Object tracking, Principal component analysis
Public URL
Publisher URL
Copyright Statement Copyright information regarding this work can be found at the following address:
Additional Information © 2011 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.


tzimiroFG11B.pdf (596 Kb)

Copyright Statement
Copyright information regarding this work can be found at the following address:

Downloadable Citations