Robust real-time visual tracking using pixel-wise posteriors
Date
2008
Authors
Bibby, C.
Reid, I.
Editors
Forsyth, D.
Torr, P.
Zisserman, A.
Torr, P.
Zisserman, A.
Advisors
Journal Title
Journal ISSN
Volume Title
Type:
Conference paper
Citation
Lecture Notes in Artificial Intelligence, 2008 / Forsyth, D., Torr, P., Zisserman, A. (ed./s), vol.5303 LNCS, iss.PART 2, pp.831-844
Statement of Responsibility
Charles Bibby and Ian Reid
Conference Name
10th European Conference on Computer Vision (ECCV) (12 Oct 2008 - 18 Oct 2008 : Marseille, France)
Abstract
We derive a probabilistic framework for robust, real-time, visual tracking of previously unseen objects from a moving camera. The tracking problem is handled using a bag-of-pixels representation and comprises a rigid registration between frames, a segmentation and online appearance learning. The registration compensates for rigid motion, segmentation models any residual shape deformation and the online appearance learning provides continual refinement of both the object and background appearance models. The key to the success of our method is the use of pixel-wise posteriors, as opposed to likelihoods. We demonstrate the superior performance of our tracker by comparing cost function statistics against those commonly used in the visual tracking literature. Our comparison method provides a way of summarising tracking performance using lots of data from a variety of different sequences.
School/Discipline
Dissertation Note
Provenance
Description
Access Status
Rights
© Springer-Verlag Berlin Heidelberg 2008