A drifting-proof framework for tracking and online appearance learning

Tony X. Han, Ming Liu, Thomas S. Huang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In order to avoid the notorious drifting problem for tracking system, a new integrated appearance learning framework is proposed in this paper. Previous tracking frameworks with appearance learning ability [3, 11] either require supervised offline training or will fail inevitably if the tracker locks on the background. While in our framework, no of-fline training is required. Given the location of the object in the first frame of the video sequence, we model the foreground (the image patch containing the object)/background difference as the transition cost in our tracking objective function. An tracker based on Dynamic Programming (DP) and template prediction [14] is carried out on the pixels with high foreground-likelihood. The typical views (i.e. appearance model) proposed by the tracker are used to initialize the states of a Hidden Markov Model (HMM). With the learned HMM, the tracking results and the appearance model can be further refined until the video sequence and all of these estimated parameters/hidden variables can be well explained by the HMM. Through this iterative procedure, typical views of the object, transition probabilities between the typical views, and location of the object are simultaneously estimated with strong confidence. The experiments show that the proposed framework achieves fairly satisfied results for several challenging video sequences and there-fore has many potential applications for video analysis.

Original languageEnglish (US)
Title of host publicationProceedings - IEEE Workshop on Applications of Computer Vision, WACV 2007
PublisherIEEE Computer Society
Pages10-15
Number of pages6
ISBN (Print)0769527949, 9780769527949
DOIs
StatePublished - 2007
Event7th IEEE Workshop on Applications of Computer Vision, WACV 2007 - Austin, TX, United States
Duration: Feb 21 2007Feb 22 2007

Publication series

NameProceedings - IEEE Workshop on Applications of Computer Vision, WACV 2007

Other

Other7th IEEE Workshop on Applications of Computer Vision, WACV 2007
Country/TerritoryUnited States
CityAustin, TX
Period2/21/072/22/07

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Software

Fingerprint

Dive into the research topics of 'A drifting-proof framework for tracking and online appearance learning'. Together they form a unique fingerprint.

Cite this