Probabilistic tracking in joint feature-spatial spaces

Ahmed Elgammal, Ramani Duraiswami, Larry S. Davis

Research output: Contribution to journalConference articlepeer-review

147 Scopus citations

Abstract

In this paper we present a probabilistic framework for tracking regions based on their appearance. We exploit the feature-spatial distribution of a region representing an object as a probabilistic constraint to track that region over time. The tracking is achieved by maximizing a similarity-based objective function over transformation space given a nonparametric representation of the joint feature-spatial distribution. Such a representation imposes a probabilistic constraint on the region feature distribution coupled with the region structure which yields an appearance tracker that is robust to small local deformations and partial occlusion. We present the approach for the general form of joint feature-spatial distributions and apply it to tracking with different types of image features including row intensity, color and image gradient.

Original languageEnglish (US)
Pages (from-to)I/781-I/788
JournalProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume1
StatePublished - 2003
Event2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Madison, WI, United States
Duration: Jun 18 2003Jun 20 2003

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Probabilistic tracking in joint feature-spatial spaces'. Together they form a unique fingerprint.

Cite this