Change search
ReferencesLink to record
Permanent link

Direct link
Learning image statistics for Bayesian tracking
KTH, Superseded Departments, Numerical Analysis and Computer Science, NADA.ORCID iD: 0000-0002-5750-9655
2001 (English)In: Proceedings of the IEEE International Conference on Computer Vision, 2001, 709-716 p.Conference paper (Refereed)
Abstract [en]

This paper describes a framework for learning probabilistic models of objects and scenes and for exploiting these models for tracking complex, deformable, or articulated objects in image sequences. We focus on the probabilistic tracking of people and learn models of how they appear and move in images. In particular, we learn the likelihood of observing various spatial and temporal filter responses corresponding to edges, ridges, and motion differences given a model of the person. Similarly, we learn probability distributions over filter responses for general scenes that define a likelihood of observing the filter responses for arbitrary backgrounds. We then derive a probabilistic model for tracking that exploits the ratio between the likelihood that image pixels corresponding to the foreground (person) were generated by an actual person or by some unknown background. The paper extends previous work on learning image statistics and combines it with Bayesian tracking using particle filtering. By combining multiple image cues, and by using learned likelihood models, we demonstrate improved robustness and accuracy when tracking complex objects such as people in monocular image sequences with cluttered scenes and a moving camera.

Place, publisher, year, edition, pages
2001. 709-716 p.
, Proceedings of the IEEE International Conference on Computer Vision, 2
National Category
Computer and Information Science
URN: urn:nbn:se:kth:diva-38209OAI: diva2:436235
8th International Conference on Computer Vision; Vancouver, BC; 9 July 2001 through 12 July 2001
Available from: 2011-08-22 Created: 2011-08-22 Last updated: 2011-09-12Bibliographically approved

Open Access in DiVA

No full text

Search in DiVA

By author/editor
Sidenbladh, Hedvig
By organisation
Numerical Analysis and Computer Science, NADA
Computer and Information Science

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 51 hits
ReferencesLink to record
Permanent link

Direct link