liu.seSearch for publications in DiVA
Change search
ReferencesLink to record
Permanent link

Direct link
Enhanced Distribution Field Tracking using Channel Representations
Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.ORCID iD: 0000-0002-6096-3648
2013 (English)In: Proceedings of the IEEE International Conference on Computer Vision Workshops (ICCVW), 2013, IEEE conference proceedings, 2013, 121-128 p.Conference paper (Refereed)
Abstract [en]

Visual tracking of objects under varying lighting conditions and changes of the object appearance, such as articulation and change of aspect, is a challenging problem. Due to its robustness and speed, distribution field tracking is among the state-of-the-art approaches for tracking objects with constant size in grayscale sequences. According to the theory of averaged shifted histograms, distribution fields are an approximation of kernel density estimates. Another, more efficient approximation are channel representations, which are used in the present paper to derive an enhanced  computational scheme for tracking. This enhanced distribution field tracking method outperforms several state-ofthe-art methods on the VOT2013 challenge, which evaluates accuracy, robustness, and speed.

Place, publisher, year, edition, pages
IEEE conference proceedings, 2013. 121-128 p.
National Category
Engineering and Technology
URN: urn:nbn:se:liu:diva-100449DOI: 10.1109/ICCVW.2013.22ISI: 000349847200017ISBN: 978-1-4799-3022-7OAI: diva2:662687
ICCV 2013 - 14th International Conference on Computer Vision (ICCV2013), Workshop on visual object tracking challenge, December 2, Sydney, Australia
Available from: 2013-11-08 Created: 2013-11-08 Last updated: 2016-06-08Bibliographically approved

Open Access in DiVA

fulltext(688 kB)731 downloads
File information
File name FULLTEXT01.pdfFile size 688 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Other links

Publisher's full text

Search in DiVA

By author/editor
Felsberg, Michael
By organisation
Computer VisionThe Institute of Technology
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 731 downloads
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

Altmetric score

Total: 542 hits
ReferencesLink to record
Permanent link

Direct link