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

Direct link
Very High Accuracy Velocity Estimation using Orientation Tensors, Parametric Motion, and Simultaneous Segmentation of the Motion Field
Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
2001 (English)In: Proceedings of the Eighth IEEE International Conference on Computer Vision: Vancouver, Canada, 2001, Vol. I, 171-177 p.Conference paper (Refereed)
Abstract [en]

In [Farnebäck00] we presented a new velocity estimation algorithm, using orientation tensors and parametric motion models to provide both fast and accurate results. One of the tradeoffs between accuracy and speed was that no attempts were made to obtain regions of coherent motion when estimating the parametric models. In this paper we show how this can be improved by doing a simultaneous segmentation of the motion field. The resulting algorithm is slower than the previous one, but more accurate. This is shown by evaluation on the well-known Yosemite sequence, where already the previous algorithm showed an accuracy which was substantially better than for earlier published methods. This result has now been improved further.

Place, publisher, year, edition, pages
2001. Vol. I, 171-177 p.
National Category
Engineering and Technology
URN: urn:nbn:se:liu:diva-21670OAI: diva2:246017
Available from: 2009-10-08 Created: 2009-10-05 Last updated: 2010-01-21

Open Access in DiVA

fulltext(225 kB)1125 downloads
File information
File name FULLTEXT01.pdfFile size 225 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Farnebäck, Gunnar
By organisation
Computer VisionThe Institute of Technology
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 1125 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

Total: 262 hits
ReferencesLink to record
Permanent link

Direct link