AMNE:(NATURAL SCIENCES) AMNE:(Computer and Information Sciences) AMNE:(Computer Vision and Robotics)
Search: AMNE:(NATURAL SCIENCES) AMNE:(Computer and Information Sciences) AMNE:(Computer Vision and Robotics) > (1995-1999) > Direct estimation o...
- 10 of 62
- Previous record
- Next record
- To hitlist
- Lindeberg, Tony,1964-KTH,Numerisk analys och datalogi, NADA (author)
Direct estimation of affine image deformations using visual front-end operations with automatic scale selection
- Article/chapterEnglish1995
Publisher, publication year, extent ...
- IEEE Computer Society,1995
- electronicrdacarrier
Numbers
- LIBRIS-ID:oai:DiVA.org:kth-58611
- https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-58611URI
- https://doi.org/10.1109/ICCV.1995.466795DOI
Supplementary language notes
- Language:English
- Summary in:English
Part of subdatabase
- SwePubSwePub
Classification
Notes
- Qc 20130419
- This article deals with the problem of estimating deformations of brightness patterns using visual front-end operations. Estimating such deformations constitutes an important subtask in several computer vision problems relating to image correspondence and shape estimation. The following subjects are treated: The problem of decomposing affine flow fields into simpler components is analysed in detail. A canonical parametrization is presented based on singular value decomposition, which naturally separates the rotationally invariant components of the flow field from the rotationally variant ones. A novel mechanism is presented for automatic selection of scale levels when estimating local affine deformations. This mechanism is expressed within a multi-scale framework where disparity estimates are computed in a hierarchical coarse-to-fine manner and corrected using iterative techniques. Then, deformation estimates are selected from the scales that minimize a certain normalized residual over scales. Finally, the descriptors so obtained serve as initial data for computing refined estimates of the local deformations.
Subject headings and genre
- NATURVETENSKAP Data- och informationsvetenskap Datavetenskap hsv//swe
- NATURAL SCIENCES Computer and Information Sciences Computer Sciences hsv//eng
- NATURVETENSKAP Data- och informationsvetenskap Datorseende och robotik hsv//swe
- NATURAL SCIENCES Computer and Information Sciences Computer Vision and Robotics hsv//eng
- affine transformation
- scale selection
- image correspondence
- optic flow
- shape estimation
- stereo
- motion
- texture
- disparity
- vergence
- invariance
- deformation
- decomposition
- singular value
- second moment matrix
- surface model
- enforced consistency
- visual front-end
- scale-space
- computer vision
Added entries (persons, corporate bodies, meetings, titles ...)
- KTHNumerisk analys och datalogi, NADA (creator_code:org_t)
Related titles
- In:Proc. 5th International Conference on Computer Vision: IEEE Computer Society, s. 134-141
Internet link
- http://www.nada.kth.se/cvap/abstracts/cvap170.htmlAt author's home page
- http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=466795IEEEXplore
- https://kth.diva-portal.org/smash/get/diva2:473428/FULLTEXT01.pdffulltext:preprint
- https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-58611
- https://doi.org/10.1109/ICCV.1995.466795
To the university's database
- 10 of 62
- Previous record
- Next record
- To hitlist
Find more in SwePub
- By the author/editor
- Lindeberg, Tony, ...
- About the subject
-
- NATURAL SCIENCES
- NATURAL SCIENCES
- and Computer and Inf ...
- and Computer Science ...
-
- NATURAL SCIENCES
- NATURAL SCIENCES
- and Computer and Inf ...
- and Computer Vision ...
- Articles in the publication
- Proc. 5th Intern ...
- By the university
- Royal Institute of Technology
Search outside SwePub
- Extend your search to:
- Google Book Search
- Google Scholar
Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.
- Copyright © LIBRIS - National Library Systems
- LIBRIS.kb.se
