A Statistical Approach to Structure and Motion from Image Features
(1998) Advances in Pattern Recognition. Joint IAPR International Workshops. SSPR'98 and SPR'98. Proceedings p.929-936- Abstract
- The estimation of structure and motion from image sequences using corresponding points, lines, conics and structured patches is treated. Recent research has provided good tools for obtaining good initial estimates of structure and motion using point, line, conic and curve correspondences. These estimates are, however, not so accurate. It is shown how to obtain statistically optimal estimates of structure and motion using a combination of such image feature correspondences. The question of using proper weighting is important when different types of features are combined. We show how weights can be chosen in a statistical optimal sense. Experiments with real data are used to evaluate every step of the algorithm
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/787603
- author
- Åström, Karl LU ; Kahl, Fredrik LU ; Heyden, Anders LU and Berthilsson, Rikard LU
- organization
- publishing date
- 1998
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- computational geometry, image motion analysis, image sequences. statistical analysis
- host publication
- [Host publication title missing]
- pages
- 929 - 936
- publisher
- Springer
- conference name
- Advances in Pattern Recognition. Joint IAPR International Workshops. SSPR'98 and SPR'98. Proceedings
- conference location
- Sydney, NSW, Australia
- conference dates
- 1998-08-11 - 1998-08-13
- external identifiers
-
- scopus:84947745451
- ISBN
- 3 540 64858 5
- language
- English
- LU publication?
- yes
- id
- 9dbabe0e-85ed-42e4-bedd-a4b9e875b3e9 (old id 787603)
- date added to LUP
- 2016-04-04 10:47:42
- date last changed
- 2023-09-06 07:34:21
@inproceedings{9dbabe0e-85ed-42e4-bedd-a4b9e875b3e9, abstract = {{The estimation of structure and motion from image sequences using corresponding points, lines, conics and structured patches is treated. Recent research has provided good tools for obtaining good initial estimates of structure and motion using point, line, conic and curve correspondences. These estimates are, however, not so accurate. It is shown how to obtain statistically optimal estimates of structure and motion using a combination of such image feature correspondences. The question of using proper weighting is important when different types of features are combined. We show how weights can be chosen in a statistical optimal sense. Experiments with real data are used to evaluate every step of the algorithm}}, author = {{Åström, Karl and Kahl, Fredrik and Heyden, Anders and Berthilsson, Rikard}}, booktitle = {{[Host publication title missing]}}, isbn = {{3 540 64858 5}}, keywords = {{computational geometry; image motion analysis; image sequences. statistical analysis}}, language = {{eng}}, pages = {{929--936}}, publisher = {{Springer}}, title = {{A Statistical Approach to Structure and Motion from Image Features}}, year = {{1998}}, }