Shape from rotation
- 10 December 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 625-631
- https://doi.org/10.1109/cvpr.1991.139764
Abstract
The construction of a 3D surface model of an object rotating in front of a camera is examined. Previous research in depth from motion has demonstrated the power of using an incremental approach to depth estimation. The author extends this approach to more general motion and uses a full 3D surface model instead of a 2 1/2 D depth map. The algorithm starts with a flow field computed using local correlation. It then projects individual measurements into 3D points with associated uncertainties. Nearby points from successive frames are merged to improve the position estimates. These points are then used to construct a deformable surface model, which is refined over time. The application of novel techniques to several image sequences is demonstrated.Keywords
This publication has 13 references indexed in Scilit:
- Estimating Motion From Sparse Range Data Without CorrespondencePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- The dynamic analysis of apparent contoursPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Using occluding contours for 3D object modelingPublished by Springer Nature ,1990
- Kalman filter-based algorithms for estimating depth from image sequencesInternational Journal of Computer Vision, 1989
- Generalizing Epipolar-Plane Image Analysis on the spatiotemporal surfaceInternational Journal of Computer Vision, 1989
- Bayesian Modeling of Uncertainty in Low-Level VisionPublished by Springer Nature ,1989
- On the estimation of optical flow: Relations between different approaches and some new resultsArtificial Intelligence, 1987
- Epipolar-plane image analysis: An approach to determining structure from motionInternational Journal of Computer Vision, 1987
- Perceptual organization and the representation of natural formArtificial Intelligence, 1986
- Three-dimensional object recognitionACM Computing Surveys, 1985