Affine models for image matching and motion detection
- 1 January 1991
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1350 (15206149), 2409-2412 vol.4
- https://doi.org/10.1109/icassp.1991.150878
Abstract
A model is developed for detecting the displacement field in spatiotemporal image sequences. It allows for affine shape deformations of corresponding spatial regions and for affine transformations of the image intensity range. The model includes the block matching method as a special case. A least-squares algorithm is used to find the model parameters. It is experimentally demonstrated that the affine matching model performs better than other standard approaches. The resulting 2-D motion estimates are then used by a 3-D affine model and a least-squares algorithm that recover 3-D rigid body motion and depth from two perspective views.Keywords
This publication has 9 references indexed in Scilit:
- Region-based optical flow estimationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Segmentation and 2-D motion estimation of noisy image sequencesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Affine morphology and affine signal modelsPublished by SPIE-Intl Soc Optical Eng ,1990
- A Pel-Recursive Wiener-Based Algorithm For The Simultaneous Estimation Of Rotation And TranslationPublished by SPIE-Intl Soc Optical Eng ,1988
- On the computation of motion from sequences of images-A reviewProceedings of the IEEE, 1988
- Advances in picture codingProceedings of the IEEE, 1985
- Uniqueness and Estimation of Three-Dimensional Motion Parameters of Rigid Objects with Curved SurfacesIEEE Transactions on Pattern Analysis and Machine Intelligence, 1984
- Determining optical flowArtificial Intelligence, 1981
- Motion-Compensated Television Coding: Part IBell System Technical Journal, 1979