Fast and accurate motion estimation using orientation tensors and parametric motion models
- 11 November 2002
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 135-139
- https://doi.org/10.1109/icpr.2000.905291
Abstract
Motion estimation in image sequences is an important step in many computer vision and image processing applications. Several methods for solving this problem have been proposed, but very few manage to achieve a high level of accuracy without sacrificing processing speed. This paper presents a novel motion estimation algorithm, which gives excellent results on both counts. The algorithm starts by computing 3D orientation tensors from the image sequence. These are combined under the constraints of a parametric motion model to produce velocity estimates. Evaluated on the well-known Yosemite sequence, the algorithm shows an accuracy, which is substantially better than for previously, published methods. Computationally the algorithm is simple and can be implemented by means of sep-arable convolutions, which makes it fast.Keywords
This publication has 11 references indexed in Scilit:
- Reliable and Efficient Computation of Optical FlowInternational Journal of Computer Vision, 1998
- Estimating optical flow in segmented images using variable-order parametric models with local deformationsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1996
- The Robust Estimation of Multiple Motions: Parametric and Piecewise-Smooth Flow FieldsComputer Vision and Image Understanding, 1996
- Skin and bones: multi-layer, locally affine, optical flow and regularization with transparencyPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1996
- Signal Processing for Computer VisionPublished by Springer Nature ,1995
- Performance of optical flow techniquesInternational Journal of Computer Vision, 1994
- Hierarchical spline-based image registrationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1994
- Computation of component image velocity from local phase informationInternational Journal of Computer Vision, 1990
- A computational approach to motion perceptionBiological Cybernetics, 1988
- Model for the extraction of image flowJournal of the Optical Society of America A, 1987