Simultaneous multiple optical flow estimation
Masahiko Shizawa, Kazuhiko Mase · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · 2002
The authors propose a simultaneous closed-form estimation method for multiple optical flow from image sequences in which each image point has multiple motions. This method only requires convolution for space-time filtering and low-dimensional eigensystem analysis as an optimization process. The authors propose a mixture flow model of a multiple flow and energy integral minimization as a model fitting method. It is shown that symmetry between component flows of the mixture flow can reduce the dimension of the eigensystem and make the optimization unimodal and stable. Successful experiments on double-flow estimation of random texture patterns and natural scene images are reported.>
Cited by 84 works. doi:10.1109/icpr.1990.118111
Authors
References
- A theory for multiresolution signal decomposition: the wavelet representation
- Theory of communication
- Determining optical flow
- Robot Vision
- The Interpretation of Visual Motion
- Mathematical Foundations of Quantum Mechanics
- Computational vision and regularization theory
- THE THEORY OF MATRICES IN NUMERICAL ANALYSIS
- Spatiotemporal energy models for the perception of motion
- Complete discrete 2-D Gabor transforms by neural networks for image analysis and compression