Toward a robust parametric identification of motion on regions of arbitrary shape by nonlinear optimization
暂无分享,去创建一个
This paper highlights some problems related to the identification of parametric motion models in image sequences by the so-called differential methods. This often entails the bad behavior of the algorithms used, leading to poor results. Appropriate solutions are proposed. The differential algorithms are particularly effective for complex motion estimation, even of large magnitude.
[1] Jean-Luc Dugelay,et al. Differential methods for the identification of 2D and 3D motion models in image sequences , 1995, Signal Process. Image Commun..
[2] W. Murray. Numerical Methods for Unconstrained Optimization , 1975 .
[3] J. Z. Zhu,et al. The finite element method , 1977 .