Digital processing of random signals: theory and methods
Digital processing of random signals: theory and methods
Computer Vision
Shape from Texture for Smooth Curved Surfaces
ECCV '92 Proceedings of the Second European Conference on Computer Vision
An estimation algorithm for 2-D polynomial phase signals
IEEE Transactions on Image Processing
| Hi-index | 0.00 |
This paper considers the problem of parametric modelingand estimation of nonhomogeneous two-dimensional (2-D) signals.In particular, we focus our study on the class of constant moduluspolynomial-phase 2-D nonhomogeneous signals. We present two differentphase models and develop computationally efficient estimationalgorithms for the parameters of these models. Both algorithmsare based on phase differencing operators. The basic propertiesof the operators are analyzed and used to develop the estimationalgorithms. The Cramer-Rao lower bound on the accuracy of jointlyestimating the model parameters is derived, for both models.To get further insight on the problem we also derive the asymptoticCramer-Rao bounds. The performance of the algorithms in the presenceof additive white Gaussian noise is illustrated by numericalexamples, and compared with the corresponding exact and asymptoticCramer-Rao bounds. The algorithms are shown to be robust in thepresence of noise, and their performance close to the CRB, evenat moderate signal to noise ratios.