Foveated multiscale models for large-scale estimation

TitleFoveated multiscale models for large-scale estimation
Publication TypeConference Paper
Year of Publication1999
AuthorsFieguth, P.
Conference NameInternational Conference on Image Processing
Keywordsasymptotic computational properties, computational complexity, conditional decorrelation, decorrelation, divide and conquer methods, divide-and-conquer strategy, foveated multiscale models, global-scale-remote sensing problems, image processing, large-scale estimation methods, multiscale estimation, nested dissection, numerical stability, statistical problem, three-dimensional problems

Efficient, large-scale estimation methods such as nested dissection or multiscale estimation rely on a divide-and-conquer strategy, in which a statistical problem is conditionally broken into smaller pieces. This conditional decorrelation is not possible for arbitrarily large problems due to issues of computational complexity and numerical stability. Given the growing interest in global-scale-remote sensing problems (or even three-dimensional problems), in this summary we develop a class of estimators with more promising asymptotic computational properties