|
Robust locally weighted regression for supperresolution enhancement of multi-angle remote sensing imagery This publication appears in: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Authors: J. Ma, J. C-W Chan and F. Canters Volume: 7 Issue: 4 Pages: 1357-1371 Publication Date: Apr. 2014
Abstract: This paper presents a robust locally weighted least-squares kernel regression method for superresolution (SR) enhancement of multi-angle remote sensing imagery. The method is based on the concept of kernel-based regression, where the local image patch is approximated by an mbiN-term Taylor series. To reduce the impact of high frequency noise on SR performance, a robust fitting procedure is adopted. The approach proposed is tested with simulated multi-angle data derived from panchromatic WorldViewDŽ imagery and with real multi-angle WorldViewDŽ remote sensing images.
|
