Robust Locally Weighted Regression for Superresolution Enhancement of Multi-Angle Remote Sensing Imagery

Author

Jianglin Ma ; Chan, Jonathan Cheung-Wai ; Canters, F.

Author_Institution

Dept. of Geogr., Vrije Univ. Brussel, Brussels, Belgium

Volume

7

Issue

4

fYear

2014

fDate

Apr-14

Firstpage

1357

Lastpage

1371

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 WorldView-2 imagery and with real multi-angle WorldView-2 remote sensing images.

Keywords

approximation theory; geophysical image processing; image denoising; image enhancement; image resolution; image sensors; least squares approximations; regression analysis; remote sensing; series (mathematics); N-term Taylor series; SR enhancement; local image patch approximation; multiangle data simulation; multiangle remote sensing imagery; panchromatic World-View-2 imagery; real multiangle WorldView-2 remote sensing image; robust fitting procedure; robust locally weighted least-square kernel regression method; robust locally weighted regression; superresolution enhancement; Image reconstruction; Interpolation; Kernel; Remote sensing; Robustness; Spatial resolution; Kernel regression; WorldView-2; outlier detection; superresolution (SR);

fLanguage

English

Journal_Title

Selected Topics in Applied Earth Observations and Remote Sensing, IEEE Journal of

Publisher

ieee

ISSN

1939-1404

Type

jour

DOI

10.1109/JSTARS.2014.2312887

Filename

6784077