Improving super-resolution mapping through combining multiple super-resolution land-cover maps

Super-resolution mapping (SRM) is an ill-posed problem, and different SRM algorithms may generate non-identical fine spatial resolution land-cover maps (sub-pixel maps) from the same input coarse spatial resolution image. The output sub-pixels maps may each have differing strengths and weaknesses. A...

Full description

Bibliographic Details
Main Authors: Li, Xiaodong, Ling, Feng, Foody, Giles M., Du, Yun
Format: Article
Published: Taylor and Francis 2016
Subjects:
Online Access:https://eprints.nottingham.ac.uk/32952/
_version_ 1848794526951407616
author Li, Xiaodong
Ling, Feng
Foody, Giles M.
Du, Yun
author_facet Li, Xiaodong
Ling, Feng
Foody, Giles M.
Du, Yun
author_sort Li, Xiaodong
building Nottingham Research Data Repository
collection Online Access
description Super-resolution mapping (SRM) is an ill-posed problem, and different SRM algorithms may generate non-identical fine spatial resolution land-cover maps (sub-pixel maps) from the same input coarse spatial resolution image. The output sub-pixels maps may each have differing strengths and weaknesses. A multiple SRM (M-SRM) method that combines the sub-pixel maps obtained from a set of SRM analyses, obtained from a single or multiple set of algorithms, is proposed in this study. Plurality voting, which selects the class with the most votes, is used to label each sub-pixel. In this study, three popular SRM algorithms, namely, the pixel swapping algorithm (PSA), the Hopfield neural network (HNN) algorithm, and Markov random field (MRF) based algorithm, were used. The proposed M-SRM algorithm was validated using two data sets: a simulated multi-spectral image and an airborne visible/infrared imaging spectrometer (AVIRIS) hyperspectral image. Results show that the highest overall accuracies were obtained by M-SRM in all experiments. For example, in the AVIRIS image experiment, the highest overall accuracies of PSA, HNN and MRF were 88.89%, 93.81% and 82.70% respectively, and increased to 95.06%, 95.37% and 85.56% respectively for M-SRM obtained from the multiple PSA, HNN and MRF analyses.
first_indexed 2025-11-14T19:17:36Z
format Article
id nottingham-32952
institution University of Nottingham Malaysia Campus
institution_category Local University
last_indexed 2025-11-14T19:17:36Z
publishDate 2016
publisher Taylor and Francis
recordtype eprints
repository_type Digital Repository
spelling nottingham-329522020-05-04T17:52:55Z https://eprints.nottingham.ac.uk/32952/ Improving super-resolution mapping through combining multiple super-resolution land-cover maps Li, Xiaodong Ling, Feng Foody, Giles M. Du, Yun Super-resolution mapping (SRM) is an ill-posed problem, and different SRM algorithms may generate non-identical fine spatial resolution land-cover maps (sub-pixel maps) from the same input coarse spatial resolution image. The output sub-pixels maps may each have differing strengths and weaknesses. A multiple SRM (M-SRM) method that combines the sub-pixel maps obtained from a set of SRM analyses, obtained from a single or multiple set of algorithms, is proposed in this study. Plurality voting, which selects the class with the most votes, is used to label each sub-pixel. In this study, three popular SRM algorithms, namely, the pixel swapping algorithm (PSA), the Hopfield neural network (HNN) algorithm, and Markov random field (MRF) based algorithm, were used. The proposed M-SRM algorithm was validated using two data sets: a simulated multi-spectral image and an airborne visible/infrared imaging spectrometer (AVIRIS) hyperspectral image. Results show that the highest overall accuracies were obtained by M-SRM in all experiments. For example, in the AVIRIS image experiment, the highest overall accuracies of PSA, HNN and MRF were 88.89%, 93.81% and 82.70% respectively, and increased to 95.06%, 95.37% and 85.56% respectively for M-SRM obtained from the multiple PSA, HNN and MRF analyses. Taylor and Francis 2016-05-06 Article PeerReviewed Li, Xiaodong, Ling, Feng, Foody, Giles M. and Du, Yun (2016) Improving super-resolution mapping through combining multiple super-resolution land-cover maps. International Journal of Remote Sensing, 37 (10). pp. 2415-2432. ISSN 1366-5901 (In Press) Super-resolution land-cover mapping; Mixed pixels; Voting http://www.tandfonline.com/doi/full/10.1080/01431161.2016.1148288 doi:10.1080/01431161.2016.1148288 doi:10.1080/01431161.2016.1148288
spellingShingle Super-resolution land-cover mapping; Mixed pixels; Voting
Li, Xiaodong
Ling, Feng
Foody, Giles M.
Du, Yun
Improving super-resolution mapping through combining multiple super-resolution land-cover maps
title Improving super-resolution mapping through combining multiple super-resolution land-cover maps
title_full Improving super-resolution mapping through combining multiple super-resolution land-cover maps
title_fullStr Improving super-resolution mapping through combining multiple super-resolution land-cover maps
title_full_unstemmed Improving super-resolution mapping through combining multiple super-resolution land-cover maps
title_short Improving super-resolution mapping through combining multiple super-resolution land-cover maps
title_sort improving super-resolution mapping through combining multiple super-resolution land-cover maps
topic Super-resolution land-cover mapping; Mixed pixels; Voting
url https://eprints.nottingham.ac.uk/32952/
https://eprints.nottingham.ac.uk/32952/
https://eprints.nottingham.ac.uk/32952/