Spectral–spatial based sub-pixel mapping of remotely sensed imagery with multi-scale spatial dependenceInternational Journal of Remote Sensing

About

Authors
Yihang Zhang, Yun Du, Feng Ling, Xia Wang, Xiaodong Li
Year
2015
DOI
10.1080/01431161.2015.1047048
Subject
Earth and Planetary Sciences (all)

Text

This article was downloaded by: [New York University]

On: 01 June 2015, At: 07:21

Publisher: Taylor & Francis

Informa Ltd Registered in England and Wales Registered Number: 1072954 Registered office: Mortimer House, 37-41 Mortimer Street, London W1T 3JH, UK

Click for updates

International Journal of Remote

Sensing

Publication details, including instructions for authors and subscription information: http://www.tandfonline.com/loi/tres20

Spectral–spatial based sub-pixel mapping of remotely sensed imagery with multi-scale spatial dependence

Yihang Zhangab, Yun Dua, Feng Linga, Xia Wanga & Xiaodong Lia a Key Laboratory of Monitoring and Estimate for Environment and

Disaster of Hubei Province, Institute of Geodesy and Geophysics,

Chinese Academy of Sciences, Wuhan 430077, PR China b University of Chinese Academy of Sciences, Beijing 100049, PR

China

Published online: 01 Jun 2015.

To cite this article: Yihang Zhang, Yun Du, Feng Ling, Xia Wang & Xiaodong Li (2015)

Spectral–spatial based sub-pixel mapping of remotely sensed imagery with multi-scale spatial dependence, International Journal of Remote Sensing, 36:11, 2831-2850, DOI: 10.1080/01431161.2015.1047048

To link to this article: http://dx.doi.org/10.1080/01431161.2015.1047048

PLEASE SCROLL DOWN FOR ARTICLE

Taylor & Francis makes every effort to ensure the accuracy of all the information (the “Content”) contained in the publications on our platform. However, Taylor & Francis, our agents, and our licensors make no representations or warranties whatsoever as to the accuracy, completeness, or suitability for any purpose of the Content. Any opinions and views expressed in this publication are the opinions and views of the authors, and are not the views of or endorsed by Taylor & Francis. The accuracy of the Content should not be relied upon and should be independently verified with primary sources of information. Taylor and Francis shall not be liable for any losses, actions, claims, proceedings, demands, costs, expenses, damages, and other liabilities whatsoever or howsoever caused arising directly or indirectly in connection with, in relation to or arising out of the use of the Content.

This article may be used for research, teaching, and private study purposes. Any substantial or systematic reproduction, redistribution, reselling, loan, sub-licensing, systematic supply, or distribution in any form to anyone is expressly forbidden. Terms &

Conditions of access and use can be found at http://www.tandfonline.com/page/termsand-conditions

D ow nl oa de d by [N ew

Y or k U niv ers ity ] a t 0 7:2 1 0 1 J un e 2 01 5

Spectral–spatial based sub-pixel mapping of remotely sensed imagery with multi-scale spatial dependence

Yihang Zhanga,b, Yun Dua, Feng Linga*, Xia Wanga, and Xiaodong Lia aKey Laboratory of Monitoring and Estimate for Environment and Disaster of Hubei Province,

Institute of Geodesy and Geophysics, Chinese Academy of Sciences, Wuhan 430077, PR China; bUniversity of Chinese Academy of Sciences, Beijing 100049, PR China (Received 19 November 2014; accepted 15 March 2015)

Sub-pixel mapping (SPM) is a technique used to obtain a land-cover map with a finer spatial resolution than input remotely sensed imagery. Spectral–spatial based SPM can directly apply original remote-sensing images as input to produce fine-resolution landcover maps. However, the existing spectral–spatial based SPM algorithms only use the maximal spatial dependence principle (calculated at the sub-pixel scale) as the spatial term to describe the local spatial distribution of different land-cover features, which always results in an over-smoothed and discontinuous land-cover map. The spatial dependence can also be calculated at the coarse-pixel scale to maintain the holistic land-cover pattern information of the resultant fine-resolution land-cover map. In this article, a novel spectral–spatial based SPM algorithm with multi-scale spatial dependence is proposed to overcome the limitation in the existing spectral–spatial based

SPM algorithms. The objective function of the proposed SPM algorithm is composed of three parts, namely spectral term, sub-pixel scale based spatial term, and coarsepixel scale based spatial term. Synthetic multi-spectral, degraded Landsat multispectral and real IKONOS multi-spectral images are employed in the experiments to validate the performance of the proposed SPM algorithm. The proposed algorithm is evaluated visually and quantitatively by comparing with the hard-classification method and two traditional SRM algorithms including pixel-swapping (PS) and Markovrandom-field (MRF) based SPM. The results indicate that the proposed algorithm can generate fine-resolution land-cover maps with higher accuracies and more detailed spatial information than other algorithms. 1. Introduction

Sub-pixel mapping (SPM) or super-resolution land-cover mapping (SRM) is a promising technique used to generate land-cover maps with finer spatial resolutions than input images (Atkinson 2009, 2005). According to the input data, SPM can be categorized into two groups. For the first group, fraction images generated by spectral unmixing or soft classification are used as input data, and SRM is then considered for the post-processing of spectral unmixing or soft-classification techniques (Atkinson 2005; Foody [1998] 2002; Foody and Doan 2007). Algorithms such as pixel-swapping (PS) (Atkinson 2005; Ling, Li, et al. 2013), sub-pixel/pixel attraction model (Mertens et al. 2006; Ge, Li, and Lakhan 2009; Wang, Wang, and Liu 2012; Ge 2013), genetic algorithm (Mertens et al. 2003), Hopfield neural network (HNN) based SPM (Tatem et al. 2002; Ling et al. 2010; Muad and Foody 2012), linear optimization (Verhoeye and De Wulf 2002), interpolation based SPM (Ling, Du, et al. 2013; Ling, Fang, et al. *Corresponding author. Email: lingf@whigg.ac.cn

International Journal of Remote Sensing, 2015

Vol. 36, No. 11, 2831–2850, http://dx.doi.org/10.1080/01431161.2015.1047048 © 2015 Taylor & Francis