Next Article in Journal
Hyperspectral Image Classification Based on Semi-Supervised Rotation Forest
Previous Article in Journal
Assessing Lodging Severity over an Experimental Maize (Zea mays L.) Field Using UAS Images
Article Menu
Issue 9 (September) cover image

Export Article

Open AccessArticle
Remote Sens. 2017, 9(9), 910; doi:10.3390/rs9090910

Spatial-Spectral-Emissivity Land-Cover Classification Fusing Visible and Thermal Infrared Hyperspectral Imagery

1,2,* , 1,2,* , 3,* , 1,2
and
1
1
The State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China
2
Collaborative Innovation Center of Geospatial Technology, Wuhan University, Wuhan 430079, China
3
College of Computer Science, China University of Geosciences, Wuhan 430074, China
*
Authors to whom correspondence should be addressed.
Academic Editors: Magaly Koch and Prasad S. Thenkabail
Received: 16 July 2017 / Revised: 25 August 2017 / Accepted: 30 August 2017 / Published: 5 September 2017
(This article belongs to the Section Remote Sensing Image Processing)
View Full-Text   |   Download PDF [3696 KB, uploaded 21 September 2017]   |  

Abstract

High-resolution visible remote sensing imagery and thermal infrared hyperspectral imagery are potential data sources for land-cover classification. In this paper, in order to make full use of these two types of imagery, a spatial-spectral-emissivity land-cover classification method based on the fusion of visible and thermal infrared hyperspectral imagery is proposed, namely, SSECRF (spatial-spectral-emissivity land-cover classification based on conditional random fields). A spectral-spatial feature set is constructed considering the spectral variability and spatial-contextual information, to extract features from the high-resolution visible image. The emissivity is retrieved from the thermal infrared hyperspectral image by the FLAASH-IR algorithm and firstly introduced in the fusion of the visible and thermal infrared hyperspectral imagery; also, the emissivity is utilized in SSECRF, which contributes to improving the identification of man-made objects, such as roads and roofs. To complete the land-cover classification, the spatial-spectral feature set and emissivity are integrated by constructing the SSECRF energy function, which relates labels to the spatial-spectral-emissivity features, to obtain an improved classification result. The classification map performs a good result in distinguishing some certain classes, such as roads and bare soil. Also, the experimental results show that the proposed SSECRF algorithm efficiently integrates the spatial, spectral, and emissivity information and performs better than the traditional methods using raw radiance from thermal infrared hyperspectral imagery data, with a kappa value of 0.9137. View Full-Text
Keywords: image fusion; thermal infrared hyperspectral imagery; conditional random fields; land-cover classification; emissivity image fusion; thermal infrared hyperspectral imagery; conditional random fields; land-cover classification; emissivity
Figures

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. (CC BY 4.0).

Scifeed alert for new publications

Never miss any articles matching your research from any publisher
  • Get alerts for new papers matching your research
  • Find out the new papers from selected authors
  • Updated daily for 49'000+ journals and 6000+ publishers
  • Define your Scifeed now

SciFeed Share & Cite This Article

MDPI and ACS Style

Zhong, Y.; Jia, T.; Zhao, J.; Wang, X.; Jin, S. Spatial-Spectral-Emissivity Land-Cover Classification Fusing Visible and Thermal Infrared Hyperspectral Imagery. Remote Sens. 2017, 9, 910.

Show more citation formats Show less citations formats

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Related Articles

Article Metrics

Article Access Statistics

1

Comments

[Return to top]
Remote Sens. EISSN 2072-4292 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top