Opin vísindi

Spectral-Spatial Hyperspectral Image Classification Using Subspace-Based Support Vector Machines and Adaptive Markov Random Fields

Spectral-Spatial Hyperspectral Image Classification Using Subspace-Based Support Vector Machines and Adaptive Markov Random Fields


Titill: Spectral-Spatial Hyperspectral Image Classification Using Subspace-Based Support Vector Machines and Adaptive Markov Random Fields
Höfundur: Benediktsson, Jon Atli   orcid.org/0000-0003-0621-9647
Yu, Haoyang
Gao, Lianru
Li, Jun
LI, Shan Shan
Zhang, Bing
Útgáfa: 2016
Umfang: 1-21
Háskóli/Stofnun: Háskóli Íslands
University of Iceland
Svið: Verkfræði- og náttúruvísindasvið (HÍ)
School of Engineering and Natural Sciences (UI)
Deild: Rafmagns- og tölvuverkfræðideild (HÍ)
Faculty of Electrical and Computer Engineering (UI)
Birtist í: Remote Sensing;8(4)
ISSN: 2072-4292
DOI: 10.3390/rs8040355
Efnisorð: Hyperspectral image classification; Support vector machines
URI: https://hdl.handle.net/20.500.11815/137

Skoða fulla færslu

Tilvitnun:

Yu, H.; Gao, L.; Li, J.; Li, S.S.; Zhang, B.; Benediktsson, J.A. (2016) Spectral-Spatial Hyperspectral Image Classification Using Subspace-Based Support Vector Machines and Adaptive Markov Random Fields. Remote Sensing, 8(4), 355.

Útdráttur:

This paper introduces a new supervised classification method for hyperspectral images that combines spectral and spatial information. A support vector machine (SVM) classifier, integrated with a subspace projection method to address the problems of mixed pixels and noise, is first used to model the posterior distributions of the classes based on the spectral information. Then, the spatial information of the image pixels is modeled using an adaptive Markov random field (MRF) method. Finally, the maximum posterior probability classification is computed via the simulated annealing (SA) optimization algorithm. The combination of subspace-based SVMs and adaptive MRFs is the main contribution of this paper. The resulting methods, called SVMsub-eMRF and SVMsub-aMRF, were experimentally validated using two typical real hyperspectral data sets. The obtained results indicate that the proposed methods demonstrate superior performance compared with other classical hyperspectral image classification methods.

Leyfi:

CC BY 4.0

Skrár

Þetta verk birtist í eftirfarandi safni/söfnum:


Fletta

Um vefinn

Reikningurinn minn