Spectral-Spatial Hyperspectral Image Classification Using Subspace-Based Support Vector Machines and Adaptive Markov Random Fields
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...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2016-04-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | http://www.mdpi.com/2072-4292/8/4/355 |
| _version_ | 1798031429825724416 |
|---|---|
| author | Haoyang Yu Lianru Gao Jun Li Shan Shan Li Bing Zhang Jón Atli Benediktsson |
| author_facet | Haoyang Yu Lianru Gao Jun Li Shan Shan Li Bing Zhang Jón Atli Benediktsson |
| author_sort | Haoyang Yu |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-04-11T19:57:18Z |
| format | Article |
| id | doaj.art-ad01009332714a47ad1c5a754beba6f8 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-04-11T19:57:18Z |
| publishDate | 2016-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-ad01009332714a47ad1c5a754beba6f82022-12-22T04:05:59ZengMDPI AGRemote Sensing2072-42922016-04-018435510.3390/rs8040355rs8040355Spectral-Spatial Hyperspectral Image Classification Using Subspace-Based Support Vector Machines and Adaptive Markov Random FieldsHaoyang Yu0Lianru Gao1Jun Li2Shan Shan Li3Bing Zhang4Jón Atli Benediktsson5Key Laboratory of Digital Earth Science, Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100094, ChinaKey Laboratory of Digital Earth Science, Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100094, ChinaSchool of Geography and Planning, Sun Yat-sen University, Guangzhou 510275, ChinaKey Laboratory of Digital Earth Science, Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100094, ChinaKey Laboratory of Digital Earth Science, Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100094, ChinaFaculty of Electrical and Computer Engineering, University of Iceland, Reykjavik IS 107, IcelandThis 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.http://www.mdpi.com/2072-4292/8/4/355hyperspectral image classificationsupport vector machines (SVMs)subspace projection methodadaptive Markov random field |
| spellingShingle | Haoyang Yu Lianru Gao Jun Li Shan Shan Li Bing Zhang Jón Atli Benediktsson Spectral-Spatial Hyperspectral Image Classification Using Subspace-Based Support Vector Machines and Adaptive Markov Random Fields Remote Sensing hyperspectral image classification support vector machines (SVMs) subspace projection method adaptive Markov random field |
| title | Spectral-Spatial Hyperspectral Image Classification Using Subspace-Based Support Vector Machines and Adaptive Markov Random Fields |
| title_full | Spectral-Spatial Hyperspectral Image Classification Using Subspace-Based Support Vector Machines and Adaptive Markov Random Fields |
| title_fullStr | Spectral-Spatial Hyperspectral Image Classification Using Subspace-Based Support Vector Machines and Adaptive Markov Random Fields |
| title_full_unstemmed | Spectral-Spatial Hyperspectral Image Classification Using Subspace-Based Support Vector Machines and Adaptive Markov Random Fields |
| title_short | Spectral-Spatial Hyperspectral Image Classification Using Subspace-Based Support Vector Machines and Adaptive Markov Random Fields |
| title_sort | spectral spatial hyperspectral image classification using subspace based support vector machines and adaptive markov random fields |
| topic | hyperspectral image classification support vector machines (SVMs) subspace projection method adaptive Markov random field |
| url | http://www.mdpi.com/2072-4292/8/4/355 |
| work_keys_str_mv | AT haoyangyu spectralspatialhyperspectralimageclassificationusingsubspacebasedsupportvectormachinesandadaptivemarkovrandomfields AT lianrugao spectralspatialhyperspectralimageclassificationusingsubspacebasedsupportvectormachinesandadaptivemarkovrandomfields AT junli spectralspatialhyperspectralimageclassificationusingsubspacebasedsupportvectormachinesandadaptivemarkovrandomfields AT shanshanli spectralspatialhyperspectralimageclassificationusingsubspacebasedsupportvectormachinesandadaptivemarkovrandomfields AT bingzhang spectralspatialhyperspectralimageclassificationusingsubspacebasedsupportvectormachinesandadaptivemarkovrandomfields AT jonatlibenediktsson spectralspatialhyperspectralimageclassificationusingsubspacebasedsupportvectormachinesandadaptivemarkovrandomfields |