A Spatial-Contextual Support Vector Machine for Remotely Sensed Image Classification
顯示簡易詮釋資料 統計資料| 欄位 | 內容 | 語言 |
|---|---|---|
dc.citation.epage |
799 | en_US |
dc.citation.issue |
3 | en_US |
dc.citation.spage |
784 | en_US |
dc.citation.volume |
50 | en_US |
dc.citation.woscount |
22 | |
dc.contributor.author |
Li, Cheng-Hsuan | en_US |
dc.contributor.author |
Kuo, Bor-Chen | en_US |
dc.contributor.author |
Lin, Chin-Teng | en_US |
dc.contributor.author |
Huang, Chih-Sheng | en_US |
dc.contributor.department |
電控工程研究所 | zh_TW |
dc.contributor.department |
腦科學研究中心 | zh_TW |
dc.contributor.department |
Institute of Electrical and Control Engineering | en_US |
dc.contributor.department |
Brain Research Center | en_US |
dc.date.accessioned |
2014-12-08T15:21:53Z | |
dc.date.available |
2014-12-08T15:21:53Z | |
dc.date.issued |
2012-03-01 | en_US |
dc.description.abstract |
Recent studies show that hyperspectral image classification techniques that use both spectral and spatial information are more suitable, effective, and robust than those that use only spectral information. Using a spatial-contextual term, this study modifies the decision function and constraints of a support vector machine (SVM) and proposes two kinds of spatial-contextual SVMs for hyperspectral image classification. One machine, which is based on the concept of Markov random fields (MRFs), uses the spatial information in the original space (SCSVM). The other machine uses the spatial information in the feature space (SCSVMF), i.e., the nearest neighbors in the feature space. The SCSVM is better able to classify pixels of different class labels with similar spectral values and deal with data that have no clear numerical interpretation. To evaluate the effectiveness of SCSVM, the experiments in this study compare the performances of other classifiers: an SVM, a context-sensitive semisupervised SVM, a maximum likelihood (ML) classifier, a Bayesian contextual classifier based on MRFs (ML_MRF), and k nearest neighbor classifier. Experimental results show that the proposed method achieves good classification performance on famous hyperspectral images (the Indian Pine site (IPS) and the Washington, DC mall data sets). The overall classification accuracy of the hyperspectral image of the IPS data set with 16 classes is 95.5%. The kappa accuracy is up to 94.9%, and the average accuracy of each class is up to 94.2%. | en_US |
dc.identifier.doi |
10.1109/TGRS.2011.2162246 | en_US |
dc.identifier.issn |
0196-2892 | en_US |
dc.identifier.journal |
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING | en_US |
dc.identifier.uri |
http://dx.doi.org/10.1109/TGRS.2011.2162246 | en_US |
dc.identifier.uri |
https://ir.lib.nycu.edu.tw/handle/11536/15589 | |
dc.identifier.wosnumber |
WOS:000300724300010 | |
dc.language.iso |
en_US | en_US |
dc.subject |
Classification | en_US |
dc.subject |
Markov random fields (MRFs) | en_US |
dc.subject |
spatial-contextual information | en_US |
dc.subject |
support vector machines (SVMs) | en_US |
dc.title |
A Spatial-Contextual Support Vector Machine for Remotely Sensed Image Classification | en_US |
dc.type |
Article | en_US |
檔案
- 000300724300010.pdf (3.26 MB, Adobe PDF)
所屬典藏: 期刊論文
引用此條目
Li, C.-H., Kuo, B.-C., Lin, C.-T., & Huang, C.-S. (2012). A Spatial-Contextual Support Vector Machine for Remotely Sensed Image Classification. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 50(3), 784–799. https://doi.org/10.1109/TGRS.2011.2162246
引用文字依 APA 第 7 版格式自動產生,使用前請再核對。
分享
永久網址:https://ir.lib.nycu.edu.tw/handle/11536/15589