Show simple item record

dc.contributor.authorSun, Zhuozh_CN
dc.contributor.authorWang, Chengzh_CN
dc.contributor.authorLi, Pengzh_CN
dc.contributor.authorWang, Hanyunzh_CN
dc.contributor.authorLi, Jonathanzh_CN
dc.contributor.author王程zh_CN
dc.contributor.author李军zh_CN
dc.date.accessioned2015-07-22T02:39:51Z
dc.date.available2015-07-22T02:39:51Z
dc.date.issued2012zh_CN
dc.identifier.citationProceedings of International Conference on Computer Vision in Remote Sensing, CVRS 2012, 2012:268-272zh_CN
dc.identifier.other20131016080645zh_CN
dc.identifier.urihttps://dspace.xmu.edu.cn/handle/2288/86815
dc.descriptionConference Name:2012 International Conference on Computer Vision in Remote Sensing, CVRS 2012. Conference Address: Xiamen, China. Time:December 16, 2012 - December 18, 2012.zh_CN
dc.descriptionXiamen University; National University of Defense Technologyzh_CN
dc.description.abstractA common assumption in hyperspectral image classification is that the distribution of the classes is stable for all the areas of hyperspectral image. However, this assumption is often incorrect due to the inner-class variety over even short distance on the ground. In this paper, we present a semi-supervised support vector machine (SVM) framework to learn the cross-domain kernels from both the source and target domain in hyperspectral data. The proposed method simultaneously learns the cross-domain kernel mapping and a robust SVM classifier, which is done by minimizing both the Maximum Mean Discrepancy and structural risk functional of SVM. Experiments are carried out on two real data sets and results show that the proposed model can achieve high classification accuracy and provide robust solutions. 漏 2012 IEEE.zh_CN
dc.language.isoen_USzh_CN
dc.publisherIEEE Computer Societyzh_CN
dc.source.urihttp://dx.doi.org/10.1109/CVRS.2012.6421273zh_CN
dc.subjectClassification (of information)zh_CN
dc.subjectImage classificationzh_CN
dc.subjectRemote sensingzh_CN
dc.subjectSpectroscopyzh_CN
dc.titleHyperspectral image classification with SVM-based domain adaption classifierszh_CN
dc.typeConferencezh_CN


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record