国土资源遥感Issue(3)：42-46,5.DOI:10.6046/gtzyyg.2015.03.08
基于MKSVM和MRF的高光谱影像分类方法
Hyperspectral images classification based on MKSVM and MRF
摘要
Abstract
To fully utilize the spectral and spatial information rich in hyperspectral remote sensing images, this paper proposes a hyperspectral images classification method based on multiple kernel support vector machine ( MKSVM) and Markov random field ( MRF ) . Firstly, the MKSVM classifier is used to classify hyperspectral images, then the MRF is used to regularize the initial classification results in the spatial structure, and the final classification results are obtained in the end. The experiment on AVIRIS hyperspectral image shows that the proposed method not only effectively eliminates the “noise” in the homogeneous regions within the classification results but also improves the classification accuracy by about 3%.关键词
高光谱影像/多核支持向量机(MKSVM)/马尔科夫随机场(MRF)/分类Key words
hyperspectral images/multiple kernel support vector machine(MKSVM)/Markov random field(MRF)/classification分类
信息技术与安全科学引用本文复制引用
谭熊,余旭初,张鹏强,付琼莹,魏祥坡,高猛..基于MKSVM和MRF的高光谱影像分类方法[J].国土资源遥感,2015,(3):42-46,5.基金项目
国家自然科学基金青年科学基金项目“机载低空摄像机在线检校与视频影像实时处理技术研究”(编号:41201477)和江西省数字国土重点实验室开放基金项目“联合光谱/空间光谱信息的高光谱影像分类技术”(编号：DLLJ201403)共同资助。 （编号:41201477）
