| 一种基于多特征的高光谱遥感图像分类方法 |
| |
| 引用本文： | 刘峰,龚健雅. 一种基于多特征的高光谱遥感图像分类方法[J]. 地理与地理信息科学, 2009, 25(3) |
| |
| 作者姓名： | 刘峰 龚健雅 |
| |
| 作者单位： | 中南大学地学与环境工程学院,湖南,长沙,410083;中南林业科技大学理学院,湖南,长沙,410004;武汉大学测绘遥感信息工程国家重点实验室,湖北,武汉,430079 |
| |
| 基金项目： | 国家重点基础研究发展规划(973计划)，中南林业科技大学青年科学基金 |
| |
| 摘 要： | 提出在多维特征空间中以互信息为评价指标进行特征选择,在特征子集中应用支持向量机(SVM)分类器实现图像监督分类的方法.首先提取图像的光谱、纹理和颜色特征,得到多特征的高维特征空间,然后用最大相关和最小冗余的互信息作为评价标准,用10-fold交叉验证误差率选择特征子集,最后用基于径向基函数的SVM实现图像的分类.实验表明,该方法能明显提高图像分类的精度.
|
| 关 键 词： | 图像分类 互信息 特征选择 SVM |
A Classification Method for High Spatial Resolution Remotely Sensed Image Based on Multi-feature |
| |
| LIU Feng,GONG Jian-ya. A Classification Method for High Spatial Resolution Remotely Sensed Image Based on Multi-feature[J]. Geography and Geo-Information Science, 2009, 25(3) |
| |
| Authors: | LIU Feng GONG Jian-ya |
| |
| Affiliation: | 1.School of Geoscience and Environmental Engineering;Central South University;Changsha 410083;2.School of Science;Central South University of Forestry and Technology;Changsha 410004;3.State Key Laboratory of Information Engineering in Surveying;Mapping and Remote Sensing;Wuhan University;Wuhan 430079;China |
| |
| Abstract: | In this paper,a novel remote sensing image classification method was proposed,which was based on feature selection and Support Vector Machine(SVM) classifier.A minimal redundancy and maximal relevance criterion based on mutual information was applied to selection a set of informative and non-redundant Gabor texture feature,HSV color feature and spectral feature from high spectral remote sensing image,which are then further enhanced by SVM based on radial basis function for supervise classification.Experimen... |
| |
| Keywords: | SVM |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
