您的位置:首页  > 论文页面

空-谱特征与高程特征相结合的多源数据联合分类研究

发表时间:2016-01-31  浏览量:1957  下载量:880
全部作者: 陶超,杨钊霞
作者单位: 中南大学地球科学与信息物理学院
摘 要: 提出一种空-谱特征与高程特征相结合的多源数据联合分类方法。首先,使用最小噪声分离变换法对原始高光谱影像进行降维处理,在此基础上,对主成分图进行空-谱特征的提取。其次,对激光点云构成的影像进行滤波并进行反距离加权内插处理以获取地物的高程信息。然后,将不同来源的特征组合,以得到组合特征。最后,使用支持向量机(support vector machine,SVM)分类器对高光谱影像进行分类。实验证明,该方法提取的特征可以有效表示影像,实现更高精度的地物分类。
关 键 词: 摄影测量与遥感技术;激光雷达;空-谱特征;高程特征;地物分类
Title: Research of multi-source data classification based on the combination of spatial-spectral feature and elevation feature
Author: TAO Chao, YANG Zhaoxia
Organization: School of Geosciences and Info-Physics, Central South University
Abstract: We propose a novel approach of multi-source data classification based on the combination of spatial-spectral feature and elevation feature. Firstly, we extract the spatial-spectral feature by reorganizing the local image patch with the first principal components into a vector representation after using minimum noise fraction to reduce dimensionality of the original hyperspectral image. Secondly, we get the feature of elevation information through processing the lidar image such as filtering and inverse distance weighting interpolation. Then, we combine features obtained from different data sources. Finally, we embed the resulting sparse feature coding into the support vector machine (SVM) for hyperspectral image classification. Experiments show that our approach can extract the effective feature to represent the image, and achieve higher classification accuracy of ground objects.
Key words: photogrammetry and remote sensing technology; lidar; spatial-spectral feature; elevation feature; land-covers classification
发表期数: 2016年1月第2期
引用格式: 陶超,杨钊霞. 空-谱特征与高程特征相结合的多源数据联合分类研究[J]. 中国科技论文在线精品论文,2016,9(2):118-125.
 
2 评论数 0
暂无评论
友情链接