| 高光谱影像波段选择算法研究* |
| |
| 引用本文： | 苏红军,杜培军,盛业华.高光谱影像波段选择算法研究*[J].计算机应用研究,2008,25(4):1093-1096. |
| |
| 作者姓名： | 苏红军 杜培军 盛业华 |
| |
| 作者单位： | 1. 南京师范大学,虚拟地理环境教育部重点实验室,南京,210046
2. 中国矿业大学,地理信息与遥感科学系,江苏,徐州,221008 |
| |
| 基金项目： | 国家自然科学基金资助项目(40401038)，地理空间信息工程国家测绘局重点实验室开放基金资助项目，中国矿业大学科学基金资助项目(D200403) |
| |
| 摘 要： | 基于高光谱影像数据的特点,分析了高光谱数据的降维方法。着重探讨了波段选择的若干算法:熵及联合熵、最佳指数因子、自动子空间划分、自适应波段选择、波段指数和最优波段指数等算法。分析了各种算法的有效性、局限性和计算复杂度,并针对波段指数的不足,设计了最优波段指数(OBI)波段选择新算法。最后通过具体的试验,验证了各种算法的性能。
|
| 关 键 词： | 高光谱影像 波段选择 特征提取与选择 |
| 文章编号： | 1001-3695(2008)04-1093-04 |
| 修稿时间： | 2007年2月27日 |
Study on band selection algorithms of hyperspectral image data |
| |
| SU Hong jun,DU Pei jun,SHENG Ye hua.Study on band selection algorithms of hyperspectral image data[J].Application Research of Computers,2008,25(4):1093-1096. |
| |
| Authors: | SU Hong jun DU Pei jun SHENG Ye hua |
| |
| Affiliation: | (1.Key Laboratory of Virtual Geographic Environment, Nanjing Normal University, Nanjing 210046, China; 2.Dept.of Geographic Information & Remote Sensing Science, China University of Mining & Technology, Xuzhou Jiangsu 221008, China) |
| |
| Abstract: | Based on the characteristic of the HRS image data, the method of dimensionality reduction was discussed.And then some key algorithms such as joint entropy,optimal index factor,auto-subspace partition,adaptive band selection,band index and optimal band index were analyzed.In addition,the effectivity,shortage and complexity between different algorithms were discussed and compared.According to the shortage of band index,the new band selection method which named optimal band index(OBI) was proposed.At last,the feasibility of proposed methods was proved by experiment results. |
| |
| Keywords: | hyperspectral image band selection feature extraction and selection |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《计算机应用研究》浏览原始摘要信息 |
|
点击此处可从《计算机应用研究》下载全文 |
|
