| 基于改进遗传算法的高光谱图像波段选择 |
| |
| 作者姓名： | 赵冬 赵光恒 |
| |
| 作者单位： | 1. 中国科学院光电研究院,北京 10019
2. 中国科学院研究生院,北京 100049 |
| |
| 摘 要： | 在对地观测领域,高光谱图像得到了广泛应用,但存在数据量大、波段间相关性高等问题. 针对以上问题分析了已有的波段选择方法,提出了基于信息量及类间可分离性准则的遗传算法对高光谱图像进行波段选择:构造波段互相关系数矩阵进行子空间划分;利用联合熵作为组合信息量的标准,Bhattacharyya距离作为类间可分离性标准,构造遗传算法的适应度方程,改进了遗传算法中的选择算子. 最后用AVIRIS图像对提出的算法进行试验,并利用最大似然分类法对最优波段组合进行分类,总体分类精度达到94.24%,Kappa系数达到0.94.
|
| 关 键 词： | 高光谱图像 波段选择 遗传算法 联合熵 Bhattacharyya距离 |
| 收稿时间： | 2009-04-10 |
| 修稿时间： | 2009-06-04 |
Band selection of hyperspectral image based on improved genetic algorithm |
| |
| Authors: | ZHAO Dong ZHAO Guang-Heng |
| |
| Institution: | 1. Academy of Optoelectronics, Chinese Academy of Sciences, Beijing 100190, China;
2. Graduate University of the Chinese Academy of Sciences, Beijing 100049, China |
| |
| Abstract: | Hyperspectral images have been widely used in earth observation. However, there are some problems such as huge amount of data and high correlation between bands. The existing band selection algorithms have been analyzed in this article regarding to the problems mentioned above. An application of genetic algorithm based on image information content and between-class separability criteria was proposed to band selection of hyperspectral image. The correlation coefficient matrix was formed for subspace partition. The fitness functions of genetic algorithm were reconstructed by using joint entropy as criterion of information content and Bhattacharya distance as between-class separability. The selection operator in genetic algorithm was improved. Finally, the improved algorithm was tested with AVIRIS image data. The maximum likelihood classification method was implemented to classify the selected optimal band combinations. The classification results illustrate that the total classification accuracy percentage of the chosen band image is 94.24% and Kappa coefficient 0.94. |
| |
| Keywords: | hyperspectral image band selection genetic algorithm joint entropy Bhattacharyya distance |
|
| 点击此处可从《》浏览原始摘要信息 |
| 点击此处可从《》下载免费的PDF全文 |
|
