关键词: 高光谱遥感图像, 波段选择, 条件互信息, 自适应分支定界法, 支持向量机, 遗传算法

Abstract: With the development and popularization of the remote-sensing imaging technology, there are more and more applications of hyperspectral image classification tasks, such as target detection and landcover investigation. It is a very challenging issue of urgent importance that how to select a minimal and effective subset from mass of bands. A novel band selection strategy is put forward based on conditional mutual information between adjacent bands and branch and bound algorithm for the high correlation between the bands. In addition, genetic algorithm and support vector machine are employed to search for the best band combination. Experimental results show that the proposed approach is very competitive and robust.

Key words: hyperspectral remote sensing, band selection, conditional mutual information, adaptive branch and bound algorithm, support vector machine, genetic algorithm