Generating labeled samples for hyperspectral image classification using correlation of spectral bands  

作　　者：Lu YU Jun XIE Songcan CHEN Lei ZHU 

机构地区：[1]Institute of Communications Engineering, PLA University of Science and Technology, Nanjing 210007, China [2]College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China [3]College of Command Information System, PLA University of Science and Technology, Nanjing 210007, China

出　　处：《Frontiers of Computer Science》2016年第2期292-301,共10页中国计算机科学前沿（英文版）

摘　　要：Because the labor needed to manually label a huge training sample set is usually not available, the problem of hyperspectral image classification often suffers from a lack of labeled training samples. At the same time, hyperspectral data represented in a large number of bands are usually highly correlated. In this paper, to overcome the small sample problem in hyperspectral image classification, correlation of spectral bands is fully utilized to generate multiple new sub-samples from each original sample. The number of labeled training samples is thus increased several times. Experiment results demonstrate that the proposed method has an obvious advantage when the number of labeled samples is small.Because the labor needed to manually label a huge training sample set is usually not available, the problem of hyperspectral image classification often suffers from a lack of labeled training samples. At the same time, hyperspectral data represented in a large number of bands are usually highly correlated. In this paper, to overcome the small sample problem in hyperspectral image classification, correlation of spectral bands is fully utilized to generate multiple new sub-samples from each original sample. The number of labeled training samples is thus increased several times. Experiment results demonstrate that the proposed method has an obvious advantage when the number of labeled samples is small.

关 键 词：hyperspectral image remote sensing image classification small sample problem 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术] TP391.41[自动化与计算机技术—计算机科学与技术]