Classification of hyperspectral remote sensing images based on simulated annealing genetic algorithm and multiple instance learning
来源期刊:中南大学学报(英文版)2014年第1期
论文作者:GAO Hong-min(高红民) ZHOU Hui(周惠) XU Li-zhong(徐立中) SHI Ai-ye(石爱业)
文章页码:262 - 271
Key words:hyperspectral remote sensing images; simulated annealing genetic algorithm; support vector machine; band selection; multiple instance learning
Abstract: A hybrid feature selection and classification strategy was proposed based on the simulated annealing genetic algorithm and multiple instance learning (MIL). The band selection method was proposed from subspace decomposition, which combines the simulated annealing algorithm with the genetic algorithm in choosing different cross-over and mutation probabilities, as well as mutation individuals. Then MIL was combined with image segmentation, clustering and support vector machine algorithms to classify hyperspectral image. The experimental results show that this proposed method can get high classification accuracy of 93.13% at small training samples and the weaknesses of the conventional methods are overcome.
GAO Hong-min(高红民)1, ZHOU Hui(周惠)1, 2, XU Li-zhong(徐立中)1, SHI Ai-ye(石爱业)1
(1. College of Computer and Information Engineering, Hohai University, Nanjing 211100, China;
2. College of Computer and Software, Nanjing Institute of Industry Technology, Nanjing 210046, China)
Abstract:A hybrid feature selection and classification strategy was proposed based on the simulated annealing genetic algorithm and multiple instance learning (MIL). The band selection method was proposed from subspace decomposition, which combines the simulated annealing algorithm with the genetic algorithm in choosing different cross-over and mutation probabilities, as well as mutation individuals. Then MIL was combined with image segmentation, clustering and support vector machine algorithms to classify hyperspectral image. The experimental results show that this proposed method can get high classification accuracy of 93.13% at small training samples and the weaknesses of the conventional methods are overcome.
Key words:hyperspectral remote sensing images; simulated annealing genetic algorithm; support vector machine; band selection; multiple instance learning