地理科学 ›› 2018, Vol. 38 ›› Issue (6): 972-978.doi: 10.13249/j.cnki.sgs.2018.06.017

• • 上一篇    下一篇

基于GANBPSO-SVM的高光谱影像特征选择方法

谢福鼎(), 姚娆()   

  1. 辽宁师范大学城市与环境学院,辽宁 大连 116029
  • 收稿日期:2017-06-12 修回日期:2017-08-04 出版日期:2018-06-20 发布日期:2018-06-20
  • 作者简介:

    作者简介:谢福鼎(1965-),男,教授,博士,主要研究方向为模式识别与高光谱遥感图像分类。E-mail:xiefd@lnnu.edu.cn

  • 基金资助:
    国家自然科学基金项目(41771178,61772252)、广东省数学与交叉科学普通高校重点实验室开放项目资助

A Feature Selection Strategy for Hyperspectral Images Classification Based on GANBPSO-SVM

Fuding Xie(), Rao Yao()   

  1. College of Urban and Environment, Liaoning Normal University, Dalian 116029, Liaoning, China
  • Received:2017-06-12 Revised:2017-08-04 Online:2018-06-20 Published:2018-06-20
  • Supported by:
    National Natural Science Foundation of China (41771178, 61772252),Open Project Program of Key Laboratory of Mathematics and Interdisciplinary Sciences of Guangdong Higher Education Institutes

摘要:

为了在保持对目标检测和分类分析所需信息的同时,降低高光谱影像的维度,提出了一种混合优化策略的特征选择方法。该方法将遗传算法和二进制粒子群优化算法融合成一种新的混合优化策略(GANBPSO),自动选择最优波段组合,同时优化分类器支持向量机(RBF-SVM)的参数,以提高分类器的分类性能。为了说明所提出方法的有效性,采用了在高光谱分类中广泛使用的Indian Pines(AVIRIS 92AV3C)数据集进行测试。结果表明所提出方法(GANBPSO-SVM)能够自动选择包含最多信息的特征子集以保证分类精度,而不需要预先设置所需要的特征子集数量,本方法与传统方法相比具有更好的分类效果。

关键词: 高光谱影像, 特征选择, 粒子群优化, 支持向量机

Abstract:

Rich spectral information from hyperspectral images can aid in the classification and recognition of the ground objects. Currently, hyperspectral images classification has already been applied successfully in various fields. However, the high dimensions of hyperspectral images cause redundancy in information and bring some troubles while classifying precisely ground truth. Hence, this paper proposes a hybrid feature selection strategy based on the Genetic Algorithm and the Novel Binary Particle Swarm Optimization (GANBPSO) to reduce the dimensionality of hyperspectral data while preserving the desired information for target detection and classification analysis. The proposed feature selection approach automatically chooses the most informative features combination. The parameters used in support vector machine (SVM) simultaneously are optimized, aiming at improving the performance of SVM. To show the validity of the proposal, Indian Pines(AVIRIS 92AV3C) data set which is widely used to test the performance of feature selection techniques is chosen to feed the proposed method. The obtained results clearly confirm that the new approach is able to automatically select the most informative features in terms of classification accuracy without requiring the number of desired features to be set a priori by users. Experimental results show that the proposed method can achieve higher classification accuracy than traditional methods.

Key words: hyperspectral images, feature selection, Particle Swarm Optimization, Support Vector Machine

中图分类号: 

  • P237