高光谱图像波段选择的改进二进制布谷鸟算法

doi:10.13474/j.cnki.11-2246.2019.0110

测绘通报 ›› 2019, Vol. 0 ›› Issue (4): 43-48.doi: 10.13474/j.cnki.11-2246.2019.0110

高光谱图像波段选择的改进二进制布谷鸟算法

宋广钦^1,2, 杜正舜^1,2, 贺智^1,2

1. 中山大学地理科学与规划学院综合地理信息研究中心, 广东广州 510275;
2. 广东省城市化与地理环境空间模拟重点实验室, 广东广州 510275

收稿日期:2018-06-28 出版日期:2019-04-25 发布日期:2019-05-07
通讯作者: 贺智。E-mail:hezh8@mail.sysu.edu.cn E-mail:hezh8@mail.sysu.edu.cn
作者简介:宋广钦(1996-),男,主要研究方向为遥感图像处理及数据挖掘。E-mail:songgqin@foxmail.com
基金资助:
国家自然科学基金（41501368）；中央高校基本科研业务费用专项资金（16lgpy04）

Improved binary cuckoo search algorithm for band selection in hyperspectral image

SONG Guangqin^1,2, DU Zhengshun^1,2, HE Zhi^1,2

1. School of Geography Science and Planning, Center of Integrated Geographic Information Anlaysis, Sun Yat-sen University, Guangzhou 510275, China;
2. Guangdong Key Laboratory for Urbanization and Geo-simulation, Guangzhou 510275, China

Received:2018-06-28 Online:2019-04-25 Published:2019-05-07

摘要/Abstract

摘要：

波段选择是高光谱遥感图像分类的重要前提，本文提出了一种用于高光谱遥感图像波段选择的改进二进制布谷鸟算法，通过使用混合二进制编码算法更新子代鸟巢和使用遗传算法交叉方式更新被发现鸟巢两个方面对二进制布谷鸟算法进行改进，找出在图像中起主要作用且相关性低的波段，实现对高光谱遥感图像降维。将本文算法运用于PaviaU数据集和AVIRIS数据集，并与二进制布谷鸟算法、二进制粒子群算法、最小冗余最大相关算法、Relief算法等进行对比分析。结果表明，改进二进制布谷鸟算法波段特征选择效率更高，且选取的波段更具代表性，能够较好地提高后续分类精度。

关键词: 二进制布谷鸟算法, 高光谱图像, 降维, 波段选择

Abstract:

Spectral band selection serves as an important part in hyperspectral image classification. In this paper, an improved binary cuckoo search algorithm for band selection in hyperspectral image is proposed. Binary cuckoo search algorithm is improved by these two ways, one of which is that we update the nests of offspring by using a binary encoding algorithm. Another one is that the found nests are updated based on the crossover mode of genetic algorithm. The improved binary cuckoo search algorithm achieves the goal of dimensionality reduction of hyperspectral image by finding the bands with low correlation and the vital function in the image. The improved binary cuckoo algorithm is applied to PaviaU datasets and AVIRIS datasets, compared with binary cuckoo algorithm, binary particle swarm algorithm, minimum redundancy maximum correlation algorithm, relief algorithm. The results show that the improved binary cuckoo search algorithm is more efficient in the band selection, and the selected bands are more representative and can improve the precision of the image classification.

Key words: binary cuckoo search algorithm, hyperspectral image, dimensionality reduction, band selection

中图分类号:

P237

宋广钦, 杜正舜, 贺智. 高光谱图像波段选择的改进二进制布谷鸟算法[J]. 测绘通报, 2019, 0(4): 43-48.

SONG Guangqin, DU Zhengshun, HE Zhi. Improved binary cuckoo search algorithm for band selection in hyperspectral image[J]. 测绘通报, 2019, 0(4): 43-48.

参考文献

[1] 谭琨,杜培军. 基于再生核Hilbert空间小波核函数支持向量机的高光谱遥感影像分类[J]. 测绘学报,2011,40(2):142-147.
[2] FORERO V S, ANGULO J. Classification of hyperspectral images by tensor modeling and additive morphological decomposition[J]. Pattern Recognition, 2013, 46(2):566-577.
[3] 苏红军,杜培军,盛业华. 高光谱影像波段选择算法研究[J]. 计算机应用研究,2008,25(4):1093-1096.
[4] 丁雪梅,王汉军,王炤光,等. 基于改进ReliefF的无监督特征选择方法[J]. 计算机系统应用,2018,27(3):149-155.
[5] MUNDRA P A, RAJAPAKSE J C. SVM-RFE with MRMR filter for gene selection[J]. IEEE Transactions on Nanobioscience, 2010, 9(1):31-37.
[6] 沈泉飞,曹敏, 史照良,等. 基于布谷鸟算法的遥感影像智能分类[J]. 测绘通报,2017(1):65-68.
[7] ZHANG X, SUN Q, LI J. Optimal band selection for high dimensional remote sensing data using genetic algorithm[C]//International Conference on Earth Observation for Global Changes.[S.l.]:International Society for Optics and Photonics, 2009.
[8] 周爽. 蚁群算法在高光谱图像降维和分类中的应用研究[D]. 哈尔滨:哈尔滨工业大学,2010.
[9] 秦全德. 粒子群算法研究及应用[D]. 广州:华南理工大学, 2011.
[10] YANG X S, DEB S. Cuckoo search via Lévy flights[C]//2009 World Congress on NaBIC. Coimbatore:IEEE, 2010:210-214.
[11] YANG X S, DEB S. Multiobjective cuckoo search for design optimization[J]. Computers & Operations Research, 2013,40(6):1616-1624.
[12] GHERBOUDJ A, LAYEB A, CHIKHI S. Solving 0-1 knapsack problems by a discrete binary version of cuckoo search algorithm[M].[S.l.]:Inderscience Publishers, 2012.
[13] MEDJAHED S A, SAADI T A, BENYETTOU A, et al. Binary cuckoo search algorithm for band selection in hyperspectral image classification[J]. Iaeng International Journal of Computer Science, 2015,42(3):1-9.
[14] 张晶,吴虎胜. 改进二进制布谷鸟搜索算法求解多维背包问题[J]. 计算机应用,2015,35(1):183-188.
[15] 纪凯,韩栋. SVM支持向量机在遥感图像中的应用研究[J]. 湖南城市学院学报(自然科学版),2016,25(3):114-116.
[16] KENNEDY J, EBERHART R C. A discrete binary version of the particle swarm algorithm[C]//IEEE International Conference on Systems, Man, and Cybernetics. Computational Cybernetics and Simulation. Orlando:IEEE, 1997.
[17] 刘建华, 杨荣华, 孙水华. 离散二进制粒子群算法分析[J]. 南京大学学报(自然科学),2011,47(5):504-514.
[18] 冯登科,阮奇,杜利敏. 二进制布谷鸟搜索算法[J]. 计算机应用,2013,33(6):1566-1570.

高光谱图像波段选择的改进二进制布谷鸟算法

Improved binary cuckoo search algorithm for band selection in hyperspectral image

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 9

编辑推荐

Metrics

本文评价

[1]	窦世卿, 陈治宇, 徐勇, 郑贺刚, 苗林林, 宋莹莹. 基于多特征融合与典型降维方法的高光谱影像分类[J]. 测绘通报, 2022, 0(4): 32-36,50.
[2]	刘彦君, 张贵, 王潇, 周璀, 杨志高, 吴鑫, 张娟. 基于无人机高光谱影像波段选择的薇甘菊分类[J]. 测绘通报, 2020, 0(4): 34-39,52.
[3]	强永刚, 肖志峰, 陈欢欢, 闫丽阳. 基于动态阈值哈希的大规模遥感影像快速内容检索方法[J]. 测绘通报, 2019, 0(8): 34-38,53.
[4]	徐君, 王彩玲. 结合空间信息选取最优端元组合的混合像元分解[J]. 测绘通报, 2019, 0(7): 6-11.
[5]	李彩虹, 赵祎霏. 一种高光谱图像的半监督分类方法[J]. 测绘通报, 2018, 0(2): 46-49.
[6]	胡冬翠, 谢福鼎, 杨俊, 张永. 一种基于空间信息和遗传算法的半监督高光谱图像分类方法[J]. 测绘通报, 2018, 0(10): 22-26.
[7]	汪少华, 杨婷. 判别流形学习算法的高光谱数据降维与树种识别[J]. 测绘通报, 2018, 0(1): 55-61.
[8]	程志会, 谢福鼎. 基于空间特征与纹理信息的高光谱图像半监督分类[J]. 测绘通报, 2016, 0(12): 56-59,73.
[9]	何晓宁曹建农高坡高美玲. 顶点成分分析法端元提取的改进算法[J]. 测绘通报, 2013, 0(7): 30-34.