基于空-谱特征 K-means的长波红外高光谱图像分类

汪凌志; 雷正刚; 周浩; 余春超; 杨智雄; 段绍丽; 聂冬

红外技术, 2020, 42 (4): 348, 网络出版: 2020-05-30

基于空-谱特征 K-means的长波红外高光谱图像分类

Long-wave Infrared Hyperspectral Image Classification Based on K-means of Spatial-Spectral Features

论文大纲

汪凌志 ¹雷正刚 ^1,*周浩 ²余春超 ¹杨智雄 ¹段绍丽 ¹聂冬 ¹

作者单位

¹ 昆明物理研究所，云南昆明 650223

² 云南大学，云南昆明 650500

空间特征光谱特征长波红外高光谱图像高光谱分类 K-means K-means, PCA, long wave infrared spectral features

摘要

高光谱图像（hyper spectral imagery，HSI）分类已成为探测技术的重要研究方向之一，同时也在**和民用领域得到广泛运用。然而，波段数目巨大、数据冗余、空间特征利用率低等因素已成为高光谱图像分类的挑战，且现有的高光谱分类大多利用可见光或短波红外高光谱数据分类。针对这些问题，本文提出了一种基于光谱和空间特征的 K-means分类方法。首先提取空间特征，然后将光谱与空间特征相结合并降维，最后引入 K-means算法得到较普通 K-means更佳的分类结果。并将此算法运用在长波红外的高光谱图像分类中。

Abstract

Hyper spectral image classification has become one of the most important research directions in detection technology; furthermore, it has been widely used in military and civilian fields. However, the significant number of bands, data redundancy, and low utilization of spatial features render the classification of hyper spectral images challenging, and most of existing hyper spectral image classifications use visible light or short-wave infrared data. Hence, a K-means classification method based on spectral and spatial features is proposed in this paper. First, spatial features are extracted; next, the spectral features are combined with the spatial features and the dimensions are reduced. Finally, the K-means algorithm is introduced to obtain classification results that are better than those of normal K-means, and the algorithm is applied to long-wave infrared hyper spectral image classification.

参考文献

[1] 何同弟. 高光谱图像的分类技术研究[D]. 重庆: 重庆大学, 2014. HE Tongdi. The Classification Technology Research Based on Hyperspectral Image[D]. Chongqing: Chongqing University, 2014.

[2] 黄何, 康镇. 高光谱图像分类[J]. 科技传播, 2019, 11(1): 123-126. HUANG He, KANG Zhen. Hyperspectral image classification[J]. Science and Technology Communication, 2019, 11(1): 123-126.

[3] 张强. 高光谱影像船舶溢油目标异常检测与识别[D]. 大连: 大连海事大学, 2018. ZHANG Qiang. Hyperspectral Image Abnormal Detection and Recognition of Ship Oil Spill Target[D]. Dalian: Dalian Maritime University, 2018.

[4] 范泽华, 姚江河, 陈杰. 运用近红外高光谱成像技术检测羊肉脂肪及蛋白质含量[J]. 吉林农业, 2016(14): 127. FAN Zehua, YAO Jianghe, CHEN Jie. Determination of fat and protein content in mutton by near infrared hyperspectral imaging[J]. Jilin Agricultural, 2016 (14): 127.

[5] 高海龙. 基于透射和反射高光谱成像技术的马铃薯缺陷检测方法研究[D]. 武汉: 华中农业大学, 2014. GAO Hailong. Potato Defect Detection Method Based on Transmission and Reflection Hyperspectral Imaging Technology[D]. Wuhan: Huazhong Agricultural University, 2014.

[6] 梁继, 王建, 王建华. 基于光谱角分类器遥感影像的自动分类和精度分析研究[J]. 遥感技术与应用, 2002(6): 299-303, 405. LIANG Ji, WANG Jian, WANG Jianhua. Automatic classification and accuracy analysis of remote sensing image based on spectral angle classifier[J]. Remote Sensing Technology and Application, 2002(6): 299-303, 405.

[7] 黄菁. 高光谱图像编码研究[D]. 南京: 南京理工大学, 2008. HUANG Jing. Research on Hyperspectral Image Coding[D]. Nanjing: Nanjing University of Technology, 2008.

[8] 陈进, 王润生. 高斯最大似然分类在高光谱分类中的应用研究[J]. 计算机应用, 2006, 26(8): 1876-1878. CHEN Jin, WANG Runsheng. Application of Gaussian maximum likelihood classification in hyperspectral classification[J]. Computer Application, 2006, 26 (8): 1876-1878.

[9] Selim S Z, Ismail M A. K-means-type algorithms: a generalized convergence theorem and characterization of local optimality[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1984, 6(1): 81-87.

[10] Modha D S, Spangler W S. Feature weighting ink-means clustering[J]. Machine Learning, 2003, 52(3): 217-237.

[11] 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. SU Hongjun, DU Peijun, SHENG Yehua. Research on band selection algorithm of hyperspectral image[J]. Computer Application Research, 2008, 25 (4): 1093-1096.

[12] 李玉, 甄畅, 石雪. 基于熵加权K-means 全局信息聚类的高光谱图像分类[J]. 中国图象图形学报, 2019, 24(4): 0630-0638. LI Yu, ZHEN Chang, SHI Xue. Hyperspectral image classification based on entropy weighted K-means global information clustering[J]. Chinese Journal of Image Graphics, 2019, 24 (4): 0630-0638.

[13] 黄鸿, 郑新磊. 加权空-谱与最近邻分类器相结合的高光谱图像分类[J]. 光学精密工程, 2016, 24(4): 873-881. HUANG Hong, ZHENG Xinlei. Hyperspectral image classification based on weighted space spectrum and nearest neighbor classifier[J].Optical Precision Engineering, 2016, 24 (4): 873-881.

[14] 王旭红, 肖平, 郭建明. 高光谱数据降维技术研究[J]. 水土保持通报, 2006(6): 89-91. WANG Xuhong, XIAO Ping, GUO Jianming. Research on dimension reduction technology of hyperspectral data[J]. Bulletin of soil and Water Conservation, 2006(6): 89-91.

[15] ZHENG Weijian, LEI Zhenggang, YU Chunchao, et al. Research on ground-based LWIR hyperspectral imaging remote gas detection[C/OL]//Applied Optics and Photonics China, 2015: DOI:10.1117/12.2199686.

汪凌志, 雷正刚, 周浩, 余春超, 杨智雄, 段绍丽, 聂冬. 基于空-谱特征 K-means的长波红外高光谱图像分类[J]. 红外技术, 2020, 42(4): 348. WANG Lingzhi, LEI Zhenggang, ZHOU Hao, YU Chunchao, YANG Zhixiong, DUAN Shaoli, NIE Dong. Long-wave Infrared Hyperspectral Image Classification Based on K-means of Spatial-Spectral Features[J]. Infrared Technology, 2020, 42(4): 348.

基于空-谱特征 K-means的长波红外高光谱图像分类

关于本站 Cookie 的使用提示

全站搜索

基于空-谱特征 K-means的长波红外高光谱图像分类

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索