基于量子遗传光谱角分类算法的高光谱植被特征波段选取  

A Hyperspectral Vegetation Feature Band Selection Based on Quantum Genetic Spectral Angle Mapper Algorithm

作　　者：邓志刚 赵红梅[2] 查文娴 汤林玲 田野 DENG Zhi-gang;ZHAO Hong-mei;ZHA Wen-xian;TANG Lin-ling;TIAN Ye(School of Information and Software Engineering,East China Jiaotong University,Nanchang 330013,China;Key Laboratory of Poyang Lake Wetland and Watershed Research(Jiangxi Normal University),Ministry of Education,Nanchang 330022,China)

机构地区：[1]华东交通大学信息与软件工程学院,江西南昌330013 [2]江西师范大学鄱阳湖湿地与流域研究教育部重点实验室/地理与环境学院,江西南昌330022

出　　处：《光谱学与光谱分析》2024年第11期3258-3265,共8页Spectroscopy and Spectral Analysis

基　　金：国家自然科学基金项目(42161062,42361066);鄱阳湖湿地与流域研究教育部重点实验室开放基金项目(PK2020001)资助。

摘　　要：高光谱数据往往具有数百个连续的窄波段,能够反应地物必要且详细的光谱反射信息,因而被广泛应用于地物精细分类中。然而,由于高光谱窄波段间较强的相关性和冗余性,将整个原始高光谱数据应用于实际分类中,并不能获得令人满意的精度。因此,特征波长或波段选择一直以来都是高光谱实际应用的关键和难点所在。前期的特征波段选择方法不仅计算效率低,容易陷于局部优化,而且波段指向性和解释性不强。以鄱阳湖湿地连续极端干旱情况下1月—5月份枯水期植被物种精细分类中的特征波段选择为例,采用便携式地物光谱仪(SVC HR1024)实测的包括青蓼、藜蒿、紫云英、风花菜、长刺酸模、看麦娘、虉草、苔草、南荻、芦苇等10种湿地植物物种的高光谱反射数据,引入量子遗传算法(QGA),综合基于k近邻分类器的光谱角分类方法(KNN-SAM),提出基于量子遗传k近邻光谱角分类算法(QGA-KNN-SAM),获取适用于湿地植被高光谱精细分类的特征波长,同时采用k中心点聚类算法确定特征波段区间。该算法与基于传统遗传k近邻光谱角分类算法(GA-KNN-SAM)进行对比实验发现,QGA-KNN-SAM的平均分类精度为95%左右,明显高于GA-KNN-SAM的平均分类精度90%;且基于QGA-KNN-SAM算法的特征波长点及波段相对聚焦,其跨度为589~634.4 nm,明显低于GA-KNN-SAM的1107.6~1205 nm。与传统植被的精细分类不同,湿地植被的精细分类除考虑反应植被的光谱波段外,还需要考虑反应地表水文特征的波段信息。与目前常见的多光谱及高光谱卫星影像的波段分布对比发现,QGA-KNN-SAM算法选取的特征波段的指向性和可解释性更优。该算法既提高了波段选择的计算效率和可解释性,又弥补了在波段选择研究中QGA方法的缺失,可为同类研究提供科学支撑。Hyperspectral data collects essential and detailed spectral responses from ground objects through hundreds of contiguous narrow spectral wavelength bands and is widely used for vegetation fine classification.However,classification accuracy is not often satisfactory in a cost-effective way when using all original hyperspectral information(HSI)for practical applications because of its strong correlation and redundantness.Therefore,feature wavelength/band selection is crucial and difficult for HSI applications.Previous band selection methods have some drawbacks,such as low computation efficiency,lack of interpretability,being trapped in local optimization,and so on.Our study focuses on the hyperspectral feature band selection for the vegetation species fine classification of Poyang Lake wetland in continuous extreme drought conditions.Hyperspectral reflectance data of 10 plant species,such as Green polygonum,Artemisia Selengensis,Astragalus sinicus,Rorippa globose,Rumex trisetifer Stokes,Sonoma alopecurus,Phalaris arundinacea,Carexcinerascens,Miscanthus sacchariflorus and Phragmites australis collected by SVC spectrometer(SVC HR1024)is used in this work.We introduce the Quantum Genetic Algorithm(QGA),which is combined with Spectral Angle Mapper-based k-Nearest Neighbors classifier(KNN-SAM),and propose a new feature band selection algorithm,i.e.,QGA-KNN-SAM,to select feature wavelength.Then,we use the K-Medoide clustering algorithm to determine the feature band interval.In our experiment,the classification performance of the proposed QGA-KNN-SAM is compared with the traditional GA-KNN-SAM algorithm.QGA-KNN-SAM generates an average classification accuracy value of 95%,higher than GA-KNN-SAM(90%).Moreover,QGA-KNN-SAM generates the feature bands range between 589~634.4 nm,which is relatively more concentrated than achieved by GA-KNN-SAM(1107.6~1205 nm).A wavelength band that reflects the surface hydrological characteristics and vegetation should be considered in the fine classification of wetland vegetation,which is dif

关 键 词：量子遗传算法 光谱角绘图 湿地植被 高光谱波段选择 

分 类 号：TP751.1[自动化与计算机技术—检测技术与自动化装置]