增强类可分性的高光谱图像分类  

Hyperspectral image classification with enhanced class separability

作　　者：方帅[1,2] 张坤 张晶 曹洋[3] 石为开[4] Fang Shuai;Zhang Kun;Zhang Jing;Cao Yang;Shi Weikai(School of Computer Science and Information Engineering,Hefei University of Technology,Hefei 230601,China;Anhui Province Key Laboratory of Industry Safety and Emergency Technology,Hefei 230601,China;Department of Automation,School of Information Science and Technology,University of Science and Technology of China,Hefei 230027,China;Computer Technology and Application,Macao University of Science and Technology,Macao 999078,China)

机构地区：[1]合肥工业大学计算机与信息学院,合肥230601 [2]工业安全与应急技术安徽省重点实验室,合肥230601 [3]中国科学技术大学信息科学技术学院自动化系,合肥230027 [4]澳门科技大学计算机技术与应用,澳门999078

出　　处：《中国图象图形学报》2021年第8期1940-1951,共12页Journal of Image and Graphics

基　　金：国家重点研发计划项目(2018YFC0213104);国家自然科学基金项目(61872327,61175033);中央高校基本科研业务费专项资金资助(JZ2017HGBZ0930,WK2380000001)。

摘　　要：目的在高光谱图像分类中,由于成像空间分辨率较低,混合像元大量存在。混合像元使得不同类别的光谱特征发生改变,失去原有的独特性,类内差异变大,类间差异变小。针对这一问题,本文提出基于分组滚动引导滤波的策略。同时针对高光谱图像中存在的"维数灾难"问题,提出了弹性网逻辑回归分类器的框架。方法通过线性判别分析(linear discriminant analysis,LDA)算法生成具有判别性的引导图,对高光谱图像的每个波段执行滚动引导,从而让光谱曲线呈现类内凝聚、类间距离增大的趋势。通过构造逻辑回归目标函数的L1&L2范数正则项约束进行嵌入式波段选择,为每个类别选择出各自可分性强的波段,同时可以使高度相关性的波段保留下来作为分类依据。最后使用邻域优化策略对分类后结果进一步优化,提升分类精度。结果分别在3个实验数据集上与其他分类算法进行对比,实验结果表明,本文算法的分类结果取得明显提升。本文算法的总体分类精度(overall accuracy,OA)在Indian Pines、Salinas和KSC(Kennedy Space Center)数据集上分别为96.61%、98.66%和99.04%,比其他算法平均分别高出4.8%、3%和1%,同时也在Indina Pines数据集中进行了对比实验以验证增强混合像元光谱可分性和波段可分性算法的有效性,对比实验结果表明本文算法改善了分类效果。结论分别在光谱特性和波段选择两个环节增强类可分性,分类精度取得明显提升;同时,本文算法适合不同的数据集,并且在不同数量的训练样本下OA均表现较优,算法具有一定的鲁棒性。Objective Hyperspectral images have been investigated and hyperspectral image classification has been widely used in many fields in recent years.Long-distance remote sensing hyperspectral images have a lot of mixed pixels due to the low spatial resolution.The ground features originally have unique spectral characteristics,but the mixed pixels reduce the separability of spectral characteristics of different ground,which increases the difficulty of hyperspectral image classification.Observing the spectral curves of long-distance remote sensing hyperspectral images indicates that the spectral curves of the single type show the tendency of larger difference within the class,and the difference between classes becomes smaller because it is mixed with different types of ground features.If the selected samples are insufficient,then misclassification between classes may occur.Moreover,the classification map has"salt and pepper noise",which leads to low classification accuracy.The traditional method uses the spectral-spatial feature joint classification method to increase the constraint of spatial information for improving the classification accuracy.This way can correct some misclassification results,but it does not improve the problem of difficult classification between classes caused by mixed pixels.Thus,a strategy based on grouped rolling guidance filtering is proposed in this study.The linear discriminant analysis(LDA)algorithm is used to generate a discriminative guidance image,and rolling guidance filtering is performed on each band of the hyperspectral image.Spectral curves show the trend of intra-class condensation given that the guidance image contains the information of classification,and the distance between classes increases.At the same time,hyperspectral images have lots of bands,and many adjacent bands may be heavily redundant and fail to provide additional discriminative information.The generalization capability of the classifier is limited when high-dimensional bands are fed back,that is,the curse of dimen

关 键 词：遥感 高光谱图像分类 增强类可分性 分组滚动引导滤波 弹性网逻辑回归 

分 类 号：TP751.[自动化与计算机技术—检测技术与自动化装置]