融合光谱滤波的高光谱图像分类深度网络  

Fusion Spectral Filter in Deep Feature Learning Net on Hyperspectral Image Classification

作　　者：张巨萍[1,2] 高光来 苏向东[1] ZHANG Juping;GAO Guanglai;SU Xiangdong(College of Computer Science,Inner Mongolia University,Hohhot 010021,China;College of Computer Information Management,Inner Mongolia University of Finance and Economics,Hohhot 010070,China)

机构地区：[1]内蒙古大学计算机学院,呼和浩特010021 [2]内蒙古财经大学计算机信息管理学院,呼和浩特010070

出　　处：《计算机科学与探索》2018年第11期1806-1814,共9页Journal of Frontiers of Computer Science and Technology

基　　金：国家自然科学基金No.61773224;内蒙古自然科学基金重大项目No.2016ZD06;内蒙古自治区高等学校科学研究基金资助项目No.NJZY14128~~

摘　　要：目前,大量深度学习方法被用于提取超光谱图像特征来完成像素点分类任务。这些超光谱图像虽然经过一系列前期处理,但是仍然包含很多噪声,噪声同时存在于光谱域和空间域。由于这些方法在提取图像深层特征时大多只进行了空间域去噪处理,没有进行光谱域噪声的滤除,最终获得的像素点深度特征中带有噪声,降低了分类精度。结合分类效果出色的空谱学习网络(spectral-spatial network,SSN),提出两种融合光谱域滤波的深层特征学习模型——Saviztky-Galoy滤波空谱学习网络(SG-SSN)和中值滤波空谱学习网络(MF-SSN)。两个模型首先分别对图像光谱域进行SG滤波和中值滤波,接着对滤波后的图像使用SSN学习图像深层特征。在两个标准数据集上,使用总体精度(overall accuracy,OA)、平均精度(average accuracy,AA)以及Kappa系数度量分类效果,发现融合光谱滤波的SG-SSN和MF-SSN模型能有效提升空谱学习网络的分类精度。利用实验比较和分析了深层特征学习中模型层数对模型性能的影响。Recently,many deep learning methods are used in hyperspectral image(HSI)pixel classification task.However,spectral noise and spatial noise still exist in HSI simultaneously even with a series of preprocessing.Most of these deep learning methods only involve the noise filtering in spatial domain while paying no attention to that in spectral domain.So spectral noise is preserved in deep features after deep feature learning process,which degrades the pixel classification accuracy.Given the excellent classification accuracy of spectral-spatial network(SSN),this paper proposes two deep feature learning models fused spectral noise filtering with it,called Saviztky-Galoy filtering SSN(SG-SSN)and median filtering SSN(MF-SSN),respectively.The models remove spectral noise by using Saviztky-Galoy filtering or median filtering on spectral domain first.Then,the denoised image is fed into SSN to learn deep features of HSI for its excellent classification effects.Experiments on two popular HSI datasets demonstrate the effectiveness of SG-SSN and MF-SSN,and classification result is measured by overall accuracy(OA),average accuracy(AA)and Kappa coefficient.How the appropriate layer number of model affects model performance is also discussed.

关 键 词：超光谱图像 SG滤波 中值滤波 空谱网络(SSN) 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]