摘要
高光谱图像具有数据量大、波段多和波段间相关性强等特性,传统高光谱分类方法通常单独考虑光谱和空间信息,特征提取不充分,忽略了图像纹理构造和重要光谱信息。针对这些问题,提出一种基于卷积神经网络(convolution neural network,CNN)的高光谱分类方法。该方法基于三维CNN(3D CNN),处理多尺度空谱数据,并对双重注意力机制进行改进,提出光谱注意力机制;其次,采取跨层特征融合和多通道特征提取策略,进一步提高地物分类精度。选取“高分五号”卫星拍摄的2景影像共6043个样本作为实验数据,并将提出的方法与支持向量机(support vector machine,SVM),一维CNN(1D CNN),二维CNN(2D CNN),3D CNN和残差网络(residual network,ResNet)进行比较分析。结果表明,所提方法的总体精度(overall accuracy,OA)和Kappa系数均有显著提高,OA值均达到95%以上。其中,OA在江苏南通地区数据集上达到了95.84%,较SVM,1D CNN,2D CNN,3D CNN和ResNet方法分别提高了21.54,21.71,7.28,3.94,2.56百分点。
Hyperspectral images are characterized by large data volumes,multiple bands,and strong interband correlation.Conventional classification methods using hyperspectral images usually consider only spectral or spatial information,while suffering insufficient feature extraction and ignoring the texture structures and important spectral information of images.Aiming at these problems,this study proposed a new classification method using hyperspectral images.First,multi-scale spatial-spectral data were processed based on the three-dimensional convolutional neural network(3D CNN),and a spectral attention mechanism was proposed by improving the dual attention mechanism.Then,the classification accuracy of surface features was further improved by adopting cross-layer feature fusion and multi-channel feature extraction strategies.In this study,6043 samples of two scenes of images captured by the GF-5 satellite were selected as experimental data.The proposed method was compared with five other methods,namely the support vector machine(SVM),the one-dimensional convolutional neural network(1D CNN),the two-dimensional convolutional neural network(2D CNN),the 3D CNN,and the residual network(ResNet).The results show that the method proposed in this study yielded significantly improved overall accuracy(OA)and Kappa coefficients with averages of 95.25%and 0.943,respectively.When applied to the dataset of Nantong,Jiangsu,this method yielded OA of up to 95.84%,which was 21.54,21.71,7.28,3.94,and 2.56 percentage points higher than that of the five other methods,respectively.
作者
郑宗生
刘海霞
王振华
卢鹏
沈绪坤
唐鹏飞
ZHENG Zongsheng;LIU Haixia;WANG Zhenhua;LU Peng;SHEN Xukun;TANG Pengfei(Department of Information,Shanghai Ocean University,Shanghai 201306,China)
出处
《自然资源遥感》
CSCD
北大核心
2023年第2期105-111,共7页
Remote Sensing for Natural Resources
基金
国家自然科学基金项目“一种面向多模态遥感信息的质量抽样检验方案研究”(编号:41671431)
上海市科委市地方能力建设项目“复杂潮汐环境影响下海岛(礁)地物信息提取与精度验证方法及其示范应用”(编号:19050502100)
国家海洋局数字海洋科学技术重点实验室开放基金项目“面向深度学习与气象云图大数据的台风强度分类研究”(编号:B201801034)共同资助。
作者简介
第一作者:郑宗生(1979-),男,博士,副教授,研究方向为遥感图像处理。Email:zszheng@shou.edu.cn;通信作者:刘海霞(1997-),女,硕士研究生,研究方向为遥感图像分类。Email:717468912@qq.com。
