改进3D-Octave卷积的高光谱图像分类方法  

An improved 3D Octave convolution-based method for hyperspectral image classification

作　　者：郑宗生[1] 王政翰 王振华[1] 卢鹏[1] 高萌 霍志俊 ZHENG Zongsheng;WANG Zhenghan;WANG Zhenhua;LU Peng;GAO Meng;HUO Zhijun(Department of Information,Shanghai Ocean University,Shanghai 201306,China)

机构地区：[1]上海海洋大学信息学院,上海201306

出　　处：《自然资源遥感》2024年第4期82-91,共10页Remote Sensing for Natural Resources

基　　金：国家自然科学基金项目“一种面向对模态遥感信息的质量抽样检验方案研究”(编号:41671431);上海市科委地方能力建设项目“复杂潮汐环境下海岛(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。

摘　　要：高光谱图像数据具有维度高、数据稀疏、空间光谱信息丰富等特点,针对空谱联合分类模型中高光谱图像卷积操作处理大片相同类别像素区域时会存在计算的空间冗余,3D卷积对深层空间纹理特征提取不充分,串行注意力机制结构不能充分考虑空谱相关性的问题,该文提出了改进的3D-Octave卷积高光谱图像分类模型。首先改进的3D-Octave卷积模块将输入的高光谱图像数据划分为高频特征图和低频特征图,减少空间信息冗余,提取多尺度的空间光谱特征,结合跨层融合策略,加强对浅层空间纹理特征和光谱特征的提取;随后利用2D卷积提取深层空间纹理特征并进行光谱特征融合;最后使用三维注意力机制跨纬度交互实现对有效特征的关注和激活,增强网络模型的性能和鲁棒性。结果表明,由于充分提取有效空谱联合特征,在印第安松树林(Indian Pines,IP)数据集的训练集比例为10%的条件下,OA,Kappa和AA分别为99.32%,99.13%和99.15%;在帕维亚大学(Pavia University,PU)数据集的训练集比例为3%的条件下,OA,Kappa和AA分别为99.61%,99.44%和99.08%。与5个主流分类模型进行对比,获得了更高的分类精度。Hyperspectral image data are characterized by high dimensionality,sparse data,and rich spatial and spectral information.In spatial-spectral joint classification models,convolution operations for hyperspectral images can lead to computational spatial redundancy when processing large regions of pixels of the same category.Furthermore,the 3D convolution fails to sufficiently extract the deep spatial texture features,and the serial attention mechanism cannot fully account for spatial-spectral correlations.This study proposed an improved 3D Octave convolution-based model for hyperspectral image classification.First,the input hyperspectral images were divided into high-and low-frequency feature maps using an improved 3D Octave convolution module to reduce spatial redundancy information and extract multi-scale spatial-spectral features.Concurrently,a cross-layer fusion strategy was introduced to enhance the extraction of shallow spatial texture features and spectral features.Subsequently,2D convolution was used to extract deep spatial texture features and perform spectral feature fusion.Finally,a 3D attention mechanism was used to focus on and activate effective features through interactions across latitudes,thereby enhancing the performance and robustness of the network model.The results indicate that,due to the adequate extraction of effective spatial-spectral joint features,the overall accuracy(OA),Kappa coefficient,and average accuracy(AA)were 99.32%,99.13%,and 99.15%,respectively in the case where the Indian Pines(IP)dataset accounted for 10%in the training set and were 99.61%,99.44%,and 99.08%,respectively when the Pavia University(PU)dataset represented for 3%of the training set.Compared to five mainstream classification models,the proposed method exhibits higher classification accuracy.

关 键 词：空间冗余 3D-Octave卷积 跨层融合 多尺度 三维注意力机制 

分 类 号：TP79[自动化与计算机技术—检测技术与自动化装置]