空谱域适应与XGBoost结合的跨场景高光谱图像分类  

Cross-scene hyperspectral image classification combined spatialspectral domain adaptation with XGBoost

作　　者：王爱丽[1] 丁姗姗 刘和 吴海滨[1] 岩堀祐之 WANG Aili;DING Shanshan;LIU He;WU Haibin;IWAHORI Yuji(Heilongjiang Province Key Laboratory of Laser Spectroscopy Technology and Application,College of measurement and control technology and communication Engineering,Harbin University of Science and Technology,Harbin 150080,China;State Grid Heilongjiang Electric Power Co.,Ltd,Integrated data center,Harbin 150010,China;Department of Computer Science,Chubu University,Aichi 487-8501,Japan)

机构地区：[1]哈尔滨理工大学,测控技术与通信工程学院,黑龙江省激光光谱技术及应用重点实验室,黑龙江哈尔滨150080 [2]国网黑龙江省电力有限公司综合信息中心,黑龙江哈尔滨150010 [3]中部大学计算机科学学院,日本爱知487-8501

出　　处：《光学精密工程》2023年第13期1950-1961,共12页Optics and Precision Engineering

基　　金：国家自然科学基金资助项目(No.61671190);“一带一路”创新人才交流外国专家项目(No.G2022012010L);黑龙江省级领军人才梯队后备带头人资助项目。

摘　　要：针对跨场景高光谱遥感图像分类中源域和目标域的频谱偏移问题,提出一种结合空谱域适应与极度梯度提升树(eXtreme Gradient Boosting, XGBoost)的跨场景高光谱图像分类模型。将深度超参数卷积模型(Depthwise Over-parameterized Convolution Model,DOCM)和大核注意力(Large Kernel Attention,LKA)结合,构成空谱注意力模型,提取源域空谱特征。利用相同的空谱注意力模型对目标域进行特征提取,并与鉴别器完成对抗域适应,减少源域与目标域之间的频谱偏移;通过目标域中少量有标签数据对目标域特征提取器进行有监督域适应,使目标域特征提取器进一步学习目标域的真实分布,并对源域和目标域的特征进行映射,形成相似的空间分布,完成聚类域适应。最后,使用集成分类器XGBoost进行高光谱图像分类,进一步提高模型的训练速度与置信度。在Pavia和Indiana高光谱数据集上的实验结果表明,本文算法的总体分类精度分别达到了91.62%和65.98%。相比较于其他跨场景高光谱图像分类模型,本文所提模型具有更高的地物分类精度。For solving the problem of spectral shift between the source domain and target domain in cross-scene hyperspectral remote sensing image classification,this study proposes a cross-scene hyperspectral image classification model combining spatial-spectral domain adaptation and Xtreme Gradient Boosting(XGBoost).First,the Depth Over Parametric Convolution Model(DOCM)and Large Kernel Attention(LKA)was combined to form a spatial-spectral attention model and extract the spatial-spectral features of the source domain.Next,the same spatialspectral attention model was used to extract features from the target domain,and the discriminator was used to adapt to the confrontation domain to reduce the spectral shift between the source and target domains.Second,the feature extractor of the target domain was adapt-ed to the supervised domain through a small amount of labeled data in the target domain such that the fea-ture extractor of the target domain can learn the true distribution of the target domain and map the features of the source and target domains to form a similar spatial distribution and complete the clustering domain adaptation.Finally,the ensemble classifier XGBoost was used to classify hyperspectral images to further improve the training speed and confidence of the model.Experimental results for the Pavia and Indiana hy-perspectral datasets indicate that the overall classification accuracy of this algorithm reaches 91.62%and 65.98%,respectively.Compared with other cross-scene hyperspectral image classification models,the proposed model has a higher classification accuracy.

关 键 词：高光谱图像 域适应 大核注意力 XGBoost 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]