用于遥感图像变化检测的结构感知多尺度混合网络  

Structure-Aware Multiscale Hybrid Network for Change Detection of Remote Sensing Images

作　　者：刘祺 曹林[2,3] 田澍 杜康宁 宋沛然 郭亚男 Liu Qi;Cao Lin;Tian Shu;Du Kangning;Song Peiran;Guo Yanan(School of Instrument Science and OptoElectronics Engineering,Beijing Information Science&Technology University,Beijing 100101,China;Key Laboratory of Optoelectronic Measurement Technology and Instrument,Ministry of Education,Beijing Information Science&Technology University,Beijing 100101,China;Key Laboratory of Information and Communication Systems,Ministry of Information Industry,Beijing Information Science&Technology University,Beijing 100101,China)

机构地区：[1]北京信息科技大学仪器科学与光电工程学院,北京100101 [2]北京信息科技大学光电测试技术及仪器教育部重点实验室,北京100101 [3]北京信息科技大学信息与通信系统信息产业部重点实验室,北京100101

出　　处：《激光与光电子学进展》2024年第14期313-323,共11页Laser & Optoelectronics Progress

基　　金：国家自然科学基金(62001032,62201066,U20A20163);北京市教委科研计划(KZ202111232049,KM202111232014)。

摘　　要：近年来,卷积神经网络(CNN)凭借强大的特征表示能力在遥感图像变化检测领域取得了显著成就。然而,CNN在双时态图像远程依赖建模方面存在不足,导致对结构信息的识别性较差。与之不同,Transformer技术能够有效捕捉输入像素间的长距离依赖关系,有助于感知和推理图像中的结构信息。为解决现有变化检测方法在模型中难以兼顾全局和局部特征信息的问题,提出多尺度级联CNN-Transformer混合网络。该算法能够充分利用混合网络中的全局和局部语义信息,提升模型对变化对象结构-语义信息的感知能力,级联架构增强了不同尺度间的交互能力,使模型更易理解不同粒度特征的区别与联系。此外,本文还对不同尺度特征进行了权重调节,提升模型对多尺度信息的利用能力。所提方法在CDD和GZ-CD数据集上的F1分数分别达97.8%和87.1%。在两个标准数据集上的实验结果表明,所提方法能有效利用不同尺度特征信息,提升变化检测精度。In recent years,convolutional neural network(CNN),with its powerful feature representation capabilities,has made remarkable achievements in the change detection of remote sensing images.However,CNN has shortcomings in modeling the longrange dependencies of dualtemporal images,resulting in the poor recognition of structural information.In contrast,the Transformer technology can effectively capture the longdistance dependencies between input pixels,thereby helping in perceiving and reasoning structural information in images.To solve the problem that existing change detection methods cannot consider global and local feature information in the model,a multiscale cascaded CNNTransformer hybrid network was proposed in this study.This algorithm can completely use the global and local semantic information on a hybrid network and improve the ability of the model to perceive changes in object structures and semantic information.The cascade network enhances the interaction ability between various scales,making it easier for the model to understand the differences and connections between features with different granularities.In addition,in this study,feature weights were adjusted at various scales to improve the ability of the model to use multiscale information.The F1-score of the proposed method reaches 97.8%and 87.1%on the CDD and GZCD datasets,respectively.Experimental results on the two standard datasets show that this method can effectively use feature information with various scales to improve the change detection accuracy of the model.

关 键 词：变化检测 深度学习 遥感 结构感知 混合网络 

分 类 号：TP751.1[自动化与计算机技术—检测技术与自动化装置]