基于特征注意力融合网络的遥感变化检测研究  

Remote Sensing Change Detection Based on Feature Fusion and Attention Network

作　　者：蓝凌翔 池明旻[1] LAN Ling-xiang;CHI Ming-min(Shanghai Key Laboratory of Data Science,Fudan University,Shanghai 200438,China)

机构地区：[1]复旦大学上海市数据科学重点实验室,上海200438

出　　处：《计算机科学》2022年第6期193-198,共6页Computer Science

基　　金：国家重点研发计划(2017YFA0402600);中国石油化工股份有限公司科技攻关项目(PE19003-3)。

摘　　要：变化检测是遥感的重要任务之一,通常被认为是像元级的分类问题。近年来,深度神经网络由于对双时相图像具有强大的层次表示能力,在变化检测中得到了广泛应用。文中基于编码器-融合-解码器框架,提出了一种基于特征注意力融合的变化检测网络(FFAN),其将编码器生成的特征与经由注意力机制增强后的双时相差异特征进行融合,以更好地捕获双时相变化信息。特别地,通过由注意力机制增强的双时相特征,可以显著增强深层网络中间层中变化信息的传播,该特征显式地建模双时相输入的相互依赖性并自适应地重新校准FFAN中的变化激活。在开源数据集上进行的实验表明,与现有方法相比,所提FFAN具有更优异的检测性能。Change detection is one of the essential tasks in remote sensing,which is usually regarded as a pixel-level classification problem.In recent years,deep neural networks have also been widely used in the change detection task due to their powerful hierarchical representation of bi-temporal images.A feature fusion and attention network(FFAN)is proposed based on neural encoder-fusion-decoder framework.It integrates features generated by encoder with the bi-temporal difference feature enhanced by attention mechanism,to better capture the bi-temporal change information.In particular,bi-temporal features enhanced by attention mechanism can significantly enhance the propagation of change information in the intermediate layers of deep networks,which adaptively recalibrates the change activation in FFAN by explicitly modeling the interdependence of bi-temporal inputs.Experiments conducted on open-source dataset demonstrate that,compared with existing methods,FFAN obtains better performance.

关 键 词：变化检测 遥感 深度学习 注意力机制 特征融合 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]