联合目标特征引导与多重注意力的建筑物变化检测  

Building change detection method combining object feature guidance and multiple attention mechanism

作　　者：丁少鹏 卢秀山[3] 刘如飞[1] 杨懿[2] 顾海燕 李海涛[2] DING Shaopeng;LU Xiushan;LIU Rufei;YANG Yi;GU Haiyan;LI Haitao(College of Geodesy and Geomatics,Shandong University of Science and Technology,Qingdao 266590,China;Chinese Academy of Surveying and Mapping,Beijing 100036,China;College of Ocean Science and Engineering,Shandong University of Science and Technology,Qingdao 266590,China)

机构地区：[1]山东科技大学测绘与空间信息学院,山东青岛266590 [2]中国测绘科学研究院,北京100036 [3]山东科技大学海洋科学与工程学院,山东青岛266590

出　　处：《测绘学报》2024年第6期1224-1235,共12页Acta Geodaetica et Cartographica Sinica

基　　金：国家重点研发计划(2023YFB3907600)。

摘　　要：高分遥感影像具有丰富的细节特征,建筑物变化类型多,尺度差异大。针对建筑物变化在复杂环境中易出现空洞和遗漏的问题,本文提出联合目标特征引导与多重注意力的建筑物变化检测方法,通过建筑物目标级引导强化类别信息,实现高分辨影像精细变化信息提取。该方法由建筑物显著增强模块和目标引导的多重注意力模块组成,通过全局深层特征感知与融合,提取建筑物重点区域,结合目标级特征引导和多重自注意力强化特征表达,增强上下文特征相关关系,有效减少细节特征损失,解决目标空洞和边缘不清晰造成的细节损失问题。通过两组试验表明该方法能够提升准确率,在变化种类越多的场景中有效减少变化损失,提高算法稳定性。High-resolution remote sensing images have rich detail features,and building changes are of variable types with large scale differences.Aiming at the problem that building changes are prone to voids and omissions in complex environments,a building change detection method combining object feature guidance and multiple attention mechanism is proposed to realize fine change information extraction from high-resolution images by enhancing category information through building target-level guidance.The method consists of a building significant enhancement module and a target-guided multi-attention module,which extracts the key areas of the building through global deep feature perception and fusion,combines the target-level feature guidance and multiple self-attention to strengthen the feature expression,enhances the contextual feature correlation,effectively reduces the loss of detailed features,and solves the problem of loss of details caused by the target voids and unclear edges.It is shown through two sets of experiments that this method can improve the accuracy,effectively reduce the change loss in scenes with more kinds of changes,and improve the stability of the algorithm.

关 键 词：高分遥感影像 建筑物变化检测 目标特征 深度学习 注意力机制 

分 类 号：P237[天文地球—摄影测量与遥感]