基于双流并行全向扫描Mamba的遥感影像建筑物变化检测  

Building Change Detection Based on Dual-Stream Parallel Omnidirectional Scan Mamba Network

作　　者：厉芳婷[1,2] 张过 周方栋[3] 王上 梁思 李志炜 LI Fangting;ZHANG Guo;ZHOU Fangdong;WANG Shang;LIANG Si;LI Zhiwei(State Key Laboratory of Information Engineering in Surveying,Mapping and Remote Sensing,Wuhan University,Wuhan 430079,China;Hubei Institute of Photogrammetry and Remote Sensing,Wuhan 430074,China;Faculty of Artificial Intelligence in Education,Central China Normal University,Wuhan 430079,China;Troops,Beijing 100841,China)

机构地区：[1]武汉大学测绘遥感信息工程国家重点实验室,湖北武汉430079 [2]湖北省航测遥感院,湖北武汉430074 [3]华中师范大学人工智能教育学部,湖北武汉430079 [4]91001部队,北京100841

出　　处：《武汉大学学报（信息科学版）》2024年第9期1574-1585,共12页Geomatics and Information Science of Wuhan University

基　　金：国家自然科学基金(62177017)。

摘　　要：采用深度学习技术对海量遥感影像进行建筑物变化检测与解译分析,可以为自然资源要素管理和国土资源节约集约化提供关键科学依据和数据支持,对自然资源动态监测和空间治理现代化具有重要意义。状态空间模型Mamba结合了全局感受野与动态加权,在时间序列预测任务中能够更好地捕捉趋势和周期性信息,然而目前Mamba在遥感影像密集预测的研究尚不充分,对高分辨率遥感影像变化检测存在计算复杂度高、检测效率低等问题。对影响Mamba算法参数量的关键因素进行了深入分析,提出了双流并行全向扫描Mamba网络,构建通道内的数据并行化处理方法,在通道总数不变的情况下,有效减少单个Mamba块中数据的通道数,实现网络总体参数量的下降和高效的特征提取。在LEVIR-CD和WHU-CD两个数据集上进行了对比实验,结果表明,所提网络各项指标均优于非Mamba架构的网络,与基准网络对比训练效率分别提升了19.45%和8.26%,且在网络参数量与计算复杂度方面显著降低,分别降低了35.8%和22.4%。Objectives The state space model Mamba,which combines global sensing field and dynamic weighting,can better capture the trend and periodic information in the time series prediction task,and has become an important direction in the current deep learning technologies for remote sensing image analysis and interpretation.However,the current research of Mamba in the dense prediction of remote sensing images is insufficient,and there are problems such as high computational complexity and low detection efficiency for the change detection of high-resolution remote sensing images.Methods We conduct an in-depth analysis of the key factors affecting the number of parameters of the Mamba layer,and propose a dual-stream parallel omnidirectional scan Mamba(DSPOSM)model architecture to construct an in-channel data parallelization processing method.The proposed DSPOSM model can effectively reduce the number of channels of the data in single Mamba block while the total number of channels remains unchanged,in order to achieve highly efficient feature extraction based on the decrease of the overall number of parameters of the model.Results Comparative experimental results on the LEVIR-CD and WHU-CD datasets show that the proposed method outperforms the non-Mamba architecture method in all metrics and significantly reduces the number of parameters and computational complexity of the network by 35.8%and 22.4%,and improves the training efficiency by 19.45%and 8.26%,compared with the benchmark method,respectively.Conclusions The proposed DSPOSM method can significantly reduce the number of parameters and computational complexity of Mamba-based networks and improve training efficiency.

关 键 词：高分辨率遥感影像 变化检测 深度学习 状态空间模型 双流并行 

分 类 号：P237[天文地球—摄影测量与遥感]