基于深度学习的多尺度无人机遥感图像道路提取  

Road extraction of UAV remote sensing image based on deep learning

作　　者：张伟 张朝龙 王本林[2] 蔡安宁 ZHANG Wei;ZHANG Chaolong;WANG Benlin;CAI Anning(College of Architecture,Anhui Science and Technology University,Bengbu 233030,China;Department of Geographic Information and Tourism,Chuzhou University,Chuzhou 239000,China;College of Tourism and Social Administration,Nanjing Xiaozhuang University,Nanjing 211171,China)

机构地区：[1]安徽科技学院建筑学院,安徽蚌埠233030 [2]滁州学院地理信息与旅游学院,安徽滁州239000 [3]南京晓庄学院旅游与社会管理学院,江苏南京211171

出　　处：《测绘通报》2024年第6期77-81,共5页Bulletin of Surveying and Mapping

基　　金：国家自然科学基金(52078237);安徽高校省级自然科学研究重点项目(KJ2021A1083,KJ2021A0860);安徽科技学院重点建设学科(XK-XJJC001)。

摘　　要：针对高分辨率遥感影像和目标场景下道路影像数据集获取难度大、成本高等问题,本文探究网络模型在不同尺度下执行提取任务的最佳影像分辨率,并评价各模型在道路提取上的适用性及可靠性,为道路识别工程提供方法借鉴和案例参考。引入图像分割领域3个经典网络模型,使用公开数据集进行模型训练,以无人机航拍的安徽省滁州市影像为试验数据,进行不同尺度下的道路提取,找出各模型在新场景下的最佳分辨率和模型适用性,并进行可靠性评价。试验结果表明,D-LinkNet网络模型在不同尺度的道路提取任务中适用性较强;DeepLabV3+网络模型的可靠性较差;U-Net、D-LinkNet网络模型的道路提取输入影像最佳分辨率分别为1.0、0.5 m。Aiming at the problems of high-resolution remote sensing images and road image datasets in the target scene in terms of difficulty in acquiring,high cost,etc.,we explore the optimal image resolution of the network models to perform the extraction task at different scales,evaluate the applicability and reliability of each model on road extraction,and provide methodological reference and case study for the road recognition project.In this paper,three classical network models in the field of image segmentation are introduced,the models are trained using public datasets,and the unmanned aerial images of Chuzhou city,Anhui province are used as the test data to perform the road extraction work at different scales,to find out the optimal resolution and model applicability of each model in the new scene,and to evaluate the reliability.The experimental results show that the applicability of the D-LinkNet network model is more prominent in the road extraction task at different scales,the reliability of the DeepLabV3+network model is poorer,and the optimal resolutions of the road extraction input images for the U-Net and D-LinkNet network models are 1.0 and 0.5 m,respectively.

关 键 词：高分辨率遥感图像 语义分割 道路提取 注意力机制 

分 类 号：P237[天文地球—摄影测量与遥感]