航拍图像跨数据域特征迁移道路提取方法  

Feature-representation-transfer based road extraction method for cross-domain aerial images

作　　者：王舒洋 慕晓冬 贺浩 杨东方 马晨晖 WANG Shuyang;MU Xiaodong;HE Hao;YANG Dongfang;MA Chenhui(The Rocket Force University of Engineering, College of Operational Support, Xi’an 710025, China;The Rocket Force University of Engineering, College of Missile Engineering, Xi’an 710025, China)

机构地区：[1]火箭军工程大学作战保障学院,陕西西安710025 [2]火箭军工程大学导弹工程学院,陕西西安710025

出　　处：《测绘学报》2020年第5期611-621,共11页Acta Geodaetica et Cartographica Sinica

基　　金：国家自然科学基金(61403398,61673017);陕西省自然科学基金面上项目(2017JM6077)。

摘　　要：针对传统道路提取方法应用于新数据泛化能力不足的问题,研究了通过特征迁移和编解码网络实现跨数据域的道路提取方法。首先,构建了基于编解码网络的道路提取基本模型,用于实现单一数据来源的道路提取任务。然后,基于道路提取网络结构和循环一致性原则,提出了用于跨数据域图像特征迁移的循环生成对抗网络,使目标域图像映射入源域特征空间。使用预训练的道路提取模型处理特征迁移后的目标域图像,即可实现跨数据域道路提取任务。试验结果表明,本文所提方法能够拓展道路提取网络的泛化能力,准确有效地提取跨数据域图像中的道路目标。相较于未特征迁移的结果,本文所提方法大幅改善了道路提取指标,使得F1提升了50%以上。本文方法不需要目标域的标注信息,也不需要对道路提取网络进行微调训练,而只需训练由目标域向源域的特征迁移模型,所耗时间和人力成本较低,因而具有良好的应用价值。Aiming at the problem of the insufficient generalization ability of traditional road extraction methods when applying to a new dataset,this paper proposes a cross-domain road extraction method that realized by feature-representation-transfer and encoder-decoder network.Firstly,a basic road extraction model based on encoder-decoder network is designed to segment the road from a single data source.Then,based on the structure of road extraction network and the principle of cycle-consistent,a cycle generative adversarial network for feature transfer of cross-domain imagery is used,which maps the feature of target city images to the domain of source data.Finally,the pre-trained road extraction model is used to segment the target domain images after the feature transfer,so that the cross-domain road extraction can be realized.The experimental results show that the proposed method improves the generalization ability of the road extraction network and can extract the road target from cross-domain images accurately and effectively.Compared with the results without feature transfer,the proposed method greatly improves the road extraction metric,and increases the F1-score by more than 50%.The proposed method does not require any annotation of the target domain images,nor does it need to fine-tune the road extraction network,while it only need to train the feature transfer model from the target domain to the source domain.Therefore,it has good application value.

关 键 词：道路提取 遥感 迁移学习 深度学习 生成对抗网络 编解码网络 

分 类 号：P237[天文地球—摄影测量与遥感]