Toward Accurate and Efficient Road Extraction by Leveraging the Characteristics of Road Shapes

doi:10.1109/TGRS.2023.3284478

CORC > 自动化研究所 > 中国科学院自动化研究所 > 多模态人工智能系统全国重点实验室

	Toward Accurate and Efficient Road Extraction by Leveraging the Characteristics of Road Shapes
	Wang, Changwei 2,3; Xu, Rongtao 2,3; Xu, Shibiao 2,3; Meng, Weiliang 2,3; Wang, Ruisheng 1; Zhang, Jiguang 2,3; Zhang, Xiaopeng 2,3
刊名	IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
	2023
卷号	61 页码:16
关键词	Efficient and accurate road extraction efficient strip transformer module (ESTM) geometric deformation estimation module (GDEM) road edge focal loss (REF loss) road shape-aware network (RSANet)
ISSN号	0196-2892
DOI	10.1109/TGRS.2023.3284478
通讯作者	Xu, Shibiao(shibiaoxu@bupt.edu.cn) ; Meng, Weiliang(weiliang.meng@ia.ac.cn)
英文摘要	Automatically extracting roads from very high-resolution (VHR) remote sensing images is of great importance in a wide range of remote sensing applications. However, complex shapes of roads (i.e., long, geometrically deformed, and thin) always affected the extraction accuracy, which is one of the challenges of road extraction. Based on the insight into road shape characteristics, we propose a novel road shape-aware network (RSANet) to achieve efficient and accurate road extraction. First, we introduce the efficient strip transformer module (ESTM) to efficiently capture the global context to model the long-distance dependence required by long roads. Second, we design a geometric deformation estimation module (GDEM) to adaptively extract the context from the shape deformation caused by shooting roads from different perspectives. Third, we provide a simple but effective road edge focal loss (REF loss) to make the network focus on optimizing the pixels around the road to alleviate the unbalanced distribution of foreground and background pixels caused by the roads being too thin. Finally, we conduct extensive evaluations on public datasets to verify the effectiveness of RSANet and each of the proposed components. Experiments validate that our RSANet outperforms state-of-the-art methods for road extraction in remote sensing images.
资助项目	National Natural Science Foundation of China[U21A20515] ; National Natural Science Foundation of China[62271074] ; National Natural Science Foundation of China[U2003109] ; National Natural Science Foundation of China[62171321] ; National Natural Science Foundation of China[62071157] ; National Natural Science Foundation of China[62162044] ; National Natural Science Foundation of China[61971418] ; Open Research Fund of Key Laboratory of Space Utilization, Chinese Academy of Sciences[LSU-KFJJ-2021-05] ; Open Projects Program of National Laboratory of Pattern Recognition
WOS关键词	CENTERLINE EXTRACTION ; NETWORK ; INFORMATION ; FEATURES ; IMAGERY ; AWARE
WOS研究方向	Geochemistry & Geophysics ; Engineering ; Remote Sensing ; Imaging Science & Photographic Technology
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:001017380100015
资助机构	National Natural Science Foundation of China ; Open Research Fund of Key Laboratory of Space Utilization, Chinese Academy of Sciences ; Open Projects Program of National Laboratory of Pattern Recognition
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/53795]
专题	多模态人工智能系统全国重点实验室
通讯作者	Xu, Shibiao; Meng, Weiliang
作者单位	1.Univ Calgary, Dept Geomat Engn, Calgary, AB T2N 1N4, Canada 2.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Wang, Changwei,Xu, Rongtao,Xu, Shibiao,et al. Toward Accurate and Efficient Road Extraction by Leveraging the Characteristics of Road Shapes[J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,2023,61:16.
APA	Wang, Changwei.,Xu, Rongtao.,Xu, Shibiao.,Meng, Weiliang.,Wang, Ruisheng.,...&Zhang, Xiaopeng.(2023).Toward Accurate and Efficient Road Extraction by Leveraging the Characteristics of Road Shapes.IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,61,16.
MLA	Wang, Changwei,et al."Toward Accurate and Efficient Road Extraction by Leveraging the Characteristics of Road Shapes".IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 61(2023):16.