干旱区生态环境知识资源中心(Arid): Deep Learning with Open Data for Desert Road Mapping

Arid

DOI	10.3390/rs12142274
	Deep Learning with Open Data for Desert Road Mapping
	Stewart, Christopher; Lazzarini, Michele; Luna, Adrian; Albani, Sergio
通讯作者	Stewart, C
来源期刊	REMOTE SENSING
EISSN	2072-4292
出版年	2020
卷号	12 期号:14
英文摘要	The availability of free and open data from Earth observation programmes such as Copernicus, and from collaborative projects such as Open Street Map (OSM), enables low cost artificial intelligence (AI) based monitoring applications. This creates opportunities, particularly in developing countries with scarce economic resources, for large-scale monitoring in remote regions. A significant portion of Earth's surface comprises desert dune fields, where shifting sand affects infrastructure and hinders movement. A robust, cost-effective and scalable methodology is proposed for road detection and monitoring in regions covered by desert sand. The technique uses Copernicus Sentinel-1 synthetic aperture radar (SAR) satellite data as an input to a deep learning model based on the U-Net architecture for image segmentation. OSM data is used for model training. The method comprises two steps: The first involves processing time series of Sentinel-1 SAR interferometric wide swath (IW) acquisitions in the same geometry to produce multitemporal backscatter and coherence averages. These are divided into patches and matched with masks of OSM roads to form the training data, the quantity of which is increased through data augmentation. The second step includes the U-Net deep learning workflow. The methodology has been applied to three different dune fields in Africa and Asia. A performance evaluation through the calculation of the Jaccard similarity coefficient was carried out for each area, and ranges from 84% to 89% for the best available input. The rank distance, calculated from the completeness and correctness percentages, was also calculated and ranged from 75% to 80%. Over all areas there are more missed detections than false positives. In some cases, this was due to mixed infrastructure in the same resolution cell of the input SAR data. Drift sand and dune migration covering infrastructure is a concern in many desert regions, and broken segments in the resulting road detections are sometimes due to sand burial. The results also show that, in most cases, the Sentinel-1 vertical transmit-vertical receive (VV) backscatter averages alone constitute the best input to the U-Net model. The detection and monitoring of roads in desert areas are key concerns, particularly given a growing population increasingly on the move.
英文关键词	synthetic aperture radar SAR Sentinel-1 Open Street Map deep learning U-Net desert road infrastructure mapping monitoring
类型	Article
语种	英语
开放获取类型	Green Submitted, gold
收录类别	SCI-E
WOS记录号	WOS:000554145900001
WOS关键词	SAND DUNES ; EXTRACTION ; INFORMATION
WOS类目	Environmental Sciences ; Geosciences, Multidisciplinary ; Remote Sensing ; Imaging Science & Photographic Technology
WOS研究方向	Environmental Sciences & Ecology ; Geology ; Remote Sensing ; Imaging Science & Photographic Technology
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/325311
作者单位	[Stewart, Christopher] European Space Agcy ESA, Earth Observat Programmes, Future Syst Dept, I-00044 Frascati, Italy; [Lazzarini, Michele; Luna, Adrian; Albani, Sergio] European Union Satellite Ctr SatCen, Madrid 28850, Spain
推荐引用方式 GB/T 7714	Stewart, Christopher,Lazzarini, Michele,Luna, Adrian,et al. Deep Learning with Open Data for Desert Road Mapping[J],2020,12(14).
APA	Stewart, Christopher,Lazzarini, Michele,Luna, Adrian,&Albani, Sergio.(2020).Deep Learning with Open Data for Desert Road Mapping.REMOTE SENSING,12(14).
MLA	Stewart, Christopher,et al."Deep Learning with Open Data for Desert Road Mapping".REMOTE SENSING 12.14(2020).