DeepVGI: Deep Learning with Volunteered Geographic Information
نویسندگان
چکیده
Recently, deep learning has been widely studied to recognize ground objects with satellite imageries. However, finding ground truths especially for developing and rural areas is quite hard and manually labeling a large set of training data is costly. In this work, we propose an ongoing research named DeepVGI which aims at deeply learning from satellite imageries with the supervision of Volunteered Geographic Information (VGI). VGI data from OpenStreetMap (OSM) and a crowdsourcing mobile application named MapSwipe which allows volunteers to label images with buildings or roads for humanitarian aids are utilized. Meanwhile, an active learning framework with deep neural networks is developed by incorporating both VGI data with more complete supervision knowledge. Our experiments show that DeepVGI can achieve high building detection performance for humanitarian mapping in rural African areas.
منابع مشابه
Validation of Volunteered Geographic Information Landuse Change Using Satellite Imagery
Land use change monitoring is one of the main concerns of managers and urban planners due to human activities and unbalanced physical development in urban areas. In this paper, a combination of remote sensing data and volunteered geographic information was used to assess the quality of volunteered geographic information on land use and land cover changes monitoring. For this purpose, the ORBVIE...
متن کاملExtraction of Pluvial Flood Relevant Volunteered Geographic Information (VGI) by Deep Learning from User Generated Texts and Photos
In recent years, pluvial floods caused by extreme rainfall events have occurred frequently. Especially in urban areas, they lead to serious damages and endanger the citizens’ safety. Therefore, real-time information about such events is desirable. With the increasing popularity of social media platforms, such as Twitter or Instagram, information provided by voluntary users becomes a valuable so...
متن کاملAssessment of the completeness of Volunteered Geographic Information focusing on building blocks data (Case Study: Tehran metropolis)
Open Street Map (OSM) is currently the largest collection of volunteered geographic data, widely used in many projects as an alternative to or integrated with authoritative data. However, the quality of these data has been one of the obstacles to the widely use of it. In this article, from among the elements related to the quality of volunteered geographic data, we have tried to examine the com...
متن کاملVolunteered Geographic Information and GIScience
What are the research questions posed by Volunteered Geographic Information (VGI)? Does Geographic Information Science (GIScience) appropriately address them or does it need to shift its attention? I discuss changes to current research agendas, propose an arising grand challenge, and outline some specific new research challenges for scientists working within and outside GIScience.
متن کاملDeep Excavation Hazard Assessment Zoning in District 1 in Shiraz Municipality Using Geographic Information System (GIS)
This research presents the geotechnical zoning map of district 1 in Shiraz municipality with focus on municipal deep excavation hazard assessment on data from 160 boreholes. For this purpose, the mechanical properties are determined according to the results of direct shear, uniaxial, and SPT tests and then excavation hazard assessment with depths of 3, 6 and 9 m, in situations where the excavat...
متن کامل