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 Voluntee...

For the most part, we find our way around the planet by tapping memory, perhaps by recalling past routes, or sometimes by accessing stored mental images that approximate maps. In other cases, however, we must rely on information collected and made available to us by others. People visiting strange cities need street maps to help them find their way around; planners need maps of wetlands and oth...

Flood forecasting is particularly difficult and uncertain for small drainage basins. One reason for that is the absence of adequate temporal and spatial hydrological input variables for model-based flood predictions. Incorporating additional information collected by volunteers with the help of their smartphones can improve flood forecasting systems. Data collected in this way is often referred ...

This paper describes an object-oriented software library called the Virtual Geometry Interface (VGI). The VGI is designed as a general, geometry representation-independent interface to geometric modeling, but is implemented speciically for mesh generation and computational mechanics. The design provides for multiple simultaneous geometric representations in a model. The design of the VGI eases ...

Volunteered Geographic Information (VGI) projects such as OpenStreetMap (OSM) have been growing in users and edits in the past few years, resulting in more accurate, complete and up-to-date datasets. As a result, governments are now interested in VGI as a source of information that could help to improve their own datasets. Integrating geographic information requires solving semantic heterogenei...

Over the last few years, much online volunteered geographic information (VGI) has emerged and has been increasingly analyzed to understand places and cities, as well as human mobility and activity. However, there are concerns about the quality and usability of such VGI. In this study, we demonstrate a complete process that comprises the collection, unification, classification and validation of ...

At the University of Minnesota, we are exploring VGI in the context of an online bike map: a geowiki for bicyclists [5]. We are building a system to enable cyclists to collaboratively build a database of geographic information relevant to them, including a fully editable map. This VGI will then be used as input for personalized route finding. In order to build a successful repository of volunte...

This paper demonstrates the use of fuzzy clustering to characterize Volunteered Geographic Information (VGI). We argue that classifying small areas based on variables related to the amount, type, and currency of VGI can provide a more nuanced understanding of the content. We present a classification of 2011 UK Census Output Areas in Leicestershire (UK) based on content of OpenStreetMap, using a...

The article explores the process of Volunteered Geographic Information (VGI) collection by assessing the relative usability and accuracy of a range of different methods (smartphone GPS, tablet, and analogue maps) for data collection among different demographic and educational groups, and in different geographical contexts within a study area. Assessments are made of positional accuracy, complet...