Designing a Volunteered Geographic Information System for Road Data Validation

Abstract

The objective of this work is to build a Volunteered Geographic Information System (VGIS) using a methodological design process. The VGIS design focuses on coordinating its three main components-project (organization), participants (community), and technological infrastructure-by aligning the project goal, crowdsourcing strategy and participation environment, the drivers and mechanisms that motivates volunteers, and the technological and data management tools that facilitate engaged participation. Following this process helped to design a solution based on the project's information requirements to handle a road data tagging task, while offering an experience that meets the interests and needs of potential participants.

A Framework Based on Nesting of Convolutional Neural Networks to Classify Secondary Roads in High Resolution Aerial Orthoimages

“…The data needed for the supervised learning process were obtained by labelling these orthoimages divided in tiles using a cartographic viewer based on Web Map Service (WMS) [27]. The task involved performing a visual comparison of the most recent orthoimages available with the existing cartographic support.…”

Proceedings - 1st Congress in Geomatics Engineering - CIGeo

“…Las tareas de baja demanda cognitiva involucran el señalar hechos, seguir procedimientos conocidos y resolver problemas rutinarios, no requieren un gran esfuerzo intelectual y se centran principalmente en proporcionar respuestas concretas y usar conocimientos previos sin necesidad de establecer o realizar nuevas conexiones (Van De Walle et al 2012). Por el contrario, las tareas de demanda cognitiva alta involucran el establecimiento de Gómez-Barrón, Manso-Callejo, Alcarria, 2017. This work is licensed under a Creative Commons 4.0 International License (CC BY-NC-ND 4.0) EDITORIAL UNIVERSITAT POLITÈCNICA DE VALÈNCIA conexiones, analizar la información y sacar conclusiones (Smith and Stein 1998). Por otro lado, siguiendo a Erickson et al (2012), podemos clasificar las habilidades necesarias para completar una tarea de crowdsourcing como: habilidades comunes o generales, requeridas en tareas sencillas y rutinarias; habilidades especializadas o avanzadas; y habilidades específicamente relacionadas a un dominio científico o tecnológico particular.…”

A Deep Learning-Based Solution for Large-Scale Extraction of the Secondary Road Network from High-Resolution Aerial Orthoimagery

“…To obtain the training set, an operator performed a visual comparison between the most recent orthoimages available and the existing cartographic support in vector format in different representative areas of the Spanish territory (Andalucía, Castilla y León, Castilla-La Mancha, Galicia, Islas Baleares, Murcia and Navarra) and manually tagged the tiles using a WMS (Web Map Service) viewer built for this purpose (described in [41]). We collected our training data as sets of aerial orthoimagery clipped into fixed tiles and their correspondent segmentation mask measuring 256 by 256 pixels (0.07 Megapixels) stored in the lossless png format (examples can be seen in Figure 1).…”