Résumé : |
(auteur) Nowadays, needs for very up to date referential spatial data increase significantly. Thus, a continuous update of authoritative spatial databases becomes highly demanding task in both aspects, technical and financial. In the same time, alternative sources of spatial data, such as Volunteered Geographical Information – VGI (Goodchild, 2007) seems to be suitable solution. This data is easy available and is being collected in almost every moment somewhere in the world. The main objective of our research is proposing a method for identifying potential updates in authoritative spatial databases using VGI data, more precisely GPS tracks. We identified walkway and tractor as very challenging types of roads for continuous update due to their intermittent nature (e.g. they appear and disappear very often) and various landscape (e.g. forest, high mountains, seashore, etc.). Even though, these types of roads are not of the highest priority for a national mapping agency, they are still very important for production of touristic maps and for other different applications such as defense, sport activities, etc. That is why we have focused on GPS traces obtained in sport activities. To detect potential update, links between similar features need to be defined. This step consists in applying a data matching algorithm in order to match VGI and authoritative data. Then, the question of VGI tracks quality arises. Furthermore, VGI traces are collected without any specified procedures, less or inexistent metadata, usually by low class GPS devices. Hence, heterogeneity of data is very high as well as spatial inaccuracy. In this work we focus on examination of data quality, especially on its spatial and temporal aspects. First, we present an overview of VGI data sources (websites) and the heterogeneities that characterize them. In terms of data, we can rely on spatiotemporal data (i.e. coordinates and sometimes elevation and timestamps) as well as on a variety of descriptive information in text format such as: type of activity, difficulty, trace description etc. Second, providing a comprehensive analysis of elements which affect GPS data quality is necessary. Sources of errors related to technical aspect of GPS data collection are partially important for our work. Since we use data obtained by low class GPS receivers, which positional accuracy is at meter level, we are not concerned about the sources that affect the accuracy at sub-meter level. Therefore, our attention is directed to identifying and classifying sources of errors according to which extent they affect positional accuracy of GPS tracks. Finally, we are interested in evaluation of data quality by analyzing VGI data itself, without comparing it to referential data. Thus, we tend to obtain the more statistical indicators of data quality that we can, such as indicators of: spatial dispersion, precision, reliability, correlation between data etc. As a result, a process of automatic collection of GPS traces from web-sites and storing them into PostgreSQL database was created. Evaluation of data quality is conducted by using an open source platform GeOxygene, developed by COGIT laboratory. |