Open Access
Mining spatial data from gps traces for automatic road network extraction
F. Lima,Michel Ferreira +1 more
TLDR
This paper has resorted to the widely available GPS/GPRS tracking technology, heavily used by trucking companies, in order to obtain more than 30 million GPS points to construct the road map of an interesting city of Portugal, called Arganil, in an accurate, inexpensive and permanently up-to-date manner.Abstract:
The car manufacturing industry has been conducting a considerable effort to allow future vehicles to communicate, either between them or with a road infrastructure, in order to improve driving safety. As the position of each vehicle is an essential attribute of the proposed application protocols (to avoid collisions at blind intersections, for instance), and is also fundamental to support complex network protocols based on mobile wireless nodes with very limited transmission range, such communicating vehicles will be further equipped with GPS receivers. This massive distribution of GPS sensors, in conjunction with a free of charge communication infrastructure that allows accessing the information collected by such devices, will create a powerful new medium of remote sensing of geographical information. In this paper we address the automatic road network extraction based on this vehicular sensing infrastructure where the sensor in play is just the GPS receiver. We have resorted to the widely available GPS/GPRS tracking technology, heavily used by trucking companies, in order to obtain more than 30 million GPS points to construct the road map of an interesting city of Portugal, called Arganil, in an accurate, inexpensive and permanently up-to-date manner. Our algorithm is implemented using spatial SQL queries to aggregate data from multiple traces to produce a weighted-mean geometry of road axles, diluting GPS errors. In order to evaluate our extracted road network, we have compared its geometric and topological layers with a vectorial road map extracted from high resolution satellite images. Results show a highly accurate correspondence between them in all areas where a sufficient number of GPS traces have been collected.read more
Citations
More filters
Book ChapterDOI
Vehicular Sensing: Emergence of a Massive Urban Scanner
Michel Ferreira,Ricardo J. Fernandes,Hugo Conceição,Pedro Gomes,Pedro M. d'Orey,Luis Moreira-Matias,João Gama,Fernanda Lima,Luís Damas +8 more
TL;DR: This paper discusses several applications that rely on vehicular sensing, using sensors such as the GPS receiver, windshield cameras, or specific sensors in special vehicles, such as a taximeter in taxi cabs, and discusses connectivity issues related to the mobility and limited wireless range of an infrastructure-less network based only onVehicular nodes.
Journal ArticleDOI
A new iterative algorithm for creating a mean 3D axis of a road from a set of GNSS traces
TL;DR: This work aims to improve the accuracy computing a sort of mean of all the traces by using two different methods (discrete Frechet distance is implemented starting with both the nearest and the farthest neighbors), and a comparative between them is analyzed by using a B-Spline fitting procedure.
Proceedings ArticleDOI
On automatic extraction of on-street parking spaces using park-out events data
TL;DR: In this paper, two different approaches were proposed to automatically create a map for valid on-street car parking spaces using car sharing park-out events data: spatial aggregation and a machine learning algorithm.
Journal ArticleDOI
Minimizing B‐spline knots in representative road axis from GPS points cloud
TL;DR: This paper exposes the previous solutions for estimating a representative axis and proposes a novel B‐spline least square method governed by a genetic algorithm that minimizes the number of knots necessary to define the B‐ Spline representative axis while keeping the axis' original shape.
Book ChapterDOI
On the Use of Data Mining Techniques in Vehicular Ad Hoc Network
TL;DR: This paper surveys some of VANET applications that used data mining techniques, and finds that position based routing protocols are becoming trendy due to development and accessibility of GPS devices.
References
More filters
Journal ArticleDOI
Algorithms for the reduction of the number of points required to represent a digitized line or its caricature
TL;DR: In this paper, two algorithms to reduce the number of points required to represent the line and, if desired, produce caricatures are presented and compared with the most promising methods so far suggested.
Journal ArticleDOI
Mining GPS Traces for Map Refinement
TL;DR: An approach to induce high-precision maps from traces of vehicles equipped with differential GPS receivers is presented, with new contributions are a spatial clustering algorithm for inferring the connectivity structure, more powerful lane finding algorithms that are able to handle lane splits and merges, and an approach to inferring detailed intersection models.
Journal ArticleDOI
Scalable, Distributed, Real-Time Map Generation
TL;DR: An algorithm for keeping digital maps up-to-date is developed, using ordinary vehicles making normal journeys rather than fleets of dedicated probe vehicles, however, further development is required to address several remaining challenges.
Proceedings ArticleDOI
Incremental map generation with GPS traces
TL;DR: This paper provides a generic approach for map generation based on Global Positioning System (GPS) traces especially for unknown terrains, using AI algorithms to infer the road geometry and clustering algorithms to construct a graph.
Proceedings ArticleDOI
Mining GPS data to augment road models
TL;DR: A data-mining approach to map refinement, using position traces that come from Global Positioning System receivers with differential corrections, which enables cheap, automated methods of inducing lane models and potentially impacts any geographic information system with a need to relate to actual behavior.