Home // GEOProcessing 2016, The Eighth International Conference on Advanced Geographic Information Systems, Applications, and Services // View article
Authors:
Alexandre Altair de Melo
Glaucio Scheibel
Fabiano Baldo
Fernando José Braz
Keywords: Moving Objects; Trajectory; Similarity; Correlation Statistics.
Abstract:
In recent years, mobile electronic devices, specially smartphones, are gaining more attention in people's daily life. These devices provide many features that often process information gathered by one of their several built-in sensors. Among them, one of the most popular is the Global Positioning System (GPS) receiver. This sensor allows the systematic and chronological collection of location information that represents the trajectory of the moving object that carries it. Trajectories are considered valuable sources of information for analysing and understanding of moving objects' behavior. There is a considerable number of researches that analyse objects' trajectories. Among them, the identification of trajectories' similarity is one where researches are currently being developed. The similarity of trajectories may indicate common behaviors inside groups of individuals that can be useful in various application areas. However, how to measure the trajectories' similarity even though they are in different directions and far from each other? Trying to solve this problem, this paper proposes a method to calculate similarity among trajectories applying statistical correlation over their vectors of angular deflections. Preliminary results indicate that the method can identify similarity in shape among trajectories. However, when their shapes are too complex, it can not reach suitable results.
Pages: 63 to 68
Copyright: Copyright (c) IARIA, 2016
Publication date: April 24, 2016
Published in: conference
ISSN: 2308-393X
ISBN: 978-1-61208-469-5
Location: Venice, Italy
Dates: from April 24, 2016 to April 28, 2016