[ Approche spatio-temporelle d’extraction de connaissances pour l’analyse du comportement humain à partir de séquences vidéo ]
Volume 39, Issue 1, March 2023, Pages 271–279
Mikaël A. Mousse1
1 Institut Universitaire de Technologie, Université de Parakou, Parakou, Benin
Original language: French
Copyright © 2023 ISSR Journals. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
The analysis and exploration of traces of mobility produced by various mobile objects is a research topic that has attracted great interest in recent years. In this article, we present a classification (or clustering) approach adapted to the data of people moving under the constraints of a road network. A similarity measure is proposed to compare the trajectories studied with each other, taking into account the displacement constraints imposed by the network. This measurement is exploited to build a graph translating the different similarity relations maintained by the trajectories between them. We partition this graph using an algorithm using the notion of modularity as a quality criterion in order to discover communities (or clusters) of trajectories which are strongly linked and which exhibit a common behavior. We have implemented and tested the proposed approach on several synthetic datasets through which we show its operation.
Author Keywords: knowledge extraction, point of interest, optical flow, decision tree, classification.
Volume 39, Issue 1, March 2023, Pages 271–279
Mikaël A. Mousse1
1 Institut Universitaire de Technologie, Université de Parakou, Parakou, Benin
Original language: French
Copyright © 2023 ISSR Journals. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Abstract
The analysis and exploration of traces of mobility produced by various mobile objects is a research topic that has attracted great interest in recent years. In this article, we present a classification (or clustering) approach adapted to the data of people moving under the constraints of a road network. A similarity measure is proposed to compare the trajectories studied with each other, taking into account the displacement constraints imposed by the network. This measurement is exploited to build a graph translating the different similarity relations maintained by the trajectories between them. We partition this graph using an algorithm using the notion of modularity as a quality criterion in order to discover communities (or clusters) of trajectories which are strongly linked and which exhibit a common behavior. We have implemented and tested the proposed approach on several synthetic datasets through which we show its operation.
Author Keywords: knowledge extraction, point of interest, optical flow, decision tree, classification.
Abstract: (french)
L’analyse et la fouille des traces de mobilité produites par divers objets mobiles est un sujet de recherche qui sollicite un grand intérêt depuis quelques années. Dans le présent article, nous présentons une approche de classification (ou clustering) adaptée aux données de personnes se déplaçant sous contraintes d’un réseau routier. Une mesure de similarité est proposée pour comparer les trajectoires étudiées entre elles en tenant compte des contraintes de déplacement imposées par le réseau. Cette mesure est exploitée pour construire un graphe traduisant les différentes relations de similarité entretenues par les trajectoires entre elles. Nous partitionnons ce graphe à l’aide d’un algorithme utilisant la notion de modularité comme critère de qualité afin de découvrir des communautés (ou clusters) de trajectoires qui sont fortement liées et qui présentent un comportement commun. Nous avons implémenté et testé l’approche proposée sur plusieurs jeux de données synthétiques à travers lesquels nous montrons son fonctionnement.
Author Keywords: extraction de connaissances, point d’intérêt, flux optique, arbre de décision, classification.
How to Cite this Article
Mikaël A. Mousse, “Spatio-temporal Approach for the Analysis of Human Behavior from Video Sequences,” International Journal of Innovation and Applied Studies, vol. 39, no. 1, pp. 271–279, March 2023.
