Human Behaviour Recognition based on Trajectory Analysis using Neural Networks
Please use this identifier to cite or link to this item:
|Title:||Human Behaviour Recognition based on Trajectory Analysis using Neural Networks|
|Authors:||Azorin-Lopez, Jorge | Saval-Calvo, Marcelo | Fuster-Guilló, Andrés | Garcia-Rodriguez, Jose|
|Research Group/s:||Informática Industrial y Redes de Computadores|
|Center, Department or Service:||Universidad de Alicante. Departamento de Tecnología Informática y Computación|
|Keywords:||Human behaviour analysis | Activity description vector|
|Knowledge Area:||Arquitectura y Tecnología de Computadores|
|Citation:||The 2013 International Joint Conference on Neural Networks (IJCNN), 4-9 Aug. 2013, Dallas, TX. IEEE, pp. 1-7|
|Abstract:||Automated human behaviour analysis has been, and still remains, a challenging problem. It has been dealt from different points of views: from primitive actions to human interaction recognition. This paper is focused on trajectory analysis which allows a simple high level understanding of complex human behaviour. It is proposed a novel representation method of trajectory data, called Activity Description Vector (ADV) based on the number of occurrences of a person is in a specific point of the scenario and the local movements that perform in it. The ADV is calculated for each cell of the scenario in which it is spatially sampled obtaining a cue for different clustering methods. The ADV representation has been tested as the input of several classic classifiers and compared to other approaches using CAVIAR dataset sequences obtaining great accuracy in the recognition of the behaviour of people in a Shopping Centre.|
|Sponsor:||This work was supported in part by the University of Alicante under Grant GRE11-01.|
|Rights:||© 2013 IEEE|
|Appears in Collections:||INV - I2RC - Comunicaciones a Congresos, Conferencias, etc.|
INV - AIA - Comunicaciones a Congresos, Conferencias, etc.
Files in This Item:
Items in RUA are protected by copyright, with all rights reserved, unless otherwise indicated.