Skip to Main content Skip to Navigation
Master thesis

Génération des événements primitifs dans une plateforme de reconnaissance d'activités.

Narjes Ghrairi 1
1 STARS - Spatio-Temporal Activity Recognition Systems
CRISAM - Inria Sophia Antipolis - Méditerranée
Abstract : Detection and activity-analysis systems have become important in various applications such as public or private monitoring space as well as intelligent technologies of maintenance and monitoring of people, mainly used in the field of health care. These systems are based on tools for computer vision technologies and integrate the intelligent use of environmental sensors. This type of systems is based on a synchronous model. The used data come from the cognitive vision platform SUP, developed in Stars team, and other environmental sensors. These signals come in an asynchronous mode, each has its own clock, and thus interfacing these entries with a synchronous module raises theoretical and technical problems. So, the objective of this study is to design a machine that could calculate the synchronous instants of asynchronous events. The machine's tests executed on real examples developed at the University Hospital (CHU) of Nice have led to positive results, as the machine has been able to calculate the right logic moment necessary for the synchronous engines of activity recognition.
Document type :
Master thesis
Complete list of metadata

Cited literature [25 references]  Display  Hide  Download

https://hal.inria.fr/hal-00871836
Contributor : Annie Ressouche <>
Submitted on : Thursday, October 10, 2013 - 4:50:22 PM
Last modification on : Friday, October 23, 2020 - 4:36:43 PM
Long-term archiving on: : Saturday, January 11, 2014 - 4:21:23 AM

File

memoire_ghrairi_2013.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00871836, version 1

Collections

Citation

Narjes Ghrairi. Génération des événements primitifs dans une plateforme de reconnaissance d'activités.. Informatique et langage [cs.CL]. 2013. ⟨hal-00871836⟩

Share

Metrics

Record views

338

Files downloads

1104