Please use this identifier to cite or link to this item:
https://dspace.univ-ouargla.dz/jspui/handle/123456789/30829
Title: | Détection D'incendie Et De Fumée A L'aide De L'apprentissage Par Transfert (Fire and Smoke Detection Using Transfer Learning |
Authors: | LATI, Abdelhai BEKKARI, Lakhdar KADI, Nadhir |
Keywords: | Fire and Smoke Detection Transfer Learning Lightweight Networks Computer Vision |
Issue Date: | 2022 |
Publisher: | UNIVERSITY OF KASDI MERBAH OUARGLA |
Abstract: | The past decade has seen tremendous growth in the fields of artificial intelligence and computer vision. Recent advancements in several technologies have enabled the growth and development of intelligent surveillance systems through the development of advanced computing and data transmission over the Internet. A fire and smoke detection system requires accurate, fast and real-time response mechanisms to make the right decision and immediately notify the corresponding personnel. Common fire detection systems cannot be used outdoors and do not guarantee the necessary availability for real-time detection. The objective of this project is to use a Deep Neural Network to detect fire and smoke in outdoor environments using an embedded system with a camera. Recently, after significant progress in programming structures and, above all, in the field of machine learning, embedded systems are now able to perform real-time edge computing. This project proposes an approach to perform computer vision fire and smoke detection using advanced computing. Once the fire or smoke appears in any camera, the system can detect and immediately send an alert to the corresponding supervisor |
Description: | Électronique Des Systèmes Embarqués |
URI: | https://dspace.univ-ouargla.dz/jspui/handle/123456789/30829 |
Appears in Collections: | Département d'Electronique et des Télécommunications - Master |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
BEKKARI Lakhdar.pdf | Électronique Des Systèmes Embarqués | 4,05 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.