ResearchBib Share Your Research, Maximize Your Social Impacts
Sign for Notice Everyday Sign up >> Login

A Real Time Image Processing Based Fire Safety Intensive Automatic Assistance System using Raspberry Pi

Journal: International Journal for Modern Trends in Science and Technology (IJMTST) (Vol.2, No. 6)

Publication Date:

Authors : ; ;

Page : 34-38

Keywords : Volume: 2 | Issue: 06 | June 2016 | ISSN: 2455-3778;

Source : Downloadexternal Find it from : Google Scholarexternal

Abstract

Fire usually cause serious disasters. Thus, fire detection has been an important issue to protect human life and property. In this project, I propose a fast and practical real-time image-based fire flame detection method based on colour pair analysis and intensity level algorithm. Then, based on the above fire flame colour features model, regions with fire-like colours are roughly separated from each frame of the test videos. Besides segmenting fire flame regions, background objects with similar fire colours or caused by colour shift resulted from the reflection of fire flames are also extracted from the image during the above colour separation process. To remove these spurious fire-like regions, the image difference method and the invented colour masking technique are applied. The device can detect fire by using Artificial Neural Network (ANN). Finally device automatically control the fire safety assistance. This method was tested with Raspberry pi B+ Board interface with camera module.

Last modified: 2016-06-14 20:11:43