Fire Detection Algorithm using Image Processing Techniques

Poobalan, Kumarguru and Liew, Siau-Chuin (2015) Fire Detection Algorithm using Image Processing Techniques. In: E-Proceeding of the 3rd International Conference on Artificial Intelligence and Computer Science (AICS2015) , 12-13 October 2015 , BayView Hotel, Penang, Malaysia. pp. 160-168.. ISBN 978-967-0792-06-4 (Online)

	PDF A058 FIRE DETECTION ALGORITHM USING IMAGE PROCESSING TECHNIQUES - KUMARGURU.pdf Restricted to Repository staff only Download (640kB) | Request a copy
Preview	PDF fskkp-2015-liew-fire detection algorithm using image1.pdf Download (497kB) | Preview

Abstract

Lately fire outbreak is common issue happening in Malays and the damage caused by these type of incidents is tremendous toward nature and human interest. Due to this the need for application for fire detection has increases in recent years. In this paper we proposed a fire detection algorithm based on image processing techniques which is compatible in surveillance devices like CCTV, wireless camera to UAVs. The algorithm uses RGB colour model to detect the colour of the fire which is mainly comprehended by the intensity of the component R which is red colour. The growth of fire is detected using sobel edge detection. Finally a colour based segmentation technique was applied based on the results from the first technique and second technique to identify the region of interest (ROI) of the fire. After analysing 50 different fire scenarios images, the final accuracy obtained from testing the algorithm was 93.61% and the efficiency was 80.64%.

Item Type:	Conference or Workshop Item (Lecture)
Uncontrolled Keywords:	Fire Detection, Image Processing, Signal Processing
Subjects:	Q Science > Q Science (General) Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Faculty/Division:	Faculty of Computer System And Software Engineering
Depositing User:	Dr. Liew Siau Chuin
Date Deposited:	19 Jul 2016 06:39
Last Modified:	27 Mar 2017 02:35
URI:	http://umpir.ump.edu.my/id/eprint/13721
Download Statistic:	View Download Statistics

Actions (login required)

View Item