Fire flame detection using color segmentation and space-time analysis

Miti Ruchanurucks; Praphin Saengngoen; Theeraphat Sajjawiso

doi:10.1117/12.913421

30 September 2011 Fire flame detection using color segmentation and space-time analysis

Miti Ruchanurucks, Praphin Saengngoen, Theeraphat Sajjawiso

Proceedings Volume 8285, International Conference on Graphic and Image Processing (ICGIP 2011); 82851J (2011) https://doi.org/10.1117/12.913421
Event: 2011 International Conference on Graphic and Image Processing, 2011, Cairo, Egypt

Abstract

This paper presents a fire flame detection using CCTV cameras based on image processing. The scheme relies on color segmentation and space-time analysis. The segmentation is performed to extract fire-like-color regions in an image. Many methods are benchmarked against each other to find the best for practical CCTV camera. After that, the space-time analysis is used to recognized fire behavior. A space-time window is generated from contour of the threshold image. Feature extraction is done in Fourier domain of the window. Neural network is used for behavior recognition. The system will be shown to be practical and robust.

Citation Download Citation

Miti Ruchanurucks, Praphin Saengngoen, and Theeraphat Sajjawiso "Fire flame detection using color segmentation and space-time analysis", Proc. SPIE 8285, International Conference on Graphic and Image Processing (ICGIP 2011), 82851J (30 September 2011); https://doi.org/10.1117/12.913421

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available