A New Approach to Vision-based Fire and its Intensity Computation Using SPATIO-Temporal Features

Abstract

Currently, fire detection systems based on computer vision techniques are highly appreciated for their intelligent detections at earliest. These systems use surveillance cameras to capture high-level information from a fire that enables a system to take preventive and corrective measures before the happening of a fire hazard. Handling false fire detection and reducing false alarm in such developed systems are still big challenges that need to be addressed. In this paper, a novel framework is proposed that uses angular and regional area information of the fire flame to predict the existence of a fire flame in sequence of a video frames. The proposed system especially handles false detection of fire object in video. The results achieved on different dataset of fire videos show that extracted features using the proposed framework efficiently distinguish fire and non-fire objects. These features are also useful to estimate the size and direction of a fire flame. The regional area information can be fed into a machine-learning algorithm to learn a model for a fire flame that can be used to predict about the existence of fire flame.

KEYWORDS:

• Background subtraction
• Blob technique
• Flame size detection
• Flame boundary
• Image segmentation
• Radial distance
• Unsupervised fire detection
• Video surveillance

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Notes on contributors

Mirza Adnan Baig

Mirza Adnan Baig is PhD research scholar at Department of Computer Science and Information Technology, NED University. He has been doing his research studies under the supervision of Dr Najeed Ahmed Khan and co-supervision of Dr Muhammad Masood Rafi. His research interest includes, fire detection, and its hazards prevention using image processing and computer vision.

Najeed Ahmed Khan

Najeed Ahmed Khan has done PhD in computer vision from the University of Leeds United Kingdom. His main interest in computer vision specific to application areas includes medical imaging. He is the author of around 30 plus publications in JCR and ISI indexed journals. Dr Khan has won HEC National Centre for Artificial Intelligence (NCAI) award for NED University as CO-PI. In addition he won multiple IGNITE (National Technology Fund) technology funds. Currently, he is serving at University as associate professor of artificial intelligence and as executive officer & caretaker MoST Chair Professor endowment. E-mail: [email protected]

Muhammad Masood Rafi

Masood Ahmed Rafi is the professor and chairman of the Department of Earthquake Engineering. He did his post-doctorate in seismic behaviour of earthen construction from the University of Aveiro. He did his PhD in structural behaviour in fire from the University of Ulster. He is the author of 80 plus publications. He is also a member of Board of Advance Studies and Research. E-mail: [email protected]