Fire Detection Using Multi Color Space and Background Modeling

  • PDF / 1,546,801 Bytes
  • 19 Pages / 439.37 x 666.142 pts Page_size
  • 98 Downloads / 243 Views

DOWNLOAD

REPORT


Fire Detection Using Multi Color Space and Background Modeling *Adnan Khalil, Sami Ur Rahman, Fakhre Alam and Irshad Khalil, Department of Computer Science and Information Technology, University of Malakand, Chakdara, Pakistan Iftikhar Ahmad, Department of Computer Science and Information Technology, University of Engineering and Technology, Peshawar, Pakistan Received: 26 January 2020/Accepted: 8 August 2020

Abstract. Emergency incidents and events of fires can be dangerous and required quick and accurate decision-making need quick and correct decision-making. The use of computer vision for fire detection can provide a efficient solution to deal with these situations. These systems handle the usual data, provide an automated solution, and discard non-relevant information without discarding relevant content. Researchers developed many techniques for fire detection in videos and still images by using different color-based models. However, for videos, these methods are unsuitable because of high false-positive results. These methods use few parameters with little physical meaning, which makes fire detection more difficult. To deal with this, we have proposed a novel fire detection method based on Red Green Blue and CIE L  a  b color models, by combining motion detection with tracking fire objects. We have eliminated the moving region and calculate the growth rate of the fire to reduce false-alarm and calculate the risk. The proposed method operates on a reduced number of parameters compared to the existing methods. Experimental results demonstrate the effectiveness of our method of reducing false positives while keeping their precision compatible with the existing methods. Keywords: Fire detection, Fire growth, Static object tracking

1. Introduction In everyday life, various abnormal events (accidents, medical emergency, disaster, fire, and flood, etc.) occur which require early detection and effective strategies to combat. Early detection of such abnormal events can significantly decrease the chance of massive disasters [1]. Fire poses a constant threat to the ecosystem, human life, and infrastructure [2]. The recent past has witnessed multiple instances of fire causing the catastrophe and resulting in loss of precious human lives and property [3]. For example, in September 2015, three major fires ravaged the state of California at the same time. The valley fire burned over 73,000 acres in the counties of Lake and Napa, killing one person and devastating almost 600 homes [3]. A series of devastating bushfires have struck Australia’s southeastern state of * Correspondence should be addressed to: Adnan Khalil, E-mail: [email protected]

1

Fire Technology 2020 Victoria, wrecking several plots of land and forcing thousands of people to flee their homes [4]. Besides human lives and valuable properties, fire is also endangering biological communities in forests. Thus, concentrated and directed efforts are required for timely detection of fire to minimize its spread and save human lives, biological communities, and properties. The tradition