Affiliation:
1. Wojskowa Akademia Techniczna
Abstract
Video-based fire detection systems represent an innovative path in fire signalling. Thanks to a suitably designed algorithm, a system of this kind can enable the detection of a flame based on its characteristics such as colour or shape, which were not previously used in classical fire detection systems. Video-based detection systems, due to their early stage of development in the fire protection market, are not yet a certified, fully tested method for early fire detection. This paper focuses on the analysis of possible causes of false alarms occurring in video-based fire detection systems in relation to classical Fire Alarm Systems (FAS). For this purpose, a video-based flame detection algorithm is designed and implemented to further analyse the phenomena occurring in such systems.
Subject
Safety, Risk, Reliability and Quality
Reference14 articles.
1. X. Zhang, K. Qian, K. Jing, J. Yang, H. Yu, “Fire Detection based on Convolutional Neural Networks with Channel Attention”, Chinese Automation Congress, China 2020.
2. T. E. Abidha, P. Mathai Paul, “Reducing False Alarms in Vision Based Fire Detection with NB Classifier in EADF Framework”, Federal Institute of Science and Technology, Angamaly 2020.
3. A. Khalil, S.U. Rahman, F. Alam, I. Khalil, “Fire Detection Using Multi Color Space and Background Modeling”, University of Malakand, Pakistan 2020.
4. P. Karasev, I. Kolesov, A. Tannenbaum, “Optical Flow Estimation for Flame Detection in Videos”, IEEE Transactions on Image Processing, 2013.
5. Y. Lee, J. Shim, “False Positive Decremented Research for Fire and Smoke Detection in Surveillance Camera using Spatial and Temporal Features Based on Deep Learning”, Andong National University, Andong 2019.