Finding the Signal from the Smoke
A Real-Time, Unattended Fire Prevention System Using 3D CNNs
DOI:
https://doi.org/10.47611/jsrhs.v11i3.2981Keywords:
artificial intelligence, CNN, 3D CNN, 3D Convolutional Neural Network, fire, fire prevention, signal, smokeAbstract
Cooking fires are dangerous. Every year, they are responsible for taking away more than 500 lives in the U.S. alone. Existing approaches using sensors usually require expensive retrofitting and are not feasible in real-life situations. This research presents Finding-Signals-from-Smoke (FiSS), a robust fire machine learning prediction model that aims to prevent cooking fires from starting using videos captured with a normal camera. FiSS is based on a 3-dimensional Convolutional Neural Network, which analyzes the video signals and models the complex relationships of the spatial-temporal features of smoke signals with fire ignition. It uses a segment-based video sampling and modeling framework that is able to generalize to a variety of kitchen/stove settings and achieve promising prediction performance. FiSS is trained and evaluated with video data from 30 full-scale kitchen fire experiments and can predict potential fire ignitions as early as 60 seconds before the moment of ignition. As a result, FiSS can be used in an early warning system to prevent fire ignitions and help to reduce casualties and injuries from cooking fires.
Downloads
References or Bibliography
Ahrens, M., 2020. Home Cooking Fires. National Fire Protection Association, Quincy, Massachusetts.
Hamins, A. , Madrzykowski, D. , Kim, S. and Kent, J. (2018), Investigation of Residential Cooking Fire Suppression Technologies, Technical Note (NIST TN), National Institute of Standards and Technology, Gaithersburg, MD, [online], https://doi.org/10.6028/NIST.TN.1969 (Accessed February 4, 2022)
Underwriters Laboratories, UL 858, Standard for Safety for Household Electric Ranges, 2014 Edition and 2017 Revision, Underwriters Laboratories, Northbrook, IL.
Kim, S. , Hamins, A. and Bundy, M. (2018), Investigation of Residential Cooktop Ignition Prevention Technologies, Technical Note (NIST TN), National Institute of Standards and Technology, Gaithersburg, MD, [online], https://doi.org/10.6028/NIST.TN.1986 (Accessed February 4, 2022)
USFA (U.S. Fire Administration), 2022. https://www.usfa.fema.gov/nfirs/
Mensch, A., Hamins, A., Lu, Z.Q., Kuperschmid, M., Tam, W.C. and You, C., 2019, September. Evaluating sensor algorithms to prevent kitchen cooktop ignition and ignore normal cooking. In Suppression, Detection and Signaling Research and Applications Conference.
Mensch, A.E., Hamins, A., Tam, W.C., Lu, Z.Q., Markell, K., You, C. and Kupferschmid, M., 2021. Sensors and machine learning models to prevent cooktop ignition and ignore normal cooking. Fire Technology, 57(6), pp.2981-3004.
Kamnitsas, K., Ledig, C., Newcombe, V.F.J., Simpson, J.P. et al., 2017. Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation. Medical image analysis, 36, pp.61-78.
Kingma, D.P., Ba, J., 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
Lin, G., Zhang, Y., Xu, G., Zhang, Q., 2019. Smoke Detection on Video Sequences Using 3D Convolutional Neural Networks. Fire Technology, 55(5), pp.1827-1847.
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., and Salakhutdinov, R.. 2014. Dropout: a simple way to prevent neural networks from overfitting. The Journal of Machine Learning Research, 15, 1 (January 2014), 1929–1958.
Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M., 2015. Learning spatiotemporal features with 3d convolutional networks. Proceedings of the IEEE international conference on computer vision, pp.4489-4497.
Wang, L., Xiong, Y., Wang, Z., Qiao, Y., Lin, D., Tang, X., Van Gool, L., 2018. Temporal segment networks for action recognition in videos. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 41, no. 11, pp. 2740-2755, 1 Nov. 2019, doi: 10.1109/TPAMI.2018.2868668.
Yuan, Y., Zhao, Y., Wang, Q., 2018. Action recognition using spatial-optical data organization and sequential learning framework. Neurocomputing, 315, pp.221-233.
Published
How to Cite
Issue
Section
Copyright (c) 2022 Michael Ngai, Eugene Fu, Andy Tam; Amber Yang, Grace Ngai
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Copyright holder(s) granted JSR a perpetual, non-exclusive license to distriute & display this article.
