This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.
Umesh Bhamare,
Smita Badarkhe,
Parth Rathi,
Rishikesh Pandey,
- Student, Department of Electronics & Telecommunication Engineering , SKN College of Engineering, Savitribai Phule Pune University, (SPPU), Pune,, Maharashtra, India
- Student, Department of Electronics & Telecommunication Engineering , SKN College of Engineering, Savitribai Phule Pune University, (SPPU), Pune,, Maharashtra, India
- Student, Department of Electronics & Telecommunication Engineering , SKN College of Engineering, Savitribai Phule Pune University, (SPPU), Pune,, Maharashtra, India
- Student, Department of Electronics & Telecommunication Engineering , SKN College of Engineering, Savitribai Phule Pune University, (SPPU), Pune,, Maharashtra, India
Abstract document.addEventListener(‘DOMContentLoaded’,function(){frmFrontForm.scrollToID(‘frm_container_abs_128197’);});Edit Abstract & Keyword
AI-based fire detection system leverages deep learning and Open CV. Issues with conventional fire detection techniques include false alarms and expense. The proposed system uses deep learning for real-time fire detection in videos, enhancing accuracy and adaptability. OpenCV aids in crowd counting, improving situational awareness during emergencies. This innovation promises to revolutionize fire safety by offering timely and precise detection, potentially saving lives and property. Additionally, by counting crowds, the method increases emergency safety awareness. It helps safeguard individuals and property by sending out prompt and precise alerts. It expedites reactions and lowers false alarms in comparison to older systems. Deep learning is used to improve accuracy and flexibility in various contexts by enabling the system to identify fires in real-time through video data. Moreover, OpenCV is employed for population counting, which improves situational awareness in emergency situations. This AI technology can be applied in industries, homes, and workplaces to improve and automate fire safety. AI-based fire alert system demonstrates significant improvements over traditional methods by reducing response times, minimizing false alarms, and enhancing overall safety. Its adaptability and scalability make it suitable for various environments, including residential buildings, commercial complexes and industrial facilities.
Keywords: Fire Detection, Deep Learning, Open CV, Real-time Detection, Crowd Counting
[This article belongs to International Journal of Optical Innovations & Research (ijoir)]
Umesh Bhamare, Smita Badarkhe, Parth Rathi, Rishikesh Pandey. AI-Powered Fire Detection System for Accurate and Timely Emergency Response. International Journal of Optical Innovations & Research. 2024; 02(02):-.
Umesh Bhamare, Smita Badarkhe, Parth Rathi, Rishikesh Pandey. AI-Powered Fire Detection System for Accurate and Timely Emergency Response. International Journal of Optical Innovations & Research. 2024; 02(02):-. Available from: https://journals.stmjournals.com/ijoir/article=2024/view=0
References
document.addEventListener(‘DOMContentLoaded’,function(){frmFrontForm.scrollToID(‘frm_container_ref_128197’);});Edit
[1] Birajdar GS, Baz M, Singh R, Rashid M, Gehlot A, Akram SV, Alshamrani SS, AlGhamdi AS. Realization of people density and smoke flow in buildings during fire accidents using raspberry and openCV. Sustainability. 2021 Oct 7;13(19):11082.
[2] Sathyakala G, Kirthika V, Aishwarya B. Computer vision-based fire detection with a video alert system. In2018 International Conference on Communication and Signal Processing (ICCSP) 2018 Apr 3 (pp. 0725-0727). IEEE.
[3] O Obulesu, A. Hanshika, A. Lahari, P. Arunodaya, R. Ashwini. People Counting and Tracking System in Real-Time Using Deep Learning Techniques, Journal for Research in Applied Science and Engineering Technology, ISSN : 2321-9653, https://doi.org/10.22214/ijraset.2023.54182
[4] Liu W, Salzmann M, Fua P. Context-aware crowd counting. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition 2019 (pp. 5099-5108).
[5] Sindagi VA, Patel VM. Ha-ccn: Hierarchical attention-based crowd counting network. IEEE Transactions on Image Processing. 2019 Jul 19;29:323-35.
[6] Shen Z, Xu Y, Ni B, Wang M, Hu J, Yang X. Crowd counting via adversarial cross-scale consistency pursuit. InProceedings of the IEEE conference on computer vision and pattern recognition 2018 (pp. 5245-5254).
[7] Zhao T, Nevatia R, Wu B. Segmentation and tracking of multiple humans in crowded environments. IEEE transactions on pattern analysis and machine intelligence. 2008 Jun 6;30(7):1198-211.
[8] Cheng G, Chen X, Wang C, Li X, Xian B, Yu H. Visual fire detection using deep learning: A survey. Neurocomputing. 2024 May 31:127975.
[9] Debnath S, Gautam J, Rai SK. IoT Based Smart Home and Office Fire Notification Alert System. In2024 IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI) 2024 Mar 14 (Vol. 2, pp. 1-5). IEEE.
[10] Razmi SM, Saad N, Asirvadam VS. Vision-based flame detection: motion detection & fire analysis. In2010 IEEE Student Conference on Research and Development (SCOReD) 2010 Dec 13 (pp. 187-191). IEEE.
[11] Ligang M, Yanjun C, Aizhong W. Flame region detection using color and motion features in video sequences. InThe 26th Chinese Control and Decision Conference (2014 CCDC) 2014 May 31 (pp. 3005-3009). IEEE.
[12] Toulouse T, Rossi L, Celik T, Akhloufi M. Automatic fire pixel detection using image processing: a comparative analysis of rule-based and machine learning-based methods. Signal, Image and Video Processing. 2016 Apr;10:647-54.
[13] Na YM, Hyun DH, Park DH, Hwang SH, Lee SH. AI Fire Detection & Notification System. Journal of the Korea Society of Computer and Information. 2020;25(12):63-71.
| Volume | 02 |
| Issue | 02 |
| Received | 10/08/2024 |
| Accepted | 18/08/2024 |
| Published | 17/09/2024 |