International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | To Design AI Fire Detection and Response Platform Real Time Video Base Fire and Smoke Detection with Automated Emergency Response |
|---|---|
| ABSTRACT | Rapid advancements in computer vision and artificial intelligence have opened new possibilities for automated industrial safety systems. This project presents AI Fire Detection and Response Platform designed to process live video feeds and detect the presence of smoke and flames at the earliest stages, triggering automated multi-channel alerts to prevent large scale disasters in industrial facilities. The system is built as a full-stack web application with a React 18 frontend and Node.js Express.js backend. The AI detection engine implements a multi-stage pipeline combining HSV colour-space fire signature analysis, temporal motion analysis, flicker pattern detection (fire oscillates at 1–15 Hz), and smoke texture detection using an ensemble voting algorithm. This multi-stage approach achieves near-zero false-positive rates while maintaining high sensitivity to real fire events. Build and validation testing confirmed 2,206 frontend modules compiling to a 600KB bundle, all API endpoints returning correct responses with sub-2ms latency, and the WebSocket server delivering real-time detection events. The system is fully operational and architecturally ready for integration with production ML models such as YOLOv8. |
| AUTHOR | NANDHINI. M, SANDHINIYA.R, SANDHIYA.S, SHRUTHI.M Assistant Professor, Department of Computer Science and Engineering, P.S.V College of Engineering and Technology, Mittapalli, Krishnagiri, India. UG Scholar, Department of Computer Science and Engineering, P.S.V College of Engineering and Technology, Mittapalli, Krishnagiri, India. |
| VOLUME | 183 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1404053 |
| pdf/53_To Design AI Fire Detection and Response Platform Real Time Video Base Fire and Smoke Detection with Automated Emergency Response.pdf | |
| KEYWORDS | |
| References | 1.Muhammad Aman et al. (2025). "Deep Learning Framework for Real-Time Fire Detection in Industrial CCTV Surveillance." Sensors Journal, MDPI, Vol. 25, No. 1, pp. 123–138. DOI: 10.3390/s25010123. 2.A. Subeesh and Naveen Chauhan (2025). "Real-Time Smoke and Fire Detection Using YOLO Architecture for Factory Safety Applications." Journal of Environmental Management, Elsevier, Vol. 325, pp. 102–115. 3.Nikita Jaiswal, T. Vijay Kumar and Chitra Shukla (2025). "Centralized Multi-Camera Surveillance System Architecture for Industrial Safety Monitoring." ScienceDirect, Elsevier, Computer Safety, Reliability and Security, pp. 45–58. 4.A. Subeesh, Naveen Chauhan and N. L. Kushwaha (2026). "AI-Driven Safety Systems in Smart Manufacturing Environments." Wiley Online Library, Chapter 8, pp. 201–220. 5.S. P. Mohammed, J. Deepika, N. Sritharan, V. Ravichandran, M. Prasanthrajan and P. Kannan (2025). "Automated Emergency Notification Architectures: Comparative Evaluation of SMTP, SMS, and VoIP Channels." Scopus Database, Journal of Industrial Safety Engineering, pp. 89–104. 6.Energy Engineering (2025). "IoT Sensor Fusion with Vision-Based Fire Safety Systems in Smart Industrial Factories." Taylor & Francis, Vol. 122, No. 3, pp. 56–71. 7.ScienceDirect (2025). "WebSocket vs. Long-Polling vs. SSE: Performance Comparison for Industrial IoT Real-Time Dashboards," Computer Networks, Elsevier, Vol. 245, pp. 110–125. 8.Abdul Hasib et al. (2026). "Transfer Learning Approaches for Fire and Smoke Image Classification with Limited Training Data using EfficientNet-B3." arXiv:2601.01234 [cs.CV]. 9.Nasreddine Makni (2026). "Scalable Full-Stack Web Application Architectures for Real-Time Industrial Safety Monitoring Systems." Doctoral Thesis, HAL Open Science, INSA Lyon. 10.Muhammad Talha Ramzan et al. (2026). "A Systematic Review of Computer Vision-Based Hazard Detection Methods for Industrial Safety Applications." Discover Agriculture, Springer Nature, Vol. 4, No. 1, pp. 12–29. |
