Authors : Sami Ud Din; Hashir Khan; Muhammad Kashif; Obaid Ullah

Volume/Issue : Volume 10 - 2025, Issue 9 - September

Google Scholar : https://tinyurl.com/mrxdjjfr

Scribd : https://tinyurl.com/2mukvwju

DOI : https://doi.org/10.38124/ijisrt/25sep947

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Note : Google Scholar may take 30 to 40 days to display the article.

Abstract : Fire detection is a critical task in safeguarding human life, property, and the environment, yet traditional methods often struggle with delayed responses and high false alarm rates. In this study, we propose a deep learning-based framework that leverages convolutional neural networks (CNNs) to automatically identify fire in digital images. The CNN is trained on a diverse dataset comprising both fire and non-fire scenes, enabling it to learn discriminative visual patterns such as color intensity, irregular flame contours, and dynamic texture characteristics. Unlike conventional rule-based or handcrafted feature approaches, our method allows the network to autonomously extract and optimize features, improving generalization across varied scenarios. The performance of the proposed system was rigorously evaluated on an independent test set, with results demonstrating strong classification accuracy, precision, and recall. These outcomes confirm the robustness of our approach in distinguishing fire from challenging non-fire instances, such as sunsets, artificial lighting, or objects with flame-like hues, thereby minimizing false positives. Due to its efficiency and adaptability, the proposed framework can be deployed in multiple real-world contexts. Potential applications include early fire warning systems in residential and industrial environments, intelligent surveillance for public safety, and large-scale monitoring of wildfire-prone regions. Overall, this work highlights the effectiveness of CNN-based methods for real-time fire detection and contributes to advancing intelligent safety and hazard management technologies.

Keywords : Fire Detection, Machine Learning, Neural network, CNN, Efficient System.

References :

1. Gaur, A. Singh, A. Kumar, K. S. Kulkarni, S. Lala, K. Kapoor, V. Srivastava, A. Kumar, and S. C. Mukhopadhyay, “Fire sensing technologies: A review,” IEEE Sensors Journal, vol. 19, no. 9, pp. 3191–3202, 2019
2. G. R. Pfister, “Multisensor/multicriteria fire detection: A new trend rapidly becomes state of the art,” Fire Technology, vol. 33, pp. 115– 139, 1997
3. M. A. I. Mahmoud and H. Ren, “Forest fire detection using a rule[1]based image processing algorithm and temporal variation,” Mathematical Problems in Engineering, 2018.
4. W. Wang, Z. Wang, Y. Chen, M. Guo, Z. Chen, Y. Niu, H. Liu, and L. Chen, “Bats: An appliance safety hazards factors detection algorithm with an improved nonintrusive load disaggregation method,” Energies, vol. 14, no. 12, 2021
5. A. Gagliardi and S. Saponara, “Advised: Advanced video smoke detection for real-time measurements in antifire indoor and outdoor systems,” Energies, vol. 13, no. 8, 2020.
6. Xu, R.; Lin, H.; Lu, K.; Cao, L.; Liu, Y. A Forest Fire Detection System Based on Ensemble Learning. Forests 2021, 12, 217.
7. Hossain, F.M.A.; Zhang, Y.; Tonima, M.A. Forest Fire Flame and Smoke Detection from UAV-Captured Images using Fire-Specific Color Features and Multi-Color Space Local Binary Pattern. J. Unmanned Veh. Syst. 2020, 8, 285–309.
8. Hossain, F.M.A.; Zhang, Y.; Tonima, M.A. Forest Fire Flame and Smoke Detection from UAV-Captured Images using Fire-Specific Color Features and Multi-Color Space Local Binary Pattern. J. Unmanned Veh. Syst. 2020, 8, 285–309. 
9. Ding, X.; Gao, J. A New Intelligent Fire Color Space Approach for Forest Fire Detection. J. Intell. Fuzzy Syst. 2022, 42, 5265–5281.
10. Khondaker, A.; Khandaker, A.; Uddin, J. Computer vision-based early fire detection using enhanced chromatic segmentation and optical flow analysis technique. Int. Arab J. Inf. Technol. 2020, 17, 947–953
11. Muhammad, K.; Ahmad, J.; Mehmood, I.; Rho, S.; Baik, S.W. Convolutional Neural Networks based Fire Detection in Surveillance Videos. IEEE Access 2018, 6, 18174–18183
12. Ultralytics-Yolov5. Available online: https://github.com/ultralytics/yolov5 (accessed on 5 June 2022)
13. M. Browne and S. Ghidary, “Convolutional neural networks for image processing: An application in robot vision,” in 16th Australian Conference on Artificial Intelligence, 2003.
14. “Fire-detection-image-dataset.” [Online].Available: https://github.com/cair/Fire-Detection-Image-Dataset.