Development of a CNN-Based Smoke/Fire Detection System for High-Risk Environments

  • Nwosu Ifeoma
  • Alagbu Ekene
  • Okeke Obinna
  • Ikpo Kingsely
  • Onwuamanam Chrysantus
Keywords: fire detection, CNN, deep learning


This paper addresses the critical challenge of fire detection in high-risk environments, such as industrial facilities, warehouses, and densely populated areas. These locations face significant fire risks due to inherent processes and flammable materials. While traditional methods like smoke and heat detectors play a role, they have limitations like slow response times, false alarms, and ineffectiveness in large spaces. We propose a novel approach using a Convolutional Neural Network (CNN) for smoke/fire detection in these environments. Our CNN-based system continuously analyses video feeds, enabling faster fire detection compared to traditional methods and easily adapts its detection for scenes with challenging lighting conditions. This paper details the development, training process, and evaluation of the CNN system in simulated high-risk environments. The analysis of the system is performed in terms of accuracy, false alarm rate, and response time. The results demonstrate the potential of CNN technology for improving fire safety and early detection in critical locations, achieving an impressive accuracy of 94.14% and minimal loss of 0.14 during evaluation.


Almoussawi, Z. A., Khalid, R., Obaid, Z. S., Al Mashhadani, Z. I., Al-Majdi, K., Alsaddon, R. E., & Abed, H. M. (2022). Fire Detection and Verification using Convolutional Neural Networks, Masked Autoencoder and Transfer Learning. Majlesi Journal of Electrical Engineering, 16(4), 159-166.
Avazov, K., Hyun, A. E., Sami S, A. A., Khaitov, A., Abdusalomov, A. B., & Cho, Y. I. (2023). Forest fire detection and notification method based on AI and IoT approaches. Future Internet, 15(2), 61.
Biswas, A., Ghosh, S. K., & Ghosh, A. (2023). Early fire detection and alert system using modified inception-v3 under deep learning framework. Procedia Computer Science, 218, 2243–2252.
Keita, Z. (2023). Convolutional Neural Networks (CNN) with TensorFlow Tutorial: Learn how to construct and implement Convolutional Neural Networks (CNNs) in Python with Tensorflow Framework 2. Datacamp.
Khan, S., Muhammad, K., Mumtaz, S., Baik, S. W., & de Albuquerque, V. H. C. (2019). Energy-efficient deep CNN for smoke detection in foggy IoT environment. IEEE Internet of Things Journal, 6(6), 9237-9245.
Lee, Y., & Shim, J. (2019). False positive decremented research for fire and smoke detection in surveillance camera using spatial and temporal features based on deep learning. Electronics, 8(10), 1167.
Mandal, M. (2023). Introduction to Convolutional Neural Networks (CNN). Analytics Vidya.
Ryu, J., & Kwak, D. (2022). A study on a complex flame and smoke detection method using computer vision detection and convolutional neural network. Fire, 5(4), 108.
Sankarasubramanian, P., & Ganesh, E. N. (2021). Artificial Intelligence-Based Detection System for Hazardous Liquid Metal Fire. In 2021 8th International Conference on Computing for Sustainable Global Development (INDIACom) (pp. 1-6). IEEE, 2021.
Sathishkumar, V. E., Cho, J., Subramanian, M., & Naren, O. S. (2023). Forest fire and smoke detection using deep learning-based learning without forgetting. Fire Ecology, 19(1).
Wahyono, Harjoko, A., Dharmawan, A., Adhinata, F., Kosala, G., & Jo, K.-H. (2022). Real-time forest fire detection framework based on artificial intelligence using color probability model and motion feature analysis. Fire, 5(1), 23.
Yavuz Selim, T., Koklu, M., & Altin, M. (2021). Fire Detection in Images Using Framework Based on Image Processing, Motion Detection and Convolutional Neural Network. International Journal of Intelligent Systems and Applications in Engineering (IJISAE), 9(4), 171-177.
How to Cite
Ifeoma, N., Ekene, A., Obinna, O., Kingsely, I., & Chrysantus, O. (2024). Development of a CNN-Based Smoke/Fire Detection System for High-Risk Environments. European Journal of Science, Innovation and Technology, 4(2), 241-248. Retrieved from