The effectiveness of fire detection with convolutional neural networks

• Autorzy: Tatko Sebastian , Mazur Michał

Identyfikatory

DOI

10.37105/iboa.236

• Języki publikacji: EN

Abstrakty

EN

The article presents problems related to the detection of fire phenomena using convolutional neural network techniques. The main issue described in the article focuses on determining the precision of flame detection depending on lighting conditions and the selection of CNN architecture. The types of neural networks tested are primarily SSD architectures, which, with their speed of operation and energy consumption, are the most common in mobile applications. The study shows which of the neural network architectures used have the highest average precision in detecting the fire phenomenon. The selection of networks under testing was analyzed in terms of the speed of the algorithm and its precision. Four pre-trained neural network models were used during the testing of two training bases. The complexity of each model directly affected the training time of the model, which oscillated between 2-8 [h], and the precision achieved.

Słowa kluczowe

EN

fire detection; convolutional neural networks; CNN; effectiveness; area monitoring

PL

CNN; wykrywanie pożaru; sieć neuronowa splotowa; skuteczność; monitorowanie; obszar

• Wydawca: Centrum Rzeczoznawstwa Budowlanego Sp. z o.o.
• Czasopismo: Inżynieria Bezpieczeństwa Obiektów Antropogenicznych
• Rocznik: 2024
• Tom: Nr 4
• Strony: 41--47
• Opis fizyczny: Bibliogr. 7 poz., tab., rys., wykr.

Twórcy

autor

Tatko Sebastian

• Military University of Technology, Warsaw, Poland

• https://orcid.org/0000-0001-9603-427X

autor

Mazur Michał

• Military University of Technology, Warsaw, Poland

• https://orcid.org/0000-0003-2208-3057

Bibliografia

• 1. Ahmed, A., (2020). A Fire Detection Algorithm Using Convolutional Neural Network. Place: Jeddah Saudi Arabia. Publisher: journal of King Abdulaziz University Engineering Science.
• 2. Gauer, A., (2020). Fire Sensing Technologies. Place: U.S. Publisher: A Review, in IEEE Sensors Journal, vol. 19, no. 9, pp. 3191-3202.
• 3. Klimczak, T., Paś, J., Deuer, S., Rośiński, A., Wetoszka P., Białek, K., (2023). Selected Issues Associated with the Operational and Power Supply Reliability of Fire Alarm Systems. Place: Warsaw Publisher: Energies 15(22), 8409.
• 4. Nagababu, P., Dhakshitha, K., Chandrika, G., (2023). Automated Fire Detection System Using Image Surveillance System (ISS) and Convolutional Neural Networks (CNN). Place: India Publisher: 9th International Conference on Advanced Computing and Communication Systems (ICACCS).
• 5. Priya, R., Vani, K., (2019). Deep Learning Based Forest Fire Classification and Detection in Satellite Images. Place: Australia. Publisher: 11th International Conference on Advanced Computing.
• 6. Wangda, Z., (2020). Image fire detection algorithms based on convolutional neural networks. Place: Holland. Publisher: Case Studies in Thermal Engineering 19, 2020, 00625, ISSN 2214-157X.
• 7. Yuan, C., Zhang, M., (2015). A survey on technologies for automatic forestfire monitoring, detection, and fighting using unmanned aerial vehicles and remote sensing techniques. Place: Canada. Publisher: Canadian Journal of Forest Research, vol. 45, no. 7, 2015, pp. 783–792.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).