2024
doi: 10.12720/jait.15.4.511-518
Comparison and Analysis of Three MobileNet-Based Models for Wildfire Detection
- 1Field of Electrical, Electronics and Information Engineering, Graduate School of Engineering, Kanagawa University, Yokohama, Japan
- 2Department of Applied Systems and Mathematics, Kanagawa University, Yokohama, Japan
- Manuscript receivedNovember 20, 2023
- revisedDecember 13, 2023
- acceptedJanuary 17, 2024
- publishedApril 16, 2024
Abstract
The dynamic equilibrium of ecosystems can be maintained through controlled burning, but excessive wildfires can lead to severe consequences. Therefore, the use of Internet of Things (IoT) devices equipped with deep image processing models for wildfire detection has recently become a trend. Conventional deep image processing models suffer from accuracy issues and large model sizes, limiting their applicability on small IoT devices. To address this challenge, we utilized lightweight deep image processing models such as the MobileNet series to train a wildfire database. Furthermore, we evaluated three different versions of MobileNet (V2, V3 Large, and V3 Small) using a cross-entropy loss function to compare their accuracy and training times. Through data analysis, recommendations for deploying MobileNet models on IoT devices are provided. The results indicate that the ranking of MobileNet’s accuracy from highest to lowest is V2, V3 Large, and V3 Small; the ranking of loss values from lowest to highest is V2, V3 Large, and V3 Small; and the ranking of training times from fastest to slowest is V3 Large, V2, and V3 Small.
Keywords
- wildfire detection
- MobileNet model
- deep learning
- comparison and analysis
How to Cite
Shiyan Du, Jiacheng Li, and Masato Noto, "Comparison and Analysis of Three MobileNet-Based Models for Wildfire Detection," Journal of Advances in Information Technology, vol. 15, no. 4, pp. 511-518, 2024. https://doi.org/10.12720/jait.15.4.511-518
Copyright & License
Copyright © 2024 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).






