Abstract
In recent years, all regions of China have constantly paid attention to forest fire prevention, which however is still restricted to onsite observation carried out by forest ranger and basic satellite resource survey. The use of UAV system for forest fire monitoring is still in its infancy. To bridge the gap, this study trains the YOLO-V3 algorithm for forest fire detection based on UAV collected data. Traditional flame detection models are commonly based on RGB colors. They can suffer low accuracy and detection speed, and it is still difficult for the YOLO-V3-based model to detect small flames. In this paper, the YOLO-V3 model is improved to support multi-feature detection. Specifically, 208208 smaller resolution feature scales are added to allow the model learning shallow features of flame images. In this way, the learning ability of the proposed model for shallow image information is improved in the feature extraction stage, which can facilitate the dentification of small flame regions. In addition, the prior box is optimized to further improve detection precision. In the experiment, the mAP value can reach 67.6% with detection speed of 190FPS.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Li, Q., Hou, J., He, N., Xu, L., Zhang, Z.: Changes in leaf stomatal traits of different aged temperate forest stands. J. For. Res. 32(3), 927–936 (2020)
Nuri, N.S., Endah, S.: A seed rain community in a reforested post-agricultural fieldand adjacent secondary forest of Mount Papandayan nature reserve, west java, Indonesia. J. For. Res. 34(03), 1013–1023 (2021)
**, Y.H., Wang, W.K., Lee, W.H., Jaegeol, Y.: An indoor location-based positioning system using stereo vision with the drone camera. Mob. Inf. Syst. 3, 5160543–5516559 (2018)
Michael, F., Jeremy, B.: US Navy “brings down” Iranian UAV threatening LHD in Strait of Hormuz. J. Jane’s Defence Weekly 56(30), 4 (2019)
Frizzi, S., Kaabi, R., Bouchouicha, M.: Convolutional Neural Network for Video Fireand Smoke Detection. In: Conference of the IEEE Industrial Electronics Society, pp. 529--542. IEEE Press, Italy (2016)
El Bouhissi, M., Bouidjra, S.E.B., Benabdeli, K.: GIS, forest fire prevention and risk matrix in the national forest of Khoudida, Sidi Bel Abbes, Algeria. Open J. Ecol. 10(06), 356–369 (2020)
Shi, R., Li, T., Ya, M.: An attribution-based pruning method for real-time mango detection with YOLO network. Comput. Electron. Agric. 169, 105214–105219 (2020)
Shaikh, S.A., Abdul, Kadir, K.S.: Object detection and tracking using YOLO v3 framework for increased resolution video. Int. J. Innov. Technol. Exploring Eng. 9(6), 141–148 (2020)
Zhao, Y.Y., Zhu, J., **e, Y.K., Li, W.L., Guo, Y.K.: Improved YOLO-V3 video image flame real-time detection algorithm. Inf. Sci. Ed. 6, 78–82 (2021)
Huang, Z.C., Wang, J.L., Fu, X.S., Yu, T.G., Wang, Y.Q.: DC-SPP-YOLO, dense connection and spatial pyramid pooling based YOLO for object detection. Inf. Sci. 3, 551–556 (2020)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Wang, Z., Zhang, H., Hou, M., Shu, X., Wu, J., Zhang, X. (2021). A Study on Forest Flame Recognition of UAV Based on YOLO-V3 Improved Algorithm. In: Li, K., Coombs, T., He, J., Tian, Y., Niu, Q., Yang, Z. (eds) Recent Advances in Sustainable Energy and Intelligent Systems. LSMS ICSEE 2021 2021. Communications in Computer and Information Science, vol 1468. Springer, Singapore. https://doi.org/10.1007/978-981-16-7210-1_47
Download citation
DOI: https://doi.org/10.1007/978-981-16-7210-1_47
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-7209-5
Online ISBN: 978-981-16-7210-1
eBook Packages: Computer ScienceComputer Science (R0)