Abstract
To address the challenges of small target flames and target scale variation in forest fire images, a target detection method for forest fire images based on multi-scale feature extraction was studied, with YOLOv9c as the baseline model. Initially, a lightweight feature extraction module named EGI (ECA_Ghost_InceptionV2) was proposed to serve as the backbone feature extraction network, which improved the model’s feature extraction capability and operational efficiency. Second, a P2 small target detection head was introduced; meanwhile, a small target feature fusion module was added to the Neck layer, and the CARAFE upsampling operator was incorporated, enhancing the model’s ability to extract underlying feature information. Finally, to solve the problems of misalignment and scale inconsistency in the traditional IoU loss function, Inner_DIoU was introduced. This enabled the relative relationship between bounding boxes to be described more accurately and improved the precision of target detection. The improved model was validated through experiments on the DFireDataset. Results show that it achieved a detection accuracy of 79.2%, representing a 3.8% improvement compared with the baseline model, while the number of parameters was reduced by 29%, It also maintains a real-time inference speed of over 25 FPS on edge GPUs, enabling deployment in UAV-based forest monitoring systems. In addition, the model exhibits strong robustness to complex natural backgrounds and significantly reduces false alarms compared with existing methods. These findings demonstrate that the proposed model exhibits excellent performance in small target flame detection and is well-suited for the target detection task of forest fire images.
Data availability
The data presented in this study are available upon request from the corresponding author.
References
Zhao, Z. Q., Zheng, P., Xu, S. & Wu, X. Object detection with deep learning: a review. IEEE Trans. Neural Netw. Learn. Syst. 30, 11, 3212–3232 (2019).
Frizzi, S., Kaabi, R., Bouchouicha, M. & Ginoux, J. M. Convolutional neural network for video fire and smoke detection. in Proceedings of the 42nd Annual Conference of the IEEE Industrial Electronics Society (IECON) 877–882 (IEEE, 2016).
Bhatt, D., Patel, C., Talsania, H. & Patel, J. Cnn variants for computer vision: history, architecture, application, challenges and future scope. Electron 10, 20, 2470 (2021).
Alkhatib, A. A. A. A review on forest fire detection techniques. Int. J. Distrib. Sens. Netw. 10, 3, 597368 (2014).
Niu, S., Zhu, Y. & Wang, J. Small target flame detection algorithm based on improved yolov7. J. Electron. Imaging. 32, 5, 053032–053032 (2023).
Gomaa, A. & Saad, O. M. Residual channel-attention (RCA) network for remote sensing image scene classification. Multimed. Tools Appl. 84, 33837–33861 (2025).
Ma, Y., Huang, Z. & Zhou, W. A lightweight remote sensing small target image detection algorithm based on improved yolov8. Comput. Eng. 51, 9, 350–361 (2025).
Gomaa, A. & Abdalrazik, A. Novel deep learning domain adaptation approach for object detection using semi-self building dataset and modified yolov4. World Electr. Veh. J. 15, 255 (2024).
Xu, R. J., Xie, H., Jiang, W. J., Li, H. B. & Xiao, Y. Lightweight early forest fire detection algorithm fusing multi-scale attention. Electron Meas. Technol.48(15), 80-90(2025).
Xue, Z., Lin, H. & Wang, F. A small target forest fire detection model based on yolov5 improvement. Forests 13, 8, 1332 (2022).
Woo, S., Park, J., Lee, J. Y. & Kweon, I. S. CBAM: Convolutional block attention module. in Proceedings of the European Conference on Computer Vision (ECCV) 3–19 (2018).
Tan, M., Pang, R. & Le, Q. V. Efficientdet: Scalable and efficient object detection. in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 10781–10790 (2020).
Liu, W., Shen, Z. & Xu, S. CF-YOLO: A capable forest fire identification algorithm founded on yolov7 improvement. Signal. Image Video Process. 18, 1–11 (2024).
Wang, C. Y., Bochkovskiy, A. & Liao, H. Y. M. Yolov7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 7464–7475 (2023).
Hou, Q., Zhou, D. & Feng, J. Coordinate attention for efficient mobile network design. in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 13713–13722 (2021).
Hou, Q., Zhou, D. & Feng, J. Coordinate attention for efficient mobile network design. in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 13713–13722 (2021).
Hassan, O. F., Ibrahim, A. F., Gomaa, A., Makhlouf, M. A. & Hafiz, B. Real-time driver drowsiness detection using transformer architectures: A novel deep learning approach. Sci. Rep. 15, 17493 (2025).
Shen, J. et al. Lightweight semantic feature extraction model with direction awareness for aerial traffic object detection. IEEE Trans. Intell. Transp. Syst. https://doi.org/10.1109/TITS.2025.3642410 (2025).
Shen, J. et al. An anchor-free lightweight deep convolutional network for vehicle detection in aerial images. IEEE Trans. Intell. Transp. Syst. 23, 12, 24330–24342. https://doi.org/10.1109/TITS.2022.3203715 (2022).
Shen, J., Liu, N., Sun, H., Li, D. & Zhang, Y. An instrument indication acquisition algorithm based on lightweight deep convolutional neural network and hybrid attention fine-grained features. IEEE Trans. Instrum. Meas. 73, 1–16. https://doi.org/10.1109/TIM.2023.3346488 (2024). Art. 5008516.
Shen, J. et al. Finger vein recognition algorithm based on lightweight deep convolutional neural network. IEEE Trans. Instrum. Meas. 71, 1–13. https://doi.org/10.1109/TIM.2021.3132332 (2022). Art. 5000413.
Abdelmaaboud, Ahmed, et al. AI-driven versus traditional ionospheric modeling approaches for GNSS positioning in Egypt. Journal of Applied Geodesy. 0 (2025).
Artificial neural network–based modeling and prediction of GNSS ionospheric errors in Egypt.
Abdalrazik, Ahmad, Ahmed Gomaa, and Asmaa Afifi. Multiband circularly-polarized stacked elliptical patch antenna with eye-shaped slot for GNSS applications. International Journal of Microwave and Wireless Technologies. 16(7), 1229-1235 (2024).
Abdalrazik, Ahmad, Ahmed Gomaa, and Ahmed A. Kishk. A wide axial-ratio beamwidth circularly-polarized oval patch antenna with sunlight-shaped slots for gnss and wimax applications. Wireless Networks . 28(8), 3779-3786 (2022).
Gomaa, Ahmed, Asmaa Afifi, and Ahmad Abdalrazik. A dual-band wide axial-ratio beamwidth circularly-polarized antenna with v-shaped slot for l2/l5 gnss applications. Novel Intelligent and Leading Emerging Sciences Conference (NILES). IEEE, (2024).
Wang, C. Y., Yeh, I. H. & Liao, H. Y. M. Yolov9: Learning what you want to learn using programmable gradient information. Preprint at (2024). https://arxiv.org/abs/2402.13616.
Zhu, H., Li, Y., Wu, Y. & Wang, J. CARAFE: Content-aware reassembly of features for high-quality feature upsampling. in Proceedings of the IEEE/CVF International Conference on Computer Vision 9915–9924 (2019).
Zhang, H., Xu, C. & Zhang, S. Inner-IoU: More effective intersection over union loss with auxiliary bounding box. Preprint at (2023). https://arxiv.org/abs/2311.02877.
Han, K., Wang, Y., Tian, Q. & Guo, J. Ghostnet: More features from cheap operations. in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 1580–1589 (2020).
Wang, Q., Wu, B., Zhu, P. & Li, P. ECA-Net: efficient channel attention for deep convolutional neural networks. in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 12911–12920 (2020).
Ioffe, S. & Szegedy, C. Batch normalization: accelerating deep network training by reducing internal covariate shift. Preprint at. (2015). https://arxiv.org/abs/1502.03167.
Terven, J., Córdova-Esparza, D. M. & Romero-González, J. A. A comprehensive review of yolo architectures in computer vision: From yolov1 to yolov8 and yolo-nas. Mach. Learn. Knowl. Extract. 5, 4, 1680–1716 (2023).
Zheng, Z., Wang, P., Liu, W. & Li, H. Distance-IoU loss: faster and better learning for bounding box regression. in Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34(07) 12993–13000 (2020).
de Venâncio, P. V. A. B., Lisboa, A. C. & Barbosa, A. V. An automatic fire detection system based on deep convolutional neural networks for low-power, resource-constrained devices. Neural Comput. Appl. 34, 18, 15349–15368 (2022).
Funding
This research was funded by the Guangxi Key Research and Development Program Grant No. FN2504240010, by the Guangxi Zhuang Autonomous Region Youth Talent Project under Grant 301780227, by the Guangxi Basic Ability Improvement Project for Young and Middle-aged Teachers under Grant 2025KY0213, and by the Guangxi Minzu University Xiangsi Lake Youth Scholar Innovation Team under Grant 2023GXUNXSHQN06.
Author information
Authors and Affiliations
Contributions
Conceptualization, Z.X.; methodology, Z.X.; software, Z.X.; validation, Z.X., W.W., Q.J., F.Z. and X.K.; formal analysis, Z.X.; investigation, Z.X.; resources, Z.X.; data curation, Z.X., Q.J. and F.Z.; writing—original draft preparation, Z.X.; writing—review and editing, W.W.; visualization, F.Z.; supervision, W.W.; project administration, W.W.; funding acquisition, W.W. All authors have read and agreed to the published version of the manuscript.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Wu, W., Zhou, X., Qin, J. et al. Research on target detection algorithm for forest fire images based on multi-scale feature extraction. Sci Rep (2026). https://doi.org/10.1038/s41598-026-41994-2
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-41994-2
