Abstract
In recent years, the number and intensity of forest fires have been increasing due to climate change, causing great ecological and property losses. The recent advances in deep learning and object detection have made it possible to use efficient models to detection forest fires. To further improve the detection speed and accuracy of early forest fires, the deep learning-based methods are increasingly adopted. Considering the detection speed and accuracy, the MobileNet SSD model has a good performance. However, it does not perform well when detecting small objects, such as fire in the initial stage. To enhance the model’s detection performance for small objects, we proposed an improved feature pyramid network. To achieve real-time speed, replace SSD (Single Shot MultiBox Detector) with SSDLite, forming a MobileNetV2_SSDLite_FPN model. The experimental results indicate that this model achieves 89.7% mean Average Precision (mAP), 2.3 MB parameters, and 0.013 s average running time on our fire dataset.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Fonollosa, J., Solórzano, A., Jiménez-Soto, J.M., Oller-Moreno, S., Marco, S.: Gas sensor array for reliable fire detection. Proc. Eng. 168, 444–447 (2016). ISSN 1877–7058, https://doi.org/10.1016/j.proeng.2016.11.540
Lee, K., Shim, Y.-S., Song, Y., Han, S., Lee, Y.-S., Kang, C.-Y.: Highly sensitive sensors based on metal-oxide nanocolumns for fire detection. Sensors 17(2), 303 (2017)
Sowah, R.A., Ofoli, A.R., Krakani, S.N., Fiawoo, S.Y.: Hardware design and web-based communication modules of a real-time multisensor fire detection and notification system using fuzzy logic. IEEE Trans. Ind. App. 53(1), 559–566 (2017)
Kr Kruger, S., Despinasse, M.C., Raspe, T., Kai, N., Moritz, W.: Early fire detection: are hydrogen sensors able to detect pyrolysis of household materials. Fire Safety J. 91, 1059–1067 (2017)
Çelik, T., Özkaramanlı, H., Demirel, H.: Fire and smoke detection without sensors: image processing based approach. In: 15th European Signal Processing Conference (EUSIPCO 2007), 3–7 September 2007
Seebamrungsat, J., Praising, S., Riyamongkol, P.: Fire detection in the buildings using image processing. In: Proceedings of the 2014 Third ICT International Student Project Conference (ICT-ISPC), pp. 95–98, IEEE, Bangkok, Thailand, March 2014
Foggia, P., Saggese, A., Vento, M.: Real-time fire detection for video-surveillance applications using a combination of experts based on color, shape, and motion. IEEE Trans. Circuits Syst. Video Technol. 25(9), 1545–1556 (2015)
Bi, F., Fu, X., Chen, W., Fang, W., Miao, X.: Fire detection method based on improved fruit fly optimization-based SVM. Comput. Mater. Cont. 62(1), 199–216 (2020)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Pereira, F., Burges, C.J.C., Bottou, L., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems 25, pp. 1097–1105. Curran Associates Inc., Red Hook (2012)
Wu S., Zhang L.: Using popular object detection methods for real time forest fire detection. In Proceedings of the 11th International Symposium on Computational Intelligence and Design (ISCID 2018), Hangzhou, China, 8–9 December 2018; pp. 280–284
Kim, B., Lee, J.: A video-based fire detection using deep learning models. Appl. Sci. 9, 2862 (2019)
Lee, Y., Shim, J.: 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 (2019). https://doi.org/10.3390/electronics8101167
Wu, S., Guo, C., Yang, J.: Using PCA and one-stage detectors for real-time forest fire detection. J. Eng. 2020, 383–387 (2020)
Muhammad, K., Ahmad, J., Lv, Z., Bellavista, P., Yang, P., Baik, S.W.: Efficient deep CNN-based fire detection and localization in video surveillance applications. IEEE Trans. Syst. Man Cybern. Syst. 49(7), 1419–1434 (2019). https://doi.org/10.1109/TSMC.2018.2830099
Peng, Y., Wang, Y.: Real-time forest smoke detection using hand-designed features and deep learning. Comput. Electron. Agric. 167, 105029 (2019). ISSN 0168–1699, https://doi.org/10.1016/j.compag.2019.105029
Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unifified, real-time object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779–788 (2016)
Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Cheng-Yang, F., Berg, A.C.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) Computer Vision – ECCV 2016. LNCS, vol. 9905, pp. 21–37. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46448-0_2
Simonyan, K., Zisserman, A.: Very Deep Convolutional Networks for Large-Scale Image Recognition. CoRR, abs/1409.1556
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.-C.: MobileNetV2: inverted residuals and linear bottlenecks. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4510–4520 (2018). https://doi.org/10.1109/CVPR.2018.00474
Howard, A.G., et al.: MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)
Lin, T.-Y., Dollár, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117–2125 (2017)
Li, Q., Lin, Y., He, W.: SSD7-FFAM: a real-time object detection network friendly to embedded devices from scratch. Appl. Sci. 11, 1096 (2021)
AL-Ghadani, S.S., Jayakumari, C.: Innovating fire detection system fire using artificial intelligence by image processing. Int. J. Innov. Technol. Explor. Eng. (IJITEE) 9(11) (2020). ISSN: 2278–3075
Wang, G.: Fire detection method based on transformer improved YOLO v4. Intell. Comput. App. 11(7), 86–90 (2021)
Acknowledgements
This work was supported by Provincial Key Platforms and Major Research Projects of Universities in Guangdong Province under No. 2021ZDZX3012 and 2021KTSCX187. The authors gratefully acknowledge all these supports.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
An, Y., Tang, J., Li, Y. (2022). A MobileNet SSDLite Model with Improved FPN for Forest Fire Detection. In: Wang, Y., Ma, H., Peng, Y., Liu, Y., He, R. (eds) Image and Graphics Technologies and Applications. IGTA 2022. Communications in Computer and Information Science, vol 1611. Springer, Singapore. https://doi.org/10.1007/978-981-19-5096-4_20
Download citation
DOI: https://doi.org/10.1007/978-981-19-5096-4_20
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-5095-7
Online ISBN: 978-981-19-5096-4
eBook Packages: Computer ScienceComputer Science (R0)