Abstract
In recent years, the frequent occurrence of forest fires has caused serious impact on the environment and economy. Fire detection has become a hot research direction. Despite the remarkable achievements, the unmanned aerial vehicle (UAV) still has some problems such as insufficient precision and excessive parameters. In order to improve the application ability of UAV in forest fire prevention and control, a lightweight target detection model based on YOLOv5 is proposed. The model is based on the overall structure of YOLOv5, MobileNetV3 is used as the backbone network, and semi-supervised knowledge distillation (SSLD) is used for training to improve the convergence speed and accuracy of the model. The final model size was reduced by 94.1% from 107.6 MB to 6.3 MB. mAP0.5 increased by 0.8% and mAP0.95 increased by 2.6%. The improved lightweight YOLOv5 model has fewer parameters and less computation, which confirms that MobileNetV3 has an excellent effect on the compression of model memory, and the semi-supervised knowledge distillation method is beneficial to improve the accuracy of the model. In the future, the accuracy of the model and the detection rate of the covered flame should be further improved.
Similar content being viewed by others
Data availability
Data will be made available on reasonable request.
References
Abbassi MAE, Jilbab A, Bourouhou A (2016) A robust model of multi-sensor data fusion applied in wireless sensor networks for fire detection. Int Rev Model Simul 9:173–180
Andrew AM, Zakaria A, Saad SM, Shakaff AYM (2016) Multi-stage feature selection based intelligent classifier for classification of incipient stage fire in building. Sensors 16:31
Bhattarai M, Mart’inez-Ram’on M (2020) A deep learning framework for detection of targets in thermal images to improve firefighting. IEEE Access 8:88308–88321
Borges PVK, Mayer J, Izquierdo E (2008) Efficient visual fire detection applied for video retrieval. 2008 16th European Signal Processing Conference, 1–5
Bushnaq OM, Chaaban A, Tareq Y, Al-Naffouri (2021) The role of uav-iot networks in future wildfire detection. IEEE Internet Things J 8:16984–16999
Conrad T, Reimann P, Schutze A (2007) A hierarchical strategy for under-ground early fire detection based on a t-cycled semiconductor gas sensor. 2007 IEEE Sensors, 1221–1224
Foggia P, Saggese A, Vento M (2015) 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 25:1545–1556
Gagliardi A, de Gioia F, Saponara S (2021) A real-time video smoke detection algorithm based on kalman filter and cnn. J Real-Time Image Proc 18:1–11
Gao Yu, Cheng PL (2019) Forest fire smoke detection based on visual smoke root and diffusion model. Fire Technol 55:1801–1826
Hackner A, Oberpriller H, Ohnesorge A, Hechtenberg V, Müller G (2016) Heterogeneous sensor arrays: merging cameras and gas sensors into innovative fire detection systems. Sens Actuators B Chem 231:497–505
Howard AG, Sandler M, Chu G, Chen L-C, Chen B, Tan M, Wang W, Zhu Y, Pang R, Vasudevan V, Le QV, Adam H (2019) Searching for MobileNetV3. 2019 IEEE/CVF International Conference on Computer Vision (ICCV), 1314–1324
Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, Adam H (2017) Mobilenets: efficient convolutional neural networks for mobile vision applications. ArXiv abs/1704.04861
Jiao Z, Zhang Y, Mu L, Xin J, Jiao S, Liu H, Liu D (2020) A yolov5-based learning strategy for real-time uav-based forest fire detection. 2020 Chinese Control and Decision Conference (CCDC), 4963–4967
Khuzani AZ, Agrawal R, Mashhadi N (2019) Fire detection in video sequences using a machine learning system and a clustered quantitative image marker. 2019 IEEE Global Humanitarian Technology Conference (GHTC), 1–5
Kuanar S, Athitsos V, Mahapatra D, Rao KR, Akhtar Z, Dasgupta D (2019) Low dose abdominal ct image reconstruction: an unsupervised learning based approach. 2019 IEEE International Conference on Image Processing (ICIP), 1351–1355
Kuanar S, Rao KR, Bilas M, Bredow JW (2019) Adaptive CU mode selection in HEVC intra prediction: a deep learning approach. Circ Syst Signal Proc 38:5081–5102
Pan J-s, Ou X, Xu L (2021) A collaborative region detection and grading framework for forest fire smoke using weakly supervised fine segmentation and lightweight faster-rcnn. Forests 12:768
Qin Yu, Cao J, Ji X (2021) Fire detection method based on depthwise separable convolution and yolov5. Int J Autom Comput 18:300–310
Redmon J, Farhadi A (2018) Yolov5: an incremental improvement. ArXiv abs/1804.02767
Redmon J, Divvala SK, Ross B, Girshick, Farhadi A (2016) You only look once: unified, real-time object detection. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, 779–788
Robinne FN, Secretariat F (2021) Impacts of disasters on forests, in particular forest fires. UNFFS background paper
Saeed F, Paul A, Karthigaikumar P, Nayyar A (2019) Convolutional neural network based early fire detection. Multimedia Tools Appl 79:9083–9099
Sandler M, Howard AG, Zhu M, Zhmoginov A, Chen L-C (2018) Mobilenetv2: inverted residuals and linear bottlenecks. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 4510–4520
Shamsoshoara A, Afghah F, Razi A, Zheng L, Ful’e PZ, Blasch EP (2020) Aerial imagery pile burn detection using deep learning: the FLAME dataset. Comput Netw 193:108001
Sharma A, Kumar H, Mittal K, Kauhsal S, Kaushal M (2021) Divyam Gupta and Abheer Narula. Iot and deep learning-inspired multi-model framework for monitoring active fire locations in agricultural activities. Comput Electr Eng 93:107216
Sudhakar S, Vijayakumar V, Kumar CS, Priya V, Ravi L, Subramaniyaswamy V (2020) Unmanned aerial vehicle (uav) based forest fire detection and monitoring for reducing false alarms in forest-fires. Comput Commun 149(Jan):1–16
Xu M, Zhang Z, Han Hu, Wang J, Wang L, Wei F, Bai X, Liu Z (2021) End-to-end semi-supervised object detection with soft teacher. 2021 IEEE/CVF International Conference on Computer Vision (ICCV), 3040–3049
Ye X, Wu S-s, Xu J (2014) Study on a fire detection system based on support vector machine. Sensors and Transducers 57–61
Zhu Y, Xie LQ (2013) Forest fire detection system based on zigbee wireless sensor network. Adv Mater Res 694–697:961–965
Zhu L, Detachment ZF (2018) Forest smoke detection algorithm based on image enhancement and multi-feature of texture. Fire Sci Technol 37:225–228 (in Chinese).
Zhu M, Gupta S (2018) To prune, or not to prune: exploring the efficacy of pruning for model compression. ArXiv abs/1710.01878
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
The authors declare no conflict of interest.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Zhou, M., Wu, L., Liu, S. et al. UAV forest fire detection based on lightweight YOLOv5 model. Multimed Tools Appl (2023). https://doi.org/10.1007/s11042-023-15770-7
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11042-023-15770-7