Abstract
Accidental fire outbreak threatens people's life and property safety, and it is of great significance to study fire detection and alarm early. The detection range of traditional fire detectors is limited, and the conventional detection algorithm has the problems of low precision and long detection time. Aiming at these problems, a video fire detection method based on improved YOLOv5 is proposed in this paper. To improve the ability of feature extraction and small-scale target detection, the dilated convolution module is introduced into the SPP module of YOLOv5, the activation function GELU and the prediction bounding box suppression DIoU-NMS are employed in the structure of the improved YOLOv5. The experimental results show that the algorithm has fast detection speed and high detection accuracy. It can accurately detect not only large-scale flame but also small-scale flame in the early stage of fire. The precision and recall of the improved small YOLOv5 are 0.983 and 0.992, the mAP@.5 is as high as 0.993, and the detection speed reaches 125 FPS. The proposed method can well suppress false detection and missed detection in complex lighting environments and improve the robustness and reliability of fire detection, meet the performance requirements of the video fire detection task.
Similar content being viewed by others
References
Gaur A, Singh A, Kumar A, Kumar A, Kapoor K (2020) Video flame and smoke based fire detection algorithms: a literature review. Fire Technol 56:1943–1980
CTIF (2021) World fire statistics. https://ctif.org/world-fire-statistics.
Barmpoutis P, Papaioannou P, Dimitropoulos K, Grammalidis N (2020) A review on early forest fire detection systems using optical remote sensing. Sensors-Basel 20(22):6442
Truong TX, Kim JM (2012) Fire flame detection in video sequences using multi-stage pattern recognition techniques. Eng Appl Artif Intell 25:1365–1372
Han XF, Jin JS, Wang MJ, Jiang W, Gao L, Xiao LP (2017) Video fire detection based on Gaussian Mixture Model and multi-color features. Signal Image Video Process 11(8):1419–1425
Peng YS, Wang Y (2019) Real-time forest smoke detection using hand-designed features and deep learning. Comput Electron Agric 167:105029
Li SB, Yan QD, Liu P (2020) An efficient fire detection method based on multiscale feature extraction, implicit deep supervision and channel attention mechanism. IEEE Trans Image Process 29:8467–8475
Torabian M, Pourghassem H, Mahdavi-Nasab H (2021) Fire detection based on fractal analysis and spatio-temporal features. Fire Technol 57(5):2583–2614
Muhammad K, Ahmad J, Mehmood I, Rho S, Baik SW (2018) Convolutional neural networks based fire detection in surveillance videos. IEEE Access 6:18174–18183
Pan HY, Badawi D, Zhang X, Cetin AE (2020) Additive neural network for forest fire detection. Signal Image Video P 14:675–682
Zhang JD, Xie WH, Liu HY, Dang WY, Yu AF, Liu D (2022) Compressed dual-channel neural network with application to image-based smoke detection. IET Image Process 16(4):1036–1043
Wang Z, Wang Z, Zhang H, Guo X (2017) A novel fire detection approach based on CNN-SVM using tensorflow. International conference on intelligent computing. Springer, Cham, pp 682–693
Mao WT, Wang WP, Dou Z, Li Y (2018) Fire recognition based on multi-channel convolutional neural network. Fire Technol 54:531–554
Luo YM, Zhao L, Liu PZ, Huang DT (2018) Fire smoke detection algorithm based on motion characteristic and convolutional neural networks. Multimed Tools Appl 77:15075–15092
Saeed F, Paul A, Karthigaikumar P, Nayyar A (2020) Convolutional neural network based early fire detection. Multimed Tools Appl 79:9083–9099
Diwate RB, Patil LV, Khodaskar MR, Kulkarni NP (2021) Lower complex CNN model for fire detection in surveillance videos. In: International conference on emerging smart computing and informatics (ESCI), pp 380–384
Matlani P, Shrivastava M (2019) Hybrid deep VGG-NET convolutional classifier for video smoke detection. CMES-Comput Model Eng 119:427–458
Wu YL, Chen MH, Wo Y, Han GQ (2020) Video smoke detection base on dense optical flow and convolutional neural network. Multimed Tools Appl 80(28):35887–35901
Chaoxia CY, Shang WW, Zhang F (2020) Information-guided flame detection based on faster R-CNN. IEEE Access 8:58923–58932
Nguyen AQ, Nguyen HT, Tran VC, Pham HX, Pestana J (2021) A visual real-time fire detection using single shot multibox detector for UAV-based fire surveillance. In: IEEE ICCE 2020: 2020 IEEE eighth international conference on communications and electronics (ICCE), pp 338–343 (2021).
Zhao J, Wei HC, Zhao XY, Ta N, Xiao MX (2021) Application of Improved YOLO v4 model for real time video fire detection. Basic Clin Pharmacol 128:47–47
Yoshiaki and Okayama (1991) A primitive study of a fire detection method controlled by artificial neural net. Fire Saf J 17:535–553
Baek J, Alhindi TJ, Jeong MK, Jeong YS, Seo S, Kang J, Choi J, Chung H (2021) Real-time fire detection algorithm based on support vector machine with dynamic time warping kernel function. Fire Technol 57(6):2929–2953
Frizzi S, Kaabi R, Bouchouicha M, Ginoux JM, Moreau E, Fnaiech F (2016) Convolutional neural network for video fire and smoke detection. In: Conference of the IEEE industrial electronics society, pp 877–882.
Maksymiv O, Rak T, Peleshko D (2017) Real-time fire detection method combining AdaBoost, LBP and convolutional neural network in video sequence. In: 2017 14th international conference: the experience of designing and application of cad systems in microelectronics (Cadsm), pp 351–353.
Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 779–788
Redmon J, Farhadi A (2017) YOLO9000: better, faster, stronger. In: IEEE conference on computer vision & pattern recognition, pp 6517–6525
Redmon J, Farhadi A (2018) YOLOv3: an incremental improvement.
Bochkovskiy A, Wang C-Y, Liao HYM (2020) YOLOv4: optimal speed and accuracy of object detection.
Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY, Berg AC (2016) SSD: single shot multibox detector. Comput Vis Pt I 9905:21–37
Lin TY, Goyal P, Girshick R, He KM, Dollar P (2020) Focal loss for dense object detection. IEEE Trans Pattern Anal Mach Intell 42:318–327
Girshick R (2015) Fast R-CNN In: 2015 IEEE international conference on computer vision (ICCV), pp 1440–1448.
Ren S, He K, Girshick R, Sun J (2017) Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39:1137–1149
Shen D, Chen X, Nguyen M, Yan WQ (2018) Flame detection using deep learning. In: 2018 4th international conference on control, automation and robotics (ICCAR), pp 416–420.
Barmpoutis P, Dimitropoulos K, Kaza K, Grammalidis N (2019) Fire detection from images using faster R-CNN and multidimensional texture analysis. Int Conf Acoust Spee 8301–8305
Saponara S, Elhanashi A, Gagliardi A (2021) Real-time video fire/smoke detection based on CNN in antifire surveillance systems. J Real-Time Image Pr 2021:889–900
Park M, Ko BC (2020) Two-step real-time night-time fire detection in an urban environment using static ELASTIC-YOLOv3 and temporal fire-tube. Sensors-Basel 20(8):2202
He K, Zhang X, Ren S, Sun J (2014) Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans Pattern Anal Mach Intell 37:1904–1916
Hendrycks D, Gimpel K (2020) Gaussian error linear units (GELUs). arXiv:1606.08415v4
Zheng Z, Wang P, Liu JLW, Ye R, Ren D (2019) Distance-IoU loss: faster and better learning for bounding box regression. arXiv:1911.08287
Ultralytics (2021) YOLOv5. https://github.com/ultralytics/yolov5.
Acknowledgements
Thanks the National Natural Science Foundation of China, Natural Science Foundation of Tibet Autonomous Region, and Scientific Research Fund Project of Xianyang Normal University support for this work.
Funding
National Natural Science Foundation of China (62073218); Natural Science Foundation of Tibet Autonomous Region (XZ202001ZR0048G); Scientific Research Project of Xianyang Science and Technology Bureau (2020K02-14); Scientific Research Fund Project of Xianyang Normal University ( XSYK20025).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no competing interests and conflicts 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
About this article
Cite this article
Wu, Z., Xue, R. & Li, H. Real-Time Video Fire Detection via Modified YOLOv5 Network Model. Fire Technol 58, 2377–2403 (2022). https://doi.org/10.1007/s10694-022-01260-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10694-022-01260-z