Image fire detection algorithms based on object detection convolutional neural networks

Fire Science and Technology ›› 2022, Vol. 41 ›› Issue (6): 807-811.

Previous Articles Next Articles

Image fire detection algorithms based on object detection convolutional neural networks

ZHANG Miao1, LI Pu2, YANG Yi3, SONG Wen-hua4

(1. Tianjin Heping Fire and Rescue Division, Tianjin 300090, China; 2. Zhengzhou Airport Economy Zone Fire and Rescue Division, He'nan Zhengzhou 450000, China; 3. Xi'an University of Science and Technology, Shaanxi Xi'an 710054, China; 4. School of Environmental Science and Engineering, Tianjin Polytechnic University, Tianjin 300387, China)

Online:2022-06-15 Published:2022-06-15

Abstract

Abstract: Abstract: The existing image fire detection algorithms have the problems of weak generalization ability, high false alarm rate, and low practicality. Based on four advanced object detection convolutional neural networks (e.g. Faster-RCNN, R-FCN, SSD and YOLO v3), new image fire detection algorithms were developed. The comparison of the proposed and current algorithms reveals that the algorithms based on object detection CNNs have significant advantages. Especially, the average precision of the algorithm based on YOLO v3 reaches to 84.5%, and the detection velocity is 28 frame/s. Besides, the YOLO v3 also has stronger robustness of detection performance, and is suitable for developing fire detection system.

Key words: Key words: convolutional neural networks, deep learning, fire detection

ZHANG Miao, LI Pu, YANG Yi, SONG Wen-hua. Image fire detection algorithms based on object detection convolutional neural networks[J]. Fire Science and Technology, 2022, 41(6): 807-811.

[1]	Fan Xiaoyong, Zou Kaiyu, Xie Jia, Lu Shouxiang. Research on the concentration characteristics of thermal decomposition particles and optimization of detection parameters of insulation materials for distribution cabinets [J]. Fire Science and Technology, 2026, 45(8): 7-15.
[2]	Zhang Zhonghua, Liu Jiang, Liu Lei, Wu Ke, Zhang Tianhang. A deep learning framework for real-time reconstruction of tunnel fire temperature fields： model design and deployment [J]. Fire Science and Technology, 2026, 45(6): 79-89.
[3]	Li Pu, Zhang Miao. Image fire detection algorithms evaluation methods based on image complexity [J]. Fire Science and Technology, 2026, 45(5): 87-93.
[4]	Wang Luyao, Bu Zonghao, Liu Quanyi, Wang Haibin. Study of the effect of low air pressure on the multi-wavelength optical properties of aerosols [J]. Fire Science and Technology, 2026, 45(4): 175-181.
[5]	Xu Baoyou, Zheng Xiaodong, Huo Yinuo. Research on early fire detection technology for high-rack storage based on visible light and thermal infrared fusion [J]. Fire Science and Technology, 2026, 45(1): 144-148.
[6]	Fu Teng, Wang Junsheng, Cheng Yanying6, Wang Yuzhong,. Advances in fire detection technologies: From conventional alarm systems to latent period monitoring and early warning [J]. Fire Science and Technology, 2025, 44(9): 1176-1183.
[7]	Yu Chunyu, Li Xiaoxu, Li Boning, Zhang Xi. Research on small target flame image detection algorithm based on improved YOLOv8 [J]. Fire Science and Technology, 2025, 44(9): 1274-1280.
[8]	Li Xiaoxu, Zhang Xi, Yu Chunyu, Li Boning. Enhancement method for synthetic samples of large-span space fire based on improved CycleGAN [J]. Fire Science and Technology, 2025, 44(9): 1281-1286.
[9]	Wang Wei. A brief analysis on the current application status and development trends of fire detection technology in public buildings [J]. Fire Science and Technology, 2025, 44(8): 1146-1151.
[10]	Ji Changqing, Cao Siyu, Li Yanzhi, Wang Zumin. Research on the influencing factors of helicopter firefighting capability in forest aviation [J]. Fire Science and Technology, 2025, 44(6): 839-845.
[11]	Zhao Pengcheng, Qin Haodong, Zhang Ying, Zhang Ke. A detection method of safety equipment for personnel in fire operation under deep learning [J]. Fire Science and Technology, 2025, 44(4): 541-547.
[12]	He Zhaoyu, Wang Li, Wang Zhuofu. Analysis of energy consumption characteristics of narrowband cellular IoT communications for independent fire detection and alarm [J]. Fire Science and Technology, 2025, 44(3): 375-381.
[13]	Jiang Li, He Tingquan, Guo Xin, Yang Dong1. Fire source location and heat release rate inversion in tunnel fires based on deep learning [J]. Fire Science and Technology, 2024, 43(9): 1292-1297.
[14]	Zhang Xinqi, Shi Jihao, Chen Guoming. Prediction of hydrogen jet diffusion based on physics-informed deep learning [J]. Fire Science and Technology, 2024, 43(5): 698-703.
[15]	Chen Qingdian, Zhong Chen, Liu Hui, Wang Xiaohui. Research and improvement of fire detection method for historical buildings based on FireNet [J]. Fire Science and Technology, 2024, 43(2): 183-188.

Image fire detection algorithms based on object detection convolutional neural networks

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics

Comments