Abstract
Aiming at the requirement of all-weather smoke and fire emission environmental detection in coke plants, this paper proposes the YOLOv5s coke oven smoke and fire recognition algorithm with joint attention mechanism. The algorithm takes YOLOv5s as the base network and adds the attention mechanism module in BackBone to make the network pay more attention to important features and improve the accuracy of target detection; in addition, this paper adds light labels to solve the interference of strong lights on flame recognition based on smoke and fire labels, and solves the smoke and fire detection problem of day and night scenes by triage training and detection. Doing comparison experiments on the self-built dataset, the YOLOv5s model with the joint CBAM module works best. The experimental results show that compared with the original YOLOv5s model, the mAP value of smoke and fire recognition in daytime scenes is improved by 4.4%, and the mAP value of smoke and fire recognition in nighttime scenes is as high as 97.1%.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Shen, S., et al.: A fire identification method based on video image correlation. J. Saf. Environ. 7(6), 96–99 (2007)
Wang, J., Yu, W., Han, T.: Fire detection based on infrared video image. J. SJTU 42(12), 1979–1987 (2008)
Wu, X., et al.: Fire detection algorithm based on multi-feature fusion. J. Int. Syst. 10(2), 240–247 (2015)
Chen, H., et al.: Fire detection method based on UO-net model. J. JOU 29(4), 8–15 (2020)
Chen, P., Xiao, D., Liu, H.: Video fire detection algorithm based on deep learning. J. Combust. Sci. Technol. 27(6), 695–700 (2021)
Li, X., et al.: Lightweight fire detection method based on CNN in complex scenes. J. Pattern Recognit. Artif. Int. 34(5), 415–421 (2021)
Miao, C., Yang, L., Jiang, Y.: Video image fire detection method based on neural network. J. Comput. Inf. Technol. 2021(04), 71–74 (2021)
Sun, W., et al.: Efficient video fire detection algorithm based on motion features. J. Data. Acquis. Process. 36(6), 1276–1285 (2021)
Liu, T.: Research on the application of pyrotechnic detection method based on deep learning in straw burning ban. D. HU (2020)
Li, L., Cao, L.: Research on fireworks image detection in farmland based on improved SSD algorithm. J. Road Eng. 52(05), 783–789 (2022)
Zhu, Y., et al.: Fire smoke detection algorithm for lightweight network. J. Appl. Technol. 49(2), 1–7 (2022)
Bai, Y., Zhao, H., Liu, H.: Analysis and control measures of “smoke and fire” in 7.63m coke oven coal. J. Manag Technol. Entertain. 12, 294 (2013)
Tan, S., et al.: Real-time detection of mask wearing based on YOLOv5 network model. J. Laser 42(2), 147–150 (2021)
Lin, S., Chen, J., Huang, S.: Research on student behavior detection based on deep learning. J. Mult. Netw. Teach. 06, 237–240 (2022)
Chen, J., Li, L.: Video detection of illegal mining based on YOLOv5 neural network model. J. Water Conserv. Tech. Support 08, 61–63+119+124 (2021)
Zhou, Y., et al.: Research on target detection algorithm of mobile robot based on YOLOv5. J. Equip. Man. Tech. 08, 15–18 (2021)
Lu, S., Feng, J., Duan, P.: Review of video fire identification methods. J. Telecommun. Technol. 37(03), 179–184+200 (2013)
Cao, J., Qin, Y., Ji, X.: Review of fire detection algorithms based on video. J. Data Acquis. Process. 35(01), 35–52 (2020)
Anshul, G., Abhishek, S., Anuj, K.: Video fire and smoke based fire detection algorithms: a literature review. J. Fire Technol. 56 (2020)
Ma, L., et al.: Research on object detection algorithm based on YOLOv5s. J. Commnu. Knowl. Technol. 17(23), 100–103 (2021)
Chen, S., et al.: Research on fire detection based on YOLO neural network and machine vision. J. Technol. Inf. 03, 107–110 (2022)
Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132–7141 (2018)
Woo, S., Park, J., Lee, J.Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 3–19. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01234-2_1
Ren, H., Wang, X.: A review of attentional mechanisms. J. Comput. Appl. 41(S1), 1–6 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Liu, Y., Zhang, Y., Zhou, Y., Zhang, X. (2023). Joint Attention Mechanism of YOLOv5s for Coke Oven Smoke and Fire Recognition Algorithm. In: Zhang, H., et al. International Conference on Neural Computing for Advanced Applications. NCAA 2023. Communications in Computer and Information Science, vol 1870. Springer, Singapore. https://doi.org/10.1007/978-981-99-5847-4_12
Download citation
DOI: https://doi.org/10.1007/978-981-99-5847-4_12
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-5846-7
Online ISBN: 978-981-99-5847-4
eBook Packages: Computer ScienceComputer Science (R0)