Abstract
In order to reduce the number of traffic accidents caused by violations, violations are detected, and drivers or passengers who violate regulations are warned and punished to encourage them to comply with traffic rules. Traditional methods for violation detecting in complex environments have low detection accuracy and poor adaptability to the environment. In response to these problems, the YOLOv5s network model is improved. The SPP module is replaced by the ghostSPPF module to reduce the number of model parameters, the CBS module in the backbone network is replaced by the MP2 module to upgrade the channel dimensionality, the C3 structure is replaced by the C2f structure, and the BCEwithlogitsloss loss function is replaced by the QFocalLoss loss function. The improved network model has been used to detect the violation of drivers using mobile phones while driving. The mAP of the improved YOLOv5s network model can reach 93.02%, which is higher than the mAP of 91.37% of the original YOLOv5s network model. The detection frame rate of the improved YOLOv5s network model can reach 87.33FPS, which can meet the needs of real-time traffic violation detection.
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
Xun, C.: Automatic Container Code Recognition Based on Deep Learning. Changchun University of Science and Technology (2020). https://doi.org/10.26977/d.cnki.gccgc.2020.000084
Liu, S., Gu, Y., Rao, W., et al.: Illegal vehicle detection method based on optimized YOLOv3 algorithm. J. Chongqing Univ. Technol. (Nat. Sci.) 35(04), 135–141 (2021)
Pan, W., Luo, Y.: Vehicle target detection based on improved YOLOV3. Comput. Appl. Softw. 40(01), 167–172, 204 (2023)
Shi, J.-w., Yang, L.-q., Fang, Y.-h., et al.: Helmet wearing detection method based on Improved YOLOv4. Comput. Eng. Des. 44(02), 518–525 (2023). https://doi.org/10.16208/j.issn1000-7024.2023.02.027
Li, J., Ge, Y., Liu, Y.-p.: Traffic sign recognition for dim small targets based on improved YOLOv5. Computer Systems & Applications, pp. 1–8 (2023). https://doi.org/10.15888/j.cnki.csa.009056
Zhao, M., Yu, H., Li, H.-q., et al.: Detection of fish stocks by fused with SKNet and YOLOv5 deep learning. J. Dalian Ocean Univ. 37(02), 312–319 (2022). https://doi.org/10.16535/j.cnki.dlhyxb.2021-324
Deng, T., Tan, S., Pu, L.: Traffic light recognition method based on improved YOLOv5s. Comput. Eng. 48(09), 55–62 (2022). https://doi.org/10.19678/j.issn.1000-3428.0062843
Long, S., Song, X., Zhang, S., et al.: Research on vehicle detection in aerial images with improved YOLOv5s. Laser J. 43(10), 22–29 (2022). https://doi.org/10.14016/j.cnki.jgzz.2022.10.022
Jiang, C., Zhang, H., Zhang, E., et al.: Pedestrian and vehicle target detection algorithm based on improved YOLOv5s. J. Yangzhou Univ. (Nat. Sci. Ed.) 25(06), 45–49 (2022). https://doi.org/10.19411/j.1007-824x.2022.06.008
Chen, Z., Qi, H., Wang, X.: Research on mask wearing detection based on improved YOLOv5 algorithm. Electron. Des. Eng. 30(22), 67–72 (2022). https://doi.org/10.14022/j.issn1674-6236.2022.22.014
Yang, X.-l., Cai, Y.-w.: Pedestrian detection system based on YOLOV5S and its implementation. Comput. Inf. Technol. 30(01), 28–30 (2022). https://doi.org/10.19414/j.cnki.1005-1228.2022.01.006
Wang, L., Duan, J., Xin, L.: YOLOv5 helmet wear detection method with introduction of attention mechanism. Comput. Eng. Appl. 58(09), 303–312 (2022)
Huang, Y., Liu, H., Chen, Q., et al.: Transmission line insulator fault detection method based on USRNet and improved YOLOv5x. High-Voltage Technol. 48(09), 3437–3446 (2022). https://doi.org/10.13336/j.1003-6520.hve.20220314
Wang, L., He, M.-t., Xu, S., et al.: Garbage classification and detection based on YOLOv5s network. Packag. Eng. 42(08), 50–56 (2021). https://doi.org/10.19554/j.cnki.1001-3563.2021.08.007
Gu, Y., Cao, M., Xiu, J., et al.: Algorithm for detecting violations based on YOLOv4 network. J. Chongqing Univ. Technol. (Nat. Sci.) 35(08), 114–121 (2021)
Gao, W., Shan, M., Song, N., et al.: Detection of microaneurysms in fundus images based on improved YOLOv4 with SENet embedded. J. Biomed. Eng. 39(04), 713–720 (2022)
Qi, L., Gao, J.: Small object detection based on improved YOLOv7. Comput. Eng. 49(01), 41–48 (2023). https://doi.org/10.19678/j.issn.1000-3428.0065942
Wang, X.: An improved traffic sign recognition and detection on rainy environment based on YOLOv5. Mod. Inf. Technol. 6(20), 71–75, 80 (2022). https://doi.org/10.19850/j.cnki.2096-4706.2022.20.018
Ma, N., Cao, Y., Wang, Z., et al.: Landing runway detection algorithm based on YOLOv5 network architecture. Laser Optoelectron. Prog. 59(14), 199–205 (2022)
Feng, H., Huang, C., Wen, Y.: Remote sensing image small target detection based on improved YOLOv3. J. Comput. Appl. 42(12), 3723–3732 (2022)
Zhnag, R., Dong, f., Cheng, X.: Application of improved YOLOv5s algorithm in non-motorized helmet wearing detection. J. Henan Univ. Sci. Technol. (Nat. Sci.) 44(01), 44–53, 57 (2023). https://doi.org/10.15926/j.cnki.issn1672-6871.2023.01.007
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, S., Liang, Yc., Ma, Xc., Guo, Yq. (2023). Violation Detection Method Based on Improved YOLOv5s. In: Jia, Y., Zhang, W., Fu, Y., Wang, J. (eds) Proceedings of 2023 Chinese Intelligent Systems Conference. CISC 2023. Lecture Notes in Electrical Engineering, vol 1089. Springer, Singapore. https://doi.org/10.1007/978-981-99-6847-3_51
Download citation
DOI: https://doi.org/10.1007/978-981-99-6847-3_51
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-6846-6
Online ISBN: 978-981-99-6847-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)