Welcome to Francis Academic Press

Academic Journal of Computing & Information Science, 2022, 5(3); doi: 10.25236/AJCIS.2022.050304.

YOLOv5-based fatigue state detection method

Author(s)

Hekai Zhang1, Sichao Cheng2

Corresponding Author:
Hekai Zhang
Affiliation(s)

1School of Electronic Engineering, Heilongjiang University, Harbin, Heilongjiang, 150080, China

2School of Electronic Information and Automation, Tianjin University of Science and Technology, Tianjin, 300457, China

Abstract

With the development of social economy and the continuous increase of car ownership in China, fatigue driving is one of the problems people need to focus on nowadays, however, most of the current fatigue state detection methods are affected by the problems of expensive, susceptible to the environment and complicated methods. In order to solve the above problems, this paper proposes a fatigue state detection method with YOLOv5m as the basic network model, which first enhances the original image and then improves the loss function. The experimental results show that the mean accuracy of this method can be as high as 95.6%, which is 4.13 percentage points higher than YOLOv4 and 6.2 percentage points higher than YOLOv3, and the model accuracy is as high as 98.27%, which is 4 and 5.2 percentage points higher than YOLOv4 and YOLOv3, respectively. The recall rate is 95.1%, which is 2 and 3.2 percentage points higher than YOLOv4 and YOLOv3, respectively. It proves the reliability and advantages of the method in this paper.

Keywords

fatigued driving, YOLOv5m, loss function.

Cite This Paper

Hekai Zhang, Sichao Cheng. YOLOv5-based fatigue state detection method. Academic Journal of Computing & Information Science (2022), Vol. 5, Issue 3: 28-34. https://doi.org/10.25236/AJCIS.2022.050304.

References

[1] Zhang Hui, Wang Kunfeng, Wang Feiyue. Progress and Prospects of Deep Learning in Target Vision Detection [J]. Journal of AutomationJournal, 2017, 43(08): 1289-1305. DOI: 10.16 383/

[2] Ma Qifeng. Research on military target detection technology based on deep learning [D]. North Central University, 2020. DOI: 10.27470/

[3] GIRSHICK R, DONAHUE J, DARRELL T, et al. Region-based convolutional networks for accurate object detection and segmentation [J]. IEEE transactions on pattern analysis and machine intelligence, 2015, 38(1): 142-158.

[4] GIRSHICK R, Fast R-CNN [C]//Proceedings of the IEEE international conference on computer vision, 2015: 1440-1448,

[5] REN S, HE K, GIRSHICK R, et al. Faster r-cnn: Towards real-time object detection with region proposal networks [J]. Advance in neural information processing systems, 2015, 28: 91-99.

[6] LIU W, ANGUELOV D, ERHAN D, et al, SSD: Single shot multibox detector [C] //European conference on computer vision, Springer, Cham, 2016: 21-37.

[7] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: Unified, real-time object detection [C] //Proceedings of the IEEE Conference on Computer Vision and Pattern Reconition, 2016: 779-788. 

[8] REDMON J, FARHADI A. YOLO9000: better, faster, stronger [C] //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 7263-7271.

[9] REDMON J, FARHADI A, Yolov3:an incremental improvement [C] //IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, 2018, 87(8): 101-104.

[10] BOCHKOVSKIY A, WANG C Y, LIAO H Y M. Yolov4: optional speed and accuracy of object detection [C] //IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, 2020, 57(5): 9-12

[11] RAMZAN M, HIKMAT U K, SHAHID A, et al. A survey on State-of-the-Art drowsiness detection techniques [J]. IEEE Access, 2019(7): 61904-61919.

[12] Huang J. C., Kuang W. T., Mao Kuan-Cheng. Research on fatigue driving detection based on key points of human face [J]. Journal of Nanjing Engineering College (Natural Science Edition), 2017, 15(04): 8-13. DOI: 10.13960.

[13] Yu Shuo, Li Hui, Gui Fangjun, Yang Yanqi, Lv Chenyang. Real-time detection algorithm of mask wearing based on YOLOv5 in complex scenes [J]. Computer Measurement and Control, 2021, 29(12): 188-194. DOI: 10.16526.

[14] Huang, Lin-Quan, Jiang, Liang-Wei, Gao, Xiao-Feng. Improved real-time video helmet wearing detection algorithm for YOLOv3 [J]. Modern Computing Computer, 2020(30): 32-38+43.

[15] ZHANG S J, GAO R, Research on Visual Image Processing of Mobile Robot Based on OpenCV [J]. Journal of Computer Science, 2017, 28(5): 255-275.

[16] Tan S.L., Beixiongbo, Lu Gonglin, Tan Xiaohu. Real-time detection of personnel mask wear based on YOLOv5 network model [J]. Laser Miscellany DOI:10.14016.

[17] JIANG B, LUO R, MAO J, et al. Acquisition of localization confidence for accurate object detection [C] //Proceedings of the European conference on computer vision (ECCV), 2018: 784-799.

[18] REZATOFIGHI H, TOSI N, GWAK J Y, et al, Generalized intersection over union: A metric and a loss for bounding box regression [C] //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2019: 658-666.

[19] ZHENG Z, WANG P, REN D, et al. Enhancing geometric factors in model learning and inference for object detection and instance segmentation [J]. IEEE Transactions on Cybernetics, 2021,26(8):1-13.

[20] FOMIN I S, BAKHSHIEV A V, GROMOSHINSKII D A. Study of using deep learning nets for mark detection in space docking control images [J]. Procedia Computer Science, 2017, 103: 59-66.