Driver’s Mobile Phone Usage Detection Model：Optimizing Yolov5n Algorithm

doi:10.3778/j.issn.1002-8331.2205-0553

Abstract

Abstract: In order to further realize the real-time detection of mobile phone usage violations on mobile devices or embedded devices, this paper proposes a lightweight, high-precision and real-time detection model by optimizing Yolov5n algorithm. Firstly, Focal-EIoU Loss and FocalL1 Loss are combined to obtain more accurate frame positioning and faster convergence of loss function. Secondly, the slimming pruning algorithm is used to further improve the lightweight and computational efficiency of the model. During the fine-tuning of the model, the data augmentation technology is used to guide the fine-tuning operation, so as to improve the performance of the model. Finally, the improved methods is used to perform ablation experiments on the mobile phone dataset to further verify the effectiveness of the detection model. Experiments show that the detection accuracy of the optimized model on the mobile phone usage dataset and Pascal VOC 2012 dataset is improved by 0.2 and 12.3 percentage points respectively, the parameter quantity is reduced by 44.4%, and the calculation amount is reduced by 45.2% and 40% respectively, which is conducive to the further real-time detection of the model on mobile devices and embedded devices.

Key words: Yolov5n algorithm optimization, Slimming pruning, Focal-EIoU Loss, FocalL1 Loss, data augmentation

摘要： 为进一步实现在移动设备或嵌入式设备上对手机使用的违法行为进行实时检测，通过优化Yolov5n算法提出了一种轻量化、高精度、实时性的检测模型。将Focal-EIoU Loss与FocalL1 Loss相结合来获得更加精确的框定位以及损失函数的更快收敛。利用Slimming剪枝算法来进一步提高模型的轻量化及计算效率。在模型微调时利用数据增强技术对微调操作进行指导，从而使模型能够获得更好的性能提升。在手机使用数据集上对改进方法进行消融实验，进一步验证检测模型的有效性。实验表明，优化后的模型在手机使用数据集及Pascal VOC 2012数据集上的检测精度分别提高了0.2、12.3个百分点，参数量减少44.4%，计算量分别减小45.2%、40%，有利于模型进一步在移动设备及嵌入式设备上的实时性检测。

关键词: Yolov5n算法优化, Slimming剪枝, Focal-EIoU Loss, FocalL1 Loss, 数据增强

WANG Xinpeng, WANG Xiaoqiang, LIN Hao, LI Leixiao, LI Kecen, TAO Yihao. Driver’s Mobile Phone Usage Detection Model：Optimizing Yolov5n Algorithm[J]. Computer Engineering and Applications, 2023, 59(18): 129-136.

王鑫鹏, 王晓强, 林浩, 李雷孝, 李科岑, 陶乙豪. 驾驶员手机使用检测模型：优化Yolov5n算法[J]. 计算机工程与应用, 2023, 59(18): 129-136.

References

[1] 魏民国.基于机器视觉的驾驶人使用手持电话行为检测方法[D].北京：清华大学，2014.
WEI M G.Detection method of handheld phone use by driver based on machine vision[D].Beijing：Tsinghua University，2014.
[2] 张波，王文军，魏民国，等.基于机器视觉的驾驶人使用手持电话行为检测[J].吉林大学学报（工学版），2015，45（5）：1688-1695.
ZHANG B，WANG W J，WEI M G，et al.Detection handheld phone use by driver based on machine vision[J].Journal of Jilin University（Engineering and Technology Edition），2015，45（5）：1688-1695.
[3] 王丹.基于机器视觉的驾驶员打电话行为检测[D].北京：北京理工大学，2015.
WANG D.Detecting driver use of mobile phone based on computer vision[D].Beijing：Beijing Institute of Technology，2015.
[4] 骆文婕.基于机器视觉的非安全驾驶行为检测算法研究[D].长沙：湖南大学，2018.
LUO W J.Research on the detection algorithm of non-safe driving behavior based on machine vision[D].Changsha：Hunan University，2018.
[5] 王尽如.基于半监督支持向量机的驾驶员打电话行为检测[D].长沙：湖南大学，2018.
WANG J R.Driver cell phone usage detection based on semi-supervised support vector machine[D].Changsha：Hunan University，2018.
[6] RAO X，LIN F，CHEN Z，et al.Distracted driving recognition method based on deep convolutional neural network[J].Journal of Ambient Intelligence and Humanized Computing，2021，12（1）：193-200.
[7] LIU S，MURESAN R，AL-DWEIK A.Leveraging deep learning for inattentive driving behavior with in-vehicle cameras[C]//2020 International Symposium on Networks，Computers and Communications（ISNCC），2020：1-6.
[8] JIN C，ZHU Z，BAI Y，et al.A Deep-learning-based scheme for detecting driver cell-phone use[J].IEEE Access，2020，8：18580-18589.
[9] XIONG Q，LIN J，YUE W，et al.A deep learning approach to driver distraction detection of using mobile phone[C]//2019 IEEE Vehicle Power and Propulsion Conference（VPPC），2019：1-5.
[10] MAO P，ZHANG K，LIANG D.Driver distraction behavior detection method based on deep learning[C]//IOP Conference Series：Materials Science and Engineering，2020.
[11] LIU S，WANG X，WANG L，et al.Abnormal behavior analysis strategy of bus drivers based on deep learning[C]//2021 IEEE 10th Data Driven Control and Learning Systems Conference（DDCLS），2021：1522-1527.
[12] 秦丹峰，尹相辉，龚学余.基于改进YOLOv4-Tiny算法的移动端实时司机违章行为检测[J].计算机科学与应用，2021，11（5）：1291-1300.
QIN D F，YIN X H，GONG X Y.Real-time drivers’ violation detection on mobile terminal based on improved YOLOv4-Tiny[J].Computer Science and Application，2021，11（5）：1291-1300.
[13] RobinReni.Driver behavior dataset[EB/OL].[2021-10-12].https：//www.kaggle.com/datasets/robinreni/revitsone-5class.
[14] ZHANG Y F，REN W，ZHANG Z，et al.Focal and efficient IOU loss for accurate bounding box regression[J].arXiv：2101.08158，2021.
[15] LIU Z，LI J，SHEN Z，et al.Learning efficient convolutional networks through network slimming[C]//Proceedings of the IEEE International Conference on Computer Vision，2017：2736-2744.
[16] HAN K，WANG Y，TIAN Q，et al.Ghostnet：more features from cheap operations[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2020：1580-1589.
[17] HOWARD A，SANDLER M，CHU G，et al.Searching for mobilenetv3[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision，2019：1314-1324.
[18] MA N，ZHANG X，ZHENG H T，et al.Shufflenet v2：practical guidelines for efficient CNN architecture design[C]//Proceedings of the European Conference on Computer Vision，2018：116-131.
[19] Make Ml.Road signs dataset[EB/OL].[2022-07-10].https：//makeml.app/datasets/road-signs.