Real‑time detection method of traffic information based on lightweight YOLOv4

doi:10.11772/j.issn.1001-9081.2021101849

Abstract

Abstract: Aiming at the problem of vehicle objection detection in daily road scenes， a real?time detection method of traffic information based on lightweight YOLOv4 （You Only Look Once version 4） was proposed. Firstly， a multi?scene and multi?period vehicle object dataset was constructed， which was preprocessed by K?means++ algorithm. Secondly， a lightweight YOLOv4 detection model was proposed， in which the backbone network was replaced by MobileNet?v3 to reduce the number of parameters of the model， and the depth separable convolution was introduced to replace the standard convolution in the original network. Finally， combined with label smoothing and annealing cosine algorithms， the activation function Leaky Rectified Linear Unit （LeakyReLU） was used to replace the original activation function in the shallow network of MobileNet?v3 in order to optimize the convergence effect of the model. Experimental results show that the lightweight YOLOv4 has the weight file of 56.4 MB， the detection rate of 85.6 FPS （Frames Per Second）， and the detection precision of 93.35%， verifying that the proposed method can provide the reference for the real?time traffic information detection and its applications in real road scenes.

Key words: object detection, deep learning, image processing, lightweight, YOLOv4 (You Only Look Once version 4)

摘要： 针对日常道路场景下的车辆目标检测问题，提出一种轻量化的YOLOv4交通信息实时检测方法。首先，制作了一个多场景、多时段的车辆目标数据集，并利用K-means++算法对数据集进行预处理；其次，提出轻量化YOLOv4检测模型，利用MobileNet?v3替换YOLOv4的主干网络，降低模型的参数量，并引入深度可分离卷积代替原网络中的标准卷积；最后，结合标签平滑和退火余弦算法，使用LeakyReLU激活函数代替MobileNet?v3浅层网络中原有的激活函数，从而优化模型的收敛效果。实验结果表明，轻量化YOLOv4的权值文件为56.4 MB，检测速率为85.6 FPS，检测精度为93.35%，表明所提方法可以为实际道路中的交通实时信息检测及其应用提供参考。

关键词: 目标检测, 深度学习, 图像处理, 轻量化, YOLOv4

CLC Number:

TP391.4

GUO Keyou, LI Xue, YANG Min. Real‑time detection method of traffic information based on lightweight YOLOv4[J]. Journal of Computer Applications, 2023, 43(1): 74-80.

郭克友, 李雪, 杨民. 基于轻量化YOLOv4的交通信息实时检测方法[J]. 《计算机应用》唯一官方网站, 2023, 43(1): 74-80.

References

1 KaewTrakulPONG P， BOWDEN R. An improved adaptive background mixture model for realtime tracking with shadow detection［M］// REMAGNINO P， JONES G A， PARAGIOS N， et al. Video?Based Surveillance Systems： Computer Vision and Distributed Processing. Boston： Springer， 2002：135-144. 10.1007/978-1-4615-0913-4_11
2 ZIVKOVIC Z， HEIJDEN F van der. Efficient adaptive density estimation per image pixel for the task of background subtraction［J］. Pattern Recognition Letters， 2006， 27（7）： 773-780. 10.1016/j.patrec.2005.11.005
3 GODBEHERE A， MATSUKAWA A， GOLDBERG K. Visual tracking of human visitors under variable?lighting conditions for a responsive audio art installation［C］// Proceedings of the 2012 American Control Conference. Piscataway： IEEE， 2012： 4305-4312. 10.1109/acc.2012.6315174
4 SCHARSTEIN D， SZELISKI R. A taxonomy and evaluation of dense two?frame stereo correspondence algorithms［J］. International Journal of Computer Vision， 2002， 47（1/2/3）： 7-42. 10.1023/a:1014573219977
5 BERGEN J R， BURT P J， HINGORANI R， et al. A three?frame algorithm for estimating two?component image motion［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 1992， 14（9）： 886-896. 10.1109/34.161348
6 BROX T， BRUHN A， PAPENBERG N， et al. High accuracy optical flow estimation based on a theory for warping［C］// Proceedings of the 2004 European Conference on Computer Vision， LNCS 3024. Berlin： Springer， 2004： 25-36.
7 王滢暄，宋焕生，梁浩翔，等. 基于改进的YOLOv4高速公路车辆目标检测研究［J］. 计算机工程与应用， 2021， 57（13）： 218-226. 10.3778/j.issn.1002-8331.2012-0581 WANG Y X， SONG H S， LIANG H X， et al. Highway vehicle object detection based on improved YOLOv4 method［J］. Computer Engineering and Applications， 2021， 57（13）： 218-226. 10.3778/j.issn.1002-8331.2012-0581
8 张慧，王坤峰，王飞跃. 深度学习在目标视觉检测中的应用进展与展望［J］. 自动化学报， 2017， 43（8）： 1289-1305. 10.16383/j.aas.2017.c160822 ZHANG H， WANG K F， WANG F Y. Advances and perspectives on applications of deep learning in visual object detection［J］. Acta Automatica Sinica， 2017， 43（8）： 1289-1305. 10.16383/j.aas.2017.c160822
9 GIRSHICK R， DONAHUE J， DARRELL T， et al. Rich feature hierarchies for accurate object detection and semantic segmentation［C］// Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2014：580-587. 10.1109/cvpr.2014.81
10 HE K M， ZHANG X Y， REN S Q， et al. Spatial pyramid pooling in deep convolutional networks for visual recognition［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2015， 37（9）： 1904-1916. 10.1109/tpami.2015.2389824
11 GIRSHICK R. Fast R?CNN［C］// Proceedings of the 2015 IEEE International Conference on Computer Vision. Piscataway： IEEE， 2015： 1440-1448. 10.1109/iccv.2015.169
12 REN S Q， HE K M， GIRSHICK R， et al. Faster R?CNN： towards real?time object detection with region proposal networks ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2017， 39（6）： 1137-1149. 10.1109/tpami.2016.2577031
13 LIU W， ANGUELOV D， ERHAN D， et al. SSD： single shot multiBox detector［C］// Proceedings of the 2016 European Conference， LNCS 9905. Cham： Springer， 2016： 21-37.
14 REDMON J， DIVVALA S， GIRSHICK R， et al. You only look once： unified， real?time object detection［C］// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2016： 779-788. 10.1109/cvpr.2016.91
15 REDMON J， FARHADI A. YOLO9000： better， faster， stronger［C］// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2017： 6517-6525. 10.1109/cvpr.2017.690
16 REDMON J， FARHADI A. YOLOv3： an incremental improvement［EB/OL］. （2018-04-18）［2021-10-12］.https：//arxiv.org/pdf/1804.02767.pdf. 10.1109/cvpr.2017.690
17 BOCHKOVSKIY A， WANG C Y， LIAO H Y M. YOLOv4： optimal speed and accuracy of object detection ［EB/OL］（2020-04-23）［2021-10-16］.https：//arxiv.org/pdf/2004.10934.pdf.
18 MacQUEEN J B. Some methods for classification and analysis of multivariate observations ［C/OL］// Proceedings of the 5th Berkeley Symposium on Mathematical Statistics and Probability， Volume 1： Statistics. ［2021-12-06］.https：//typeset.io/pdf/some-methods-for- classification-and-analysis-of-multivariate-4pswti19oz.pdf.
19 钟志峰，夏一帆，周冬平，等. 基于改进YOLOv4的轻量化目标检测算法［J］. 计算机应用， 2022， 42（7）： 2201?2209. ZHONG Z F， XIA Y F， ZHOU D P， et al. Lightweight object detection algorithm based on improved YOLOv4［J］. Journal of Computer Applications， 2022， 42（7）： 2201?2209.
20 LIU S， QI L， QIN H F， et al. Path aggregation network for instance segmentation［C］// Proceeding of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2018： 8759-8768. 10.1109/cvpr.2018.00913
21 叶子勋，张红英. YOLOv4口罩检测算法的轻量化改进［J］. 计算机工程与应用， 2021， 57（17）： 157-168. YE Z X， ZHANG H Y. Lightweight improvement of YOLOv4 mask detection algorithm［J］. Computer Engineering and Applications， 2021， 57（17）： 157-168.
22 邓若辰，彭程，边赟. 基于深度可分离卷积的指静脉识别算法［J］. 计算机应用， 2020， 40（S2）： 199-203. 10.11772/j.issn.1001-9081.2020030395 DENG R C， PENG C， BIAN Y. Finger vein recognition algorithm based on depthwise convolution［J］. Journal of Computer Applications， 2020， 40（S2）： 199-203. 10.11772/j.issn.1001-9081.2020030395
23 HOWARD A G， ZHU M L， CHEN B， et al. MobileNets： efficient convolutional neural networks for mobile vision applications［EB/OL］. （2017-04-17）［2021-10-12］.https：//arxiv.org/pdf/1704. 04861.pdf. 10.48550/arXiv.1704.04861
24 SANDLER M， HOWARD A， ZHU M L， et al. MobileNetV2： inverted residuals and linear bottlenecks ［C］// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2018： 4510-4520. 10.1109/cvpr.2018.00474
25 HOWARD A， SANDLER M， CHEN B， et al. Searching for MobileNetV3［C］// Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision. Piscataway： IEEE， 2019： 1314-1324. 10.1109/iccv.2019.00140
26 KAMIBABA R， KONISHI K， FUKADA Y， et al， et al. Next generation 650V CSTBTTM with improved SOA fabricated by an advanced thin wafer technology ［C］// Proceedings of the IEEE 27th International Symposium on Power Semiconductor Devices and ICs. Piscataway： IEEE， 2015：29-32. 10.1109/ispsd.2015.7123381
27 王帅，彭意兵，何顶新. 基于深度可分离卷积神经网络的关键词识别系统［J］. 微电子学与计算机， 2019， 36（9）： 103-108. WANG S， PENG Y B， HE N. Keywords spotting system based on deepwise separable convolutional neural network［J］. Microelectronics & Computer， 2019， 36（9）： 103-108.
28 李维刚，杨潮，蒋林，等. 基于改进YOLOv4算法的室内场景目标检测［J/OL］. 激光与光电子学进展. （2021-08-03）［2021-10-12］.https：//kns.cnki.net/kcms/detail/31.1690.TN.20210802.1726.044.html. LI W G， YANG C， JIANG L， et al. Indoor scene object detection based on improved YOLOv4 algorithm［J/OL］. Laser and Optoelectronics Progress. （2021-08-03）［2021-11-05］.https：//kns.cnki.net/kcms/detail/31.1690.TN.20210802.1726.044.html.

[1]	Kansong CHEN, Yuan ZHENG, Lijun XU, Zhouyu WANG, Zhe ZHANG, Fujuan YAO. ShuffaceNet： face recognition neural network based on ThetaMEX global pooling [J]. Journal of Computer Applications, 2023, 43(8): 2572-2580.
[2]	Yi WANG, Jie XIE, Jia CHENG, Liwei DOU. Review of object pose estimation in RGB images based on deep learning [J]. Journal of Computer Applications, 2023, 43(8): 2546-2555.
[3]	Shengwei DUAN, Xinyu CHENG, Haozhou WANG, Fei WANG. Dam surface disease detection algorithm based on improved YOLOv5 [J]. Journal of Computer Applications, 2023, 43(8): 2619-2629.
[4]	Xiaolin LI, Songjia YANG. Hybrid beamforming for multi-user mmWave relay networks using deep learning [J]. Journal of Computer Applications, 2023, 43(8): 2511-2516.
[5]	Junjian JIANG, Dawei LIU, Yifan LIU, Yougui REN, Zhibin ZHAO. Few-shot object detection algorithm based on Siamese network [J]. Journal of Computer Applications, 2023, 43(8): 2325-2329.
[6]	Xiang GUO, Wengang JIANG, Yuhang WANG. Encrypted traffic classification method based on improved Inception-ResNet [J]. Journal of Computer Applications, 2023, 43(8): 2471-2476.
[7]	Yumeng CUI, Jingya WANG, Xiaowen LIU, Shangyi YAN, Zhizhong TAO. General text classification model combining attention and cropping mechanism [J]. Journal of Computer Applications, 2023, 43(8): 2396-2405.
[8]	Kun ZHANG, Fengyu YANG, Fa ZHONG, Guangdong ZENG, Shijian ZHOU. Source code vulnerability detection based on hybrid code representation [J]. Journal of Computer Applications, 2023, 43(8): 2517-2526.
[9]	Libin CEN, Jingdong LI, Chunbo LIN, Xiaoling WANG. Approximate query processing approach based on deep autoregressive model [J]. Journal of Computer Applications, 2023, 43(7): 2034-2039.
[10]	Zhongyu LI, Haodong SUN, Jiao LI. Lightweight gesture recognition algorithm for basketball referee [J]. Journal of Computer Applications, 2023, 43(7): 2173-2181.
[11]	Yuxin TUO, Tao XUE. Joint triple extraction model combining pointer network and relational embedding [J]. Journal of Computer Applications, 2023, 43(7): 2116-2124.
[12]	Zhangjian JI, Ming ZHANG, Zilong WANG. High-precision object detection algorithm based on improved VarifocalNet [J]. Journal of Computer Applications, 2023, 43(7): 2147-2154.
[13]	Min LIANG, Jiayi LIU, Jie LI. Image super-resolution reconstruction method based on iterative feedback and attention mechanism [J]. Journal of Computer Applications, 2023, 43(7): 2280-2287.
[14]	Jing ZHOU, Yiyu HU, Chengyu HU, Tianjiang WANG. Weakly perceived object detection method based on point cloud completion and multi-resolution Transformer [J]. Journal of Computer Applications, 2023, 43(7): 2155-2165.
[15]	Kunpei YE, Xi XIONG, Zhe DING. Recruitment recommendation model based on field fusion and time weight [J]. Journal of Computer Applications, 2023, 43(7): 2133-2139.