基于路侧监控的车型分类算法研究
Research on Vehicle Classification Algorithm Based on Road Side Monitoring
DOI: 10.12677/CSA.2022.124113, PDF,    科研立项经费支持
作者: 余 波：济南金衢公路勘察设计研究有限公司，山东 济南；杨 博, 李 健：华北科技学院，河北 廊坊；田 岩：华中科技大学，湖北 武汉
关键词: 车辆检测；车型分类；监控视频；Vehicle Detection； Vehicle Classification； Surveillance Video
摘要: 交通场景中车辆的检测和分类是发展智能交通的应有之义。本文基于利旧的原则，利用路侧交通监控视频数据，设计改进的YOLOv3深度学习网络模型，使用残差单元以保证卷积神经网络收敛损失，算法采取多尺度特征融合预测的策略，直接在多个尺度的特征图上回归预测车辆边界框和类型，实现车辆的目标快速检测和车型判定。将改进前后的模型在测试集中进行测试，实验结果表明本文提出的深度学习网络在实际交通场景中既满足实时性的要求，又具有良好的车型检测和分类效果。
Abstract: The detection and classification of vehicles in traffic scenes is an essential part of the development of intelligent transportation. In this paper, based on the principle of benefiting the old, an improved deep learning network is proposed to realize the detection of vehicles and the determination of vehicle models by using the road measurement traffic surveillance video. Experimental results show that the proposed deep learning network has good detection and classification effects in real traffic scenes.
文章引用：余波, 杨博, 李健, 田岩. 基于路侧监控的车型分类算法研究[J]. 计算机科学与应用, 2022, 12(4): 1099-1107. https://doi.org/10.12677/CSA.2022.124113

参考文献

[1] 郝兴伟. 基于车速传感器的雷达测速仪检定装置[D]: [硕士学位论文]. 长春: 吉林大学, 2014.
[2] 曹林, 李佳, 张鑫怡, 王东峰, 付冲. 一种基于微波雷达回波信号的车型分类方法[J]. 电讯技术, 2020, 60(5): 542-548.
[3] 周博, 马戎, 李岁劳, 等. 基于多普勒的车辆测速仪[J]. 机械与电子, 2014(2): 70-73.
[4] 蔡常青, 孙桥, 张跃, 等. 机动车激光测速仪校准技术的研究[J]. 计量学报, 2008, 29(4): 339-343.
[5] 叶青, 刘剑雄, 刘铮, 陈众, 李靓. 基于电磁感应的道路车辆车型在线分类方法研究[J]. 湖南大学学报(自然科学版), 2019, 46(12): 41-49.
[6] 王树欣, 伍湘彬. 地感线圈在交通控制领域中的应用[J]. 电子世界, 2005(8): 48.
[7] 石鑫, 赵池航, 林盛梅, 李彦伟, 薛善光, 钱子晨. 基于深度学习网络模型的车辆类型识别方法研究[J]. 筑路机械与施工机械化, 2020, 37(4): 67-73+78.
[8] 晏世武, 罗金良, 严庆. 基于卷积神经网络车型分类的研究[J]. 智能计算机与应用, 2020, 10(1): 67-70.
[9] 吕磊, 李文彬, 王晓鸣, 胡隆基. 基于深度卷积神经网络的小样本车型分类方法[J]. 兵器装备工程学报, 2020, 41(8): 193-200+221.
[10] 杜青, 苗艳华, 沈花玉. 基于机器视觉的车型自动分类算法设计[J]. 电子测试, 2019(1): 56-58.
[11] Lipton, A., Fujiyoshi, H. and Patil, R. (1998) Moving Target Classification and Tracking from Real-Time Video. Proceedings of the 1998 DAPA Image Understanding Workshop (IUW’98), Princeton, 19-21 October 1998, 8-14.
[12] Stauffer, C. and Grimson, W.E.L. (1999) Adaptive Background Mixture Models for Re-al-Time Tracking. IEEE Computer Society Conference on Computer Vision & Pattern Recognition, Vol. 2, 246-252.
[13] Barnich, O. and Droogenbroeck, M.V. (2009) ViBE: A Powerful Random Technique to Estimate the Background in Video Sequences. 2009 IEEE International Conference on Acoustics, Speech and Signal Processing, Taipei, 19-24 April 2009, 945-948. [Google Scholar] [CrossRef] 
[14] Viola, P. and Jones, M. (2001) Rapid Object Detection Using a Boosted Cascade of Simple Features. Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Volume 2, 511.
[15] Dalal, N. and Triggs, B. (2005) Histograms of Oriented Gradients for Human Detection. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Diego, 20-25 June 2005, 886-893.
[16] Szegedy, C., Toshev, A. and Erhan, D. (2013) Deep Neural Networks for Object Detection. Proceedings of the 26th International Conference on Neural Information Pro-cessing Systems, Volume 2, 2553-2561.
[17] 吴乐平, 窦祥星. 基于CNN的车辆目标检测与车型分类研究[J]. 电子测试, 2021(6): 37-39.
[18] Girshick, R., Donahue, J., Darrell, T., et al. (2014) Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, 23-28 June 2014, 580-587. [Google Scholar] [CrossRef] 
[19] Girshick, R. (2015) Fast R-CNN. 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, 7-13 December 2015, 1440-1448. [Google Scholar] [CrossRef] 
[20] Ren, S., He, K., Girshick, R., et al. (2015) Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. Proceedings of the 28th International Conference on Neural Information Processing Systems, Volume 1, 91-99.
[21] 李大湘, 王小雨, 刘颖. 监控视频中的车型分类方法[J]. 西安邮电大学学报, 2018, 23(4): 40-47.
[22] Dai, J., Li, Y., He, K., et al. (2016) R-FCN: Object Detection via Region-Based Fully Convolutional Networks. Proceedings of the 30th International Conference on Neural Infor-mation Processing Systems, Barcelona, 5-10 December 2016, 379-387.
[23] Redmon, J., Divvala, S., Girshick, R., et al. (2016) You Only Look Once: Unified, Real-Time Object Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, 27-30 June 2016, 779-788. [Google Scholar] [CrossRef] 
[24] Redmon, J. and Farhadi, A. (2017) YOLO9000: Better, Faster, Stronger. IEEE Conference on Computer Vision & Pattern Recognition, Honolulu, 21-26 July 2017, 6517-6525. [Google Scholar] [CrossRef] 
[25] Redmon, J. and Farhadi, A. (2018) YOLOv3: An Incremental Im-provement.
[26] Liu, W., Anguelov, D., Erhan, D., et al. (2016) SSD: Single Shot MultiBox Detector. European Con-ference on Computer Vision, Amsterdam, 11-14 October 2016, 21-37. [Google Scholar] [CrossRef] 
[27] Fu, C.Y., Liu, W., Ranga, A., et al. (2017) DSSD: Deconvolu-tional Single Shot Detector.
[28] Hartigan, J.A. and Wong, M.A. (1979) Algorithm AS 136: A K-Means Clustering Algorithm. Journal of the Royal Statistical Society, 28, 100-108. [Google Scholar] [CrossRef]