深度学习中的单阶段车辆检测算法综述

doi:10.3778/j.issn.1002-8331.2110-0307

摘要/Abstract

摘要： 随着深度学习的发展，基于深度学习的车辆检测算法性能不断被提升，在构建智能交通体系方面发挥重要作用。单阶段目标检测模型因其检测速度的优越性，被广泛应用于车辆实时检测。为了综合分析基于深度学习的单阶段车辆检测算法相关改进及应用，分别对比了各类常用单阶段车辆检测算法，列举其改进措施以及在车辆检测方面存在的问题；重点阐述了基于常见单阶段车辆检测算法针对现有问题采取的相关改进以及应用领域；简要介绍了车辆检测相关数据集，对现阶段车辆检测中亟待解决的问题与难点进行了分析，提出了车辆检测未来的研究方向。

关键词: 深度学习, 车辆检测, 单阶段目标检测

Abstract: With the development of deep learning, the performance of vehicle detection algorithm based on deep learning is continuously improved and plays an important role in building intelligent transportation system. One-stage target detection model is widely used in real-time vehicle detection in video stream due to its advantages in detection speed. In order to analyze the relevant improvements and applications of one-stage vehicle detection algorithm based on deep learning comprehensively, various common one-stage vehicle detection algorithms are compared by listing their improvements and problems left to be solved in vehicle detection, and then emphatically describes the relevant improvements and application fields of vehicle algorithm based on common one-stage framework. Finally, the data sets of vehicle detection are introduced briefly, the problems and difficulties to be solved in vehicle detection at the present stage are analyzed, and the feature research direction is put forward.

Key words: deep learning, vehicle detection, one-stage target detection

杨锦帆, 王晓强, 林浩, 李雷孝, 杨艳艳, 李科岑, 高静. 深度学习中的单阶段车辆检测算法综述[J]. 计算机工程与应用, 2022, 58(7): 55-67.

YANG Jinfan, WANG Xiaoqiang, LIN Hao, LI Leixiao, YANG Yanyan, LI Kecen, GAO Jing. Review of One-Stage Vehicle Detection Algorithms Based on Deep Learning[J]. Computer Engineering and Applications, 2022, 58(7): 55-67.

参考文献

[1] CAO X，WU C，YAN P，et al.Linear SVM classification using boosting HOG features for vehicle detection in low-altitude airborne videos[C]//Proceedings of the 18th IEEE International Conference on Image Processing，2011：2421-2424.
[2] VOLA P，JONES M.Rapid object detection using a boosted cascade of simple features[C]//Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition，2001.
[3] WANG X，HAN T X，YAN S.An HOG-LBP human detector with partial occlusion handling[C]//Proceedings of the IEEE 12th International Conference on Computer Vision，2009：32-39.
[4] HONG Z.A preliminary study on artificial neural network[C]//Proceedings of the 6th IEEE Joint International Information Technology and Artificial Intelligence Conference，2011：336-338.
[5] KAZEMI F M，SAMADI S，POORREZA H R，et al.Vehicle recognition using curvelet transform and SVM[C]//Proceedings of the 4th International Conference on Information Technology，2007：516-521.
[6] WU S，NAGAHASHI H.Parameterized AdaBoost：Introducing a parameter to speed up the training of real AdaBoost[J].IEEE Signal Processing Letters，2014，21（6）：687-691.
[7] 李明熹，林正奎，曲毅.计算机视觉下的车辆目标检测算法综述[J].计算机工程与应用，2019，55（24）：20-28.
LI M X，LIN Z K，QU Y.Survey of vehicle object detection algorithm in computer vision[J].Computer Engineering and Applications，2019，55（24）：20-28.
[8] TSAI D，LAI S.Independent component analysis-based background subtraction for indoor surveillance[J].IEEE Transactions on Image Processing，2009，18（1）：158-167.
[9] LEE D S.Effective gaussian mixture learning for video background subtraction[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2005，27（5）：827-832.
[10] MERLIN P M，FARBER D J.A parallel mechanism for detecting curves in pictures[J].IEEE Transactions on Computers，1975，24（1）：96-98.
[11] BERTHOLD K.P.HORN，BRIAN G.SCHUNCK.Deter mining optical flow[J].Artificial Intelligence，1981，17（1/3）：185-203.
[12] VIOLA P，JONES M.Rapid object detection using a boosted cascade of simple features[C]//Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition，2001.
[13] FELZENSZWALB P F，GIRSHICK R B，MCALLESTER D，et al.Object detection with discriminatively trained part-based models[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2010，32（9）：1627-1645.
[14] NIE X，GAO Y，GAO F，et al.A novel vision based road detection algorithm for intelligent vehicle[C]//Proceedings of the IEEE International Conference on Power，Intelligent Computing and Systems（ICPICS），2019：504-507.
[15] MAYA P，THARINI C.Performance analysis of lane detection algorithm using partial Hough transform[C]//Proceedings of the 21st International Arab Conference on Information Technology（ACIT），2020：1-4.
[16] 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 Recognition（CVPR），2016：779-788.
[17] REDMON J，FARHADI A.YOLO9000：Better，faster，stronger[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition（CVPR），2017：6517-6525.
[18] REDMON J，FARHADI A.YOLOv3：An incremental improvement[J].arXiv：1804.02767，2018.
[19] BOCHKOVSKIY A，WANG C Y，LIAO H Y.YOLOv4：Optimal speed and accuracy of object detection[J].arXiv：2004.10934，2020.
[20] LIU W，ANGUELOV D，ERHAN D，et al.SSD：Single shot multibox detector[J].arXiv：1512.02325，2015.
[21] FU C Y，LIU W，RANGA ANANTH，et al.DSSD：Deconvolutional single shot detector[J].arXiv：1701.06659，2017.
[22] JISOO J，HYOGIN P，NOJUN K.Enhancement of SSD by concatenating feature maps for object detection[J].arXiv：1705.09587，2017.
[23] SHEN Z，LIU Z，LI J，et al.DSOD：Learning deeply supervised object detectors from scratch[C]//Proceedings of the IEEE International Conference on Computer Vision（ICCV），2017：1937-1945.
[24] LI Z X，ZHOU F Q.FSSD：Feature fusion single shot multibox detector[J].arXiv：1712.00960，2017.
[25] LIN T，GOYAL P，GIRSHICK R，et al.Focal loss for dense object detection[C]//Proceedings of the IEEE International Conference on Computer Vision（ICCV），2017：2999-3007.
[26] ZHANG S，WEN L，BIAN X，et al.Single-shot refinement neural network for object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2018：4203-4212.
[27] ZHOU X Y，WANG D，KRAHENBUHL P.Objects as points[J].arXiv：1904.07850，2019.
[28] HEI L，TENG Y，OLGA R，et al.CornerNet-Lite：Efficient keypoint based object detection[J].arXiv：1904.08900，2019.
[29] TIAN Z，JIN Y，CAO H，et al.Real-time vehicle detection under complex road conditions[C]//Proceedings of the 2nd International Conference on Industrial Artificial Intelligence（IAI），2020：1-4.
[30] 刘肯，何姣姣，张永平，等.改进YOLO的车辆检测算法[J].现代电子技术，2019，42（13）：47-50.
LIU K，HE J J，ZHANG Y P，et al.Improved YOLO vehicle detection algorithm[J].Modern Electronics Technique，2019，42（13）：47-50.
[31] CHOI J，CHUN D，KIM H，et al.Gaussian YOLOv3：An accurate and fast object detector using localization uncertainty for autonomous driving[C]//Proceedings of the IEEE/CVFIEEE International Conference on Computer Vision（ICCV），2019：502-511.
[32] XU C J，YE Q，LIU J X，et al.Research on vehicle detection based on YOLOv3[C]//Proceedings of the 2nd International Conference on Information Technology and Computer Application（ITCA），2020：433-436.
[33] 袁小平，马绪起，刘赛.改进YOLOv3的行人车辆目标检测算法[J].科学技术与工程，2021，21（8）：3192-3198.
YUAN X P，MA X Q，LIU S.An improved algorithm of pedestrian and vehicle detection based on YOLOv3[J].Science Technology and Engineering，2021，21（8）：3192-3198.
[34] 谢俊章，彭辉，唐健峰.改进YOLOv4的密集遥感目标检测[J].计算机工程与应用，2021，57（22）：247-256.
XIE J Z，PENG H，TANG J F.Improved YOLOv4’s dense remote sensing target detection[J].Computer Engineering and Applications，2021，57（22）：247-256.
[35] Do T H，TRAN D，.HOANG D Q，et al.A novel algorithm for estimating fast-moving vehicle speed in intelligent transport systems[C]//Proceedings of International Conference on Information Networking（ICOIN），2021：499-503.
[36] 金宇尘，罗娜.结合多尺度特征的改进YOLOv2车辆实时检测算法[J].计算机工程与设计，2019，40（5）：1457-1463.
JIN Y C，LUO N.Improved YOLOv2 vehicle real-time detection algorithm combined with multi-scale features[J].Computer Engineering and Design，2019，40（5）：1467-1463.
[37] RHMAN Z，AMI A M，ULLAH M A.A real-time wrong-way vehicle detection based on YOLO and centroid tracking[C]//Proceedings of IEEE Region 10 Symposium（TENSYMP），202：916-920.
[38] 顾恭，徐旭东.改进YOLOv3的车辆实时检测与信息识别技术[J].计算机工程与应用，2020，56（22）：173-184.
GU G，XU X D.Real-time vehicle detection and information recognition technology based on YOLOv3 improved algorithm[J].Computer Engineering and Applications，2020，56（22）：173-184.
[39] YONETSU S，IWAMOTO Y，CHEN Y W.Two-stage YOLOv2 for accurate license-plate detection in complex scenes[C]//Proceedings of IEEE International Conference on Consumer Electronics（ICCE），2019：1-4.
[40] WANG Z，LI L，LI L，et al.Object detection algorithm based on improved YOLOv3-tiny network in traffic scenes[C]//Proceedings of the 4th CAA International Conference on Vehicular Control and Intelligence（CVCI），2020：514-518.
[41] DU S，ZHANG P，ZHANG B，et al.Weak and occluded vehicle detection in complex infrared environment based on improved YOLOv4[J].IEEE Access，2021，9：25671-25680.
[42] CAI Y，LUAN T，GAO H，et al.YOLOv4-5D：An effective and efficient object detector for autonomous driving[J].IEEE Transactions on Instrumentation and Measurement，2021，70：1-13.
[43] HU X，WEI Z，ZHOU W.A video streaming vehicle detection algorithm based on YOLOv4[C]//Proceedings of the IEEE 5th Advanced Information Technology，Electronic and Automation Control Conference（IAEAC），2021：2081-2086.
[44] 张宝朋，康谦泽，李佳萌.轻量化改进的YOLOv4目标检测算法[J/OL].计算机工程：1-13[2021-11-05].https：//doi.org/10.19678/j.issn.1000-3428.0062216.
ZHANG B P，KANG Q Z，LI J M.Light improved YOLOv4 target detection algorithm[J/OL].Computer Engineering：1-13[2021-11-05].https：//doi.org/10.19678/j.issn.1000-3428.0062216.
[45] WANG C，WANG H，YU F，et al.A high-precision fast smoky vehicle detection method based on improved YOLOv5 network[C]//Proceedings of the IEEE International Conference on Artificial Intelligence and Industrial Design（AIID），2021：255-259.
[46] 张成标，童宝宏，程进，等.改进的Yolo_v2违章车辆检测方法[J].计算机工程与应用，2020，56（20）：104-110.
ZHANG C B，TONG B H，CHENG J，et al.Improved Yolo_v2 illegal vehicle detection method[J].Computer Engineering and Applications，2020，56（20）：104-110.
[47] 李珣，时斌斌，刘洋，等.基于改进YOLOv2模型的多目标识别方法[J].激光与光电子学进展，2020，57（10）：113-122.
LI X，SHI B B，LIU Y，et al.Multi-target recognition method based on improved YOLOv2 model[J].Laser and Optoelectronics Progress，2020，57（10）：113-122.
[48] 朱茂桃，邢浩，方瑞华.基于YOLO-TridentNet的车辆检测方法[J].重庆理工大学学报（自然科学），2020，34（11）：1-8.
ZHU M T，XING H，FANG R H.Vehicle detection based on YOLO-TridentNet[J].Journal of Chongqing University of Technology（Natural Science），2020，34（11）：1-8.
[49] XIAO D，SHAN F，LI Z，et al.A target detection model based on improved tiny-Yolov3 under the environment of mining truck[J].IEEE Access，2019，7：123757-123764.
[50] CHEN S，LIN W.Embedded system real-time vehicle detection based on improved YOLO network[C]//Proceedings of the IEEE 3rd Advanced Information Management，Communicates，Electronic and Automation Control Conference（IMCEC），2019：1400-1403.
[51] SINDHU V S.Vehicle identification from traffic video surveillance using YOLOv4[C]//Proceedings of the 5th International Conference on Intelligent Computing and Control Systems（ICICCS），2021：1768-1775.
[52] ALSANABANI A A，SAEED S A，AL-MKHLAFI M，et al.A low cost and real time vehicle detection using enhanced YOLOv4-tiny[C]//Proceedings of the IEEE International Conference on Artificial Intelligence and Computer Applications（ICAICA），2021：372-377.
[53] GUO X Y.Target detection of forward vehicle based on improved SSD[C]//Proceedings of the IEEE 6th International Conference on Cloud Computing and Big Data Analytics（ICCCBDA），2021：466-468.
[54] 李国进，胡洁，艾矫燕.基于改进SSD算法的车辆检测[J].计算机工程，2022，48（1）：266-274.
LI G J，HU J，AI J Y.Vehicle detection based on improved SSD algorithm[J].Computer Engineering，2022，48（1）：266-274.
[55] 徐浩，杨德刚，蒋倩倩，等.基于SSD的轻量级车辆检测网络改进[J/OL].计算机工程与应用：1-10（2021-03-31）[2021-09-07].http：//kns.cnki.net/kcms/detail/11.2127.TP. 20210331.
0930.002.html.
XU H，YANG D G，JIANG Q Q，et al.Improvement of lightweight vehicle detection network based on SSD[J/OL].Computer Engineering and Applications：1-10（2021-03-31）[2021?09?07].http：//kns.cnki.net/kcms/detail/11.2127.TP.
20210331.0930.002.html.
[56] 乔延婷，陈万培，张涛.基于SSD的轻量级车辆检测网络[J].无线电工程，2020，50（11）：926-931.
QIAO Y T，CHEN W P，ZHANG T.A lightweight vehicle detection network based on SSD[J].Radio Engineering，2020，50（11）：926-931.
[57] 杨艳红，钟宝江，徐云龙.改进的SSD算法在智慧交通中的应用[J/OL].电讯技术：1-8[2021-11-06].http：//kns.cnki.net/kcms/detail/51.1267.TN.20210531.1441.002.html.
YANG Y H，ZHONG B J，XU Y L.Application of improved SSD algorithm in intelligent transportation[J/OL].Telecommunication Engineering：1-8[2021-11-06].http：//kns.cnki.net/kcms/detail/51.1267.TN.20210531.1441.002.html.
[58] 宋世奇，李旭，祝雪芬，等.基于改进SSD的航拍城市道路车辆检测方法[J].传感器与微系统，2021，40（1）：114-117.
SONG S Q，LI X，ZHU X F，et al.Urban road vehicle detetion method by aerial photography based on improved SSD[J].Transducer and Miscrosystem Technologies，2021，40（1）：114-117.
[59] RAJ M，CHANDAN S.Pedestrian and vehicle detection using night-vision camera through CNN on Indian roads[C]//Proceedings of the International Conference on Advances in Computing，Communication Control and Networking（ICACCCN），2018：1136-1142.
[60] PIAO Z，ZHAO B，TANG L，et al.VDetor：An effective and efficient neural network for vehicle detection in aerial image[C]//Proceedings of the IEEE International Conference on Signal，Information and Data Processing（ICSIDP），2019：1-4.
[61] 杨帆，吴韶波.基于SSD的目标车辆检测算法研究[J].物联网技术，2021，11（6）：19-22.
YANG F，WU S B.Research on target vehicle detection algorithm based on SSD[J].Internet of Things Technology，2021，11（6）：19-22.
[62] KITVIMONRAT A，WATCHARABUTSARAKHAM S.Vehicle manufacturer recognition（VMR） using SSD model[C]//Proceedings of the 18th International Conference on Electrical Engineering/Electronics，Computer，Telecommunications and Information Technology（ECTI-CON），2021：724-727.
[63] LI H，YUAN J，LIU H，et al.Incremental learning of infrared vehicle detection method based on SSD[C]//Proceedings of the IEEE 20th International Conference on Communication Technology（ICCT），2020：1423-1426.
[64] SAINI P，BIDHAN K，MALHOTRA S.A detection system for stolen vehicles using vehicle attributes with deep learning[C]//Proceedings of the 5th International Conference on Signal Processing，Computing and Control（ISPCC），2019：251-254.
[65] CHEN K，SHOU T D，LI J K，et al.Vehicles detection on expressway via deep learning：Single shot multibox object detector[C]//Proceedings of the International Conference on Machine Learning and Cybernetics（ICMLC），2018：467-473.
[66] 张炳力，秦浩然，江尚，等.基于RetinaNet及优化损失函数的夜间车辆检测方法[J].汽车工程，2021，43（8）：1195-1202.
ZHANG B L，QIN H R，JIANG S，et al.A method of vehicle detection at night based on RetinaNet and optimized loss functions[J].Automotive Engineering，2021，43（8）：1195-1202.
[67] 刘革，郑叶龙，赵美蓉.基于RetinaNet改进的车辆信息检测[J].计算机应用，2020，40（3）：854-858.
LIU G，ZHENG Y L，ZHAO M R.Vehicle information detection based on improved RetinaNet[J].Journal of Computer Applications，2020，40（3）：854-858.
[68] LI Y，CHEN Y，WANG N，et al.Scale-aware trident networks for object detection[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision（ICCV），2019：6053-6062.
[69] 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.
[70] 梁礼明，熊文，彭仁杰，等.基于中心点的多类别车辆检测算法[J].科学技术与工程，2021，21（7）：2767-2772.
LIANG L M，XIONG W，PENG R J，et al.Center-based algorithm for multi-class vehicle detection[J].Science Technology and Engineering，2021，21（7）：2767-2772.
[71] 宋欢欢，惠飞，景首才，等.改进的RetinaNet模型的车辆目标检测[J].计算机工程与应用，2019，55（13）：225-230.
SONG H H，HUI F，JING S C，et al.Improved RetinaNet model for vehicle target detection[J].Computer Engineering and Applications，2019，55（13）：225-230.
[72] 荣亮，高清维，李笑语，等.RefineDet网络与注意力机制结合的目标检测算法[J].传感器与微系统，2021，40（3）：130-133.
RONG L，GAO Q W，LI X Y，et al.Target detection algorithm combining RefineDet network and attention mechanism[J].Transducer and Microsystem Technologies，2021，40（3）：130-133.
[73] 梁礼明，熊文，蓝智敏，等.改进的CornerNet-Saccade车辆检测算法[J].重庆理工大学学报（自然科学），2021，35（6）：137-146.
LIANG L M，XIONG W，LAN Z M，et al.Improved CornerNet-Saccade algorithm for vehicle detection[J].Journal of Chongqing University of Technology（Natural Science），2021，35（6）：137-146.
[74] 易诗，周思尧，沈练，等.基于增强型轻量级网络的车载热成像目标检测方法[J].红外技术，2021，43（3）：237-245.
YI S，ZHOU S Y，SHEN L，et al.Vehicle-based thermal imaging target detection method based on enhanced lightweight network[J].Infrared Technology，2021，43（3）：237-245.
[75] 魏玮，杨茹，朱叶.改进CenterNet的遥感图像目标检测[J].计算机工程与应用，2021，57（6）：191-199.
WEI W，YANG R，SONG Y.Target detection of improved CenterNet to remote sensing images[J].Computer Engineering and Applications，2021，57（6）：191-199.
[76] TAFAZZOLI F，FRIGUI H，NISHIYAMA K.A large and diverse dataset for improved vehicle make and model recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops（CVPRW），2017：874-881.
[77] XIA G S，BAI X，DING J，et al.DOTA：A large-scale dataset for object detection in aerial images[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2018：3974-3983.
[78] ALSANABANI A A，AHMED M A，AL SMADI A M.Vehicle counting using detecting-tracking combinations：A comparative analysis[C]//Proceedings of the 4th International Conference on Video and Image Processing，2020：48-54.
[79] DONG Z，PEI M，HE Y，et al.Vehicle type classification using unsupervised convolutional neural network[C]//Proceedings of the 22nd International Conference on Pattern Recognition，2014：172-177.