| 1,852 | 8 | 1259 |
| 下载次数 | 被引频次 | 阅读次数 |
基于深度学习的车辆检测方法近年来取得了显著进展，深度学习模型的引入使得车辆检测在精度和效率方面取得了巨大的提升。针对车辆检测的难点进行了归纳概述；重点综述了目前应用于不同场景和其他因素影响下的基于深度学习的车辆检测方法，包括基于区域方法、基于单阶段方法和基于注意力机制方法等，对每种方法进行了整理介绍，分析所能解决的问题；对主流的车辆开源数据集和车辆检测的评价指标进行了介绍；对车辆检测算法已解决的问题和待改进的难点分别进行了总结；对后续的相关研究方向进行了展望，包括引入多模态信息、跨时空车辆检测等方面。将进一步推动基于深度学习的车辆检测技术的发展，使其在实际应用中发挥更大的作用。
Abstract：Detection methods based on deep learning have made significant research progress in recent years. The introduction of deep learning models has made vehicle detection greatly improved in terms of accuracy and efficiency. This study reviews the research progress of vehicle detection methods based on deep learning. Firstly, the difficulties of vehicle detection are introduced and summarized. Then, it focuses on the current deep learning-based vehicle detection methods applied in different scenarios as well as those under the influence of other factors, including region-based methods, single-phase-based methods, and attention mechanism-based methods, and briefly introduces each method and analyzes the problems they can solve; it also presents the mainstream vehicle open source datasets and evaluation metrics for vehicle detection; Finally, the solved problems and difficulties to be improved of vehicle detection algorithm are summarized respectively, and future research directions are prospected, including the introduction of multimodal information, cross-temporal and spatial vehicle detection and other aspects of the research. These studies will further promote the development of deep learning-based vehicle detection technologies, making it play a greater role in practical applications.
[1] CHUN L Z,DIAN L,ZHI J Y,et al.YOLOv3:Face Detection in Complex Environments[J].International Journal of Computational Intelligence Systems,2020,13(1):1153-1160.
[2] DENG Z R,YANG R,LAN R S,et al.SE-IYOLOV3:An Accurate Small Scale Face Detector for Outdoor Security[J].Mathematics,2020,8(1):93.
[3] SHARIF M,AMIN J,SIDDIQA A,et al.Recognition of Diffe-rent Types of Leukocytes Using YOLOv2 and Optimized Bag-of-features[J].IEEE Access,2020,8:167448-167459.
[4] DI TOMMASO A,BETTI A,FONTANELLI G,et al.A Multi-stage Model Based on YOLOv3 for Defect Detection in PV Panels Based on IR and Visible Imaging by Unmanned Aerial Vehicle[J].Renewable Energy,2022,193:941-962.
[5] SHARIF M I,LI J P,AMIN J,et al.An Improved Framework for Brain Tumor Analysis Using MRI Based on YOLOv2 and Convolutional Neural Network[J].Complex & Intelligent Systems,2021,7(4):1-14.
[6] 孔令军，王茜雯，包云超，等.一种基于深度学习的臂丛神经超声图像分割网络[J].无线电工程，2021,51(9):841-847.
[7] ABAS S M,ABDULAZEEZ A M.Detection and Classification of Leukocytes in Leukemia Using YOLOv2 with CNN[J].Asian Journal of Research in Computer Science,2021:64-75.
[8] REDMON J,DIVVALA S,GIRSHICK R,et al.You Only Look Once:Unified,Real-time Object Detection[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas:IEEE,2016:779-788.
[9] LIU W,ANGUELOV D,ERHAN D,et al.SSD:Single Shot Multibox Detector[C]//Computer Vision-ECCV 2016:14th European Conference.Amsterdam:Springer,2016:21-37.
[10] LIN T Y,GOYAL P,GIRSHICK R,et al.Focal Loss for Dense Object Detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2020,42(2):318-327.
[11] GIRSHICK R,DONAHUE J,DARRELL T,et al.Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation[C]//2014 IEEE Conference on Computer Vision and Pattern Recognition.Columbus:IEEE,2014:580-587.
[12] GIRSHICK R.Fast R-CNN[C]//2015 IEEE International Conference on Computer Vision.Boston:IEEE,2015:1440-1448.
[13] 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.
[14] HE K M,GKIOXARI G,DOLLáR P,et al.Mask R-CNN[C]//2017 IEEE International Conference on Computer Vision.Honolulu:IEEE,2017:2980-2988.
[15] DODIA A,KUMAR S.A Comparison of YOLO Based Vehicle Detection Algorithms[C]//2023 International Conference on Artificial Intelligence and Applications (ICAIA) Alliance Technology Conference (ATCON-1).Bangalore:IEEE,2023:1-6.
[16] REDMON J,FARHADI A.YOLOv3:An Incremental Improvement[EB/OL].(2018-04-08)[2024-03-10].https://arxiv.org/abs/1804.02767.
[17] JUNG H K,CHOI G S.Improved YOLOv5:Efficient Object Detection Using Drone Images Under Various Conditions[J].Applied Sciences,2022,12(14):7255.
[18] WANG C Y,BOCHKOVSKIY A,LIAO H Y M.YOLOv7:Trainable Bag-of-freebies Sets New State-of-the-art for Real-time Object Detectors[C]//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Vancouver:IEEE,2023:7464-7475.
[19] 罗江宏，袁梓麒，易志雄.基于改进的YOLOv5城市道路车辆行人检测方法[J].电子制作，2023,31(19):67-72.
[20] 朱联祥，徐莉娟.基于改进YOLOv3-tiny的车辆目标检测[J].信息技术与信息化，2022(3):9-12.
[21] ALSANABANI A A,SAEED S A,AL-MKHLAFI M,et al.A Low Cost and Real Time Vehicle Detection Using Enhanced YOLOv4-Tiny[C]//2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA).Dalian:IEEE,2021:372-377.
[22] 张利丰，田莹.改进YOLOv8的多尺度轻量型车辆目标检测算法[J].计算机工程与应用，2024,60(3):129-137.
[23] LI H L,LI J,WEI H B,et al.Slim-neck By GSConv:A Better Design Paradigm of Detector Architectures for Autonomous Vehicles[EB/OL].(2022-06-06)[2024-03-10].https://arxiv.org/abs/2206.02424.
[24] YANG L X,ZHANG R Y,LI L D,et al.SimAM:A Simple,Parameter-free Attention Module for Convolutional Neural Networks[C]//International Conference on Machine Learning.Vienna:PMLR,2021:11863-11874.
[25] TONG Z J,CHEN Y H,XU Z W,et al.Wise-IoU:Bounding Box Regression Loss with Dynamic Focusing Mechanism[EB/OL].(2023-01-24)[2024-03-15].https://arxiv.org/abs/2301.10051.
[26] KULKARNI A P,BALIGAR V P.Real Time Vehicle Detection,Tracking and Counting Using Raspberry-Pi[C]//2020 2nd International Conference on Innovative Mechanisms for Industry Applications (ICIMIA).Bangalore:IEEE,2020:603-607.
[27] KALYAN S S,PRATYUSHA V,NISHITHA N,et al.Vehicle Detection Using Image Processing[C]//2020 IEEE International Conference for Innovation in Technology (INOCON).Bangaluru:IEEE,2020:1-5.
[28] ABROUGUI A,HAYOUNI M.Convolutional Neural Network for Vehicle Detection in a Captured Image[C]//2022 International Wireless Communications and Mobile Computing (IWCMC).Dubrovnik:IEEE,2022:1166-1171.
[29] 李颀，叶小敏，冯文斌.融合毫米波雷达与机器视觉的雾天车辆检测[J].液晶与显示，2023,38(10):1445-1454.
[30] 苏彤，王颖，邓启扬，等.基于YOLOv5改进的雾天行人与车辆检测算法[J].系统仿真学报，2024,36(10):2413-2422.
[31] WANG D,ZHOU Y,WU L,et al.Research on Vehicle Detection Algorithm Based on Convolutional Neural Network and Combining Color and Depth Images[C]//2019 2nd International Conference on Information Systems and Computer Aided Education (ICISCAE).Dalian:IEEE,2019:274-277.
[32] WU R T,CHOWDHURY Z,SANCHEZ G V,et al.Real-time Vehicle Detection System for Intelligent Transportation Using Machine Learning[C]//2022 IEEE Green Energy and Smart System Systems (IGESSC).Long Beach:IEEE,2022:1-6.
[33] ZHANG S Q,TONG Y L.Nighttime Vehicle Detection Algorithm Enhanced by NightvisionGAN[C]//2023 4th International Conference on Computer Vision,Image and Deep Learning (CVIDL).Zhuhai:IEEE,2023:672-676.
[34] XU Y Q,CHU K B,ZHANG J.Nighttime Vehicle Detection Algorithm Based on Improved Faster-RCNN[J].IEEE Access,2024,12:19299-19306.
[35] SHAN Z Y,TIAN H Y.A Real-time Vehicle Detection Algorithm Based on Instance Segmentation[C]//2021 IEEE 2nd International Conference on Big Data,Artificial Intelligence and Internet of Things Engineering (ICBAIE).Nanchang:IEEE,2021:239-243.
[36] LAW H,DENG J.CornerNet:Detecting Objects as Paired Keypoints[C]//Computer Vision-ECCV 2018:15th European Conference.Munich:Springer,2018:642-656.
[37] SHI F R,ZHANG T,ZHANG T.Orientation-aware Vehicle Detection in Aerial Images via an Anchor-free Object Detection Approach[J].IEEE Transactions on Geoscience and Remote Sensing,2020,59(6):5221-5233.
[38] LI J X,ZHANG Z L,TIAN Y,et al.Target-guided Feature Super-resolution for Vehicle Detection in Remote Sensing Images[J].IEEE Geoscience and Remote Sensing Letters,2021,19:1-5.
[39] LIU S,ZHANG L,LU H C,et al.Center-boundary Dual Attention for Oriented Object Detection in Remote Sensing Images[J].IEEE Transactions on Geoscience and Remote Sensing,2021,60:1-14.
[40] DUAN K W,BAI S,XIE L X,et al.CenterNet:Keypoint Triplets for Object Detection[C]//2019 IEEE/CVF International Conference on Computer Vision.Seoul:IEEE,2019:6568-6577.
[41] LIU S J Y,ZHUANG Y,DONG H,et al.Adaptive Local Context Embedding for Small Vehicle Detection from Ae-rial Optical Remote Sensing Images[C]//IGARSS 2022-2022 IEEE International Geoscience and Remote Sensing Symposium.Kuala Lumpur:IEEE,2022:1712-1715.
[42] ZHU H G,CHEN X G,DAI W Q,et al.Orientation Robust Object Detection in Aerial Images Using Deep Convolutional Neural Network[C]//2015 IEEE International Conference on Image Processing(ICIP).Quebec City:IEEE,2015:3735-3739.
[43] RAZAKARIVONY S,JURIE F.Vehicle Detection in Aerial Imagery:A Small Target Detection Benchmark[J].Journal of Visual Communication and Image Representation,2016,34:187-203.
[44] HUANG W X,DONG C J,OU K T,et al.Vehicle Detection Method in UAV Images Based on Improved ObjectBox[C]//2023 IEEE 6th International Conference on Pattern Recognition and Artificial Intelligence (PRAI).Haikou:IEEE,2023:306-310.
[45] ZAND M,ETEMAD A,GREENSPAN M.ObjectBox:From Centers to Boxes for Anchor-free Object Detection[EB/OL].(2022-07-14)[2024-03-10].https://arxiv.org/abs/2207.06985.
[46] MENG Y Y,WEI J L,HUO J Y.Research on Multi-lane Vehicle Target Detection in Complex Scene[C]//2023 IEEE 11th Joint International Information Technology and Artificial Intelligence Conference (ITAIC).Changqing:IEEE,2023,11:868-872.
[47] 范江霞，张文豪，张丽丽，等.改进YOLOv5的无人机影像车辆检测方法[J].遥感信息，2023,38(3):114-121.
[48] ZHANG H,ZHANG S C.A YOLOv5s-SE Model for Object Detection in X-ray Security Images[C]//2021 International Conference on Control,Automation and Information Sciences (ICCAIS).Xi'an:IEEE,2021:626-631.
[49] COBB M,REISMAN M,KILLAM P,et al.Wide-area Motion Imagery Vehicle Detection in Adverse Conditions[C]∥2023 IEEE Applied Imagery Pattern Recognition Workshop (AIPR).St.Louis:IEEE,2023:1-6.
[50] 李洪兴.被低估的广域运动图像系统[J].现代军事，2017(3):12.
[51] HE K J,ZHANG L.Vehicle Detection in Satellite Images with Deep Neural Networks and Vehicle Shape Features[C]//2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS.Brussels:IEEE,2021:4212-4215.
[52] 宋庆钰.基于特征抗干扰与尺度上下文的车辆检测与计数研究[D].南宁：广西大学，2023.
[53] 曲海成，王蒙，柴蕊.双向多尺度特征融合的高效遥感图像车辆检测[J/OL].计算机工程与应用，1-13[2024-03-28].https:∥kns.cnki.net/kcms2/article/abstract?v=r_P-ES8duRq_v6HvUBAaoqcqMHY4BqEFTyFuwIXBpiVlBSxfLKm41jg0Z4cc0oHs04ZPbdC82JrqT6DvL9b6JtBbMICI51chMfxmpjp4gCZsZGGw5ZY4VXTUOX6btk3G6QX2vrQYcKe9Dtnrn5tg_EmYS4xUq7kx&uniplatform=NZKPT&language=CHS&version=LYDG.
[54] 孙营，王波涛.基于可变形部件改进模型的夜间车辆检测方法[J].计算机工程，2019,45(3):202-206.
[55] 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.
[56] 游丽萍，贝绍轶.结合可变形卷积和注意力机制的目标跟踪方法[J].科技与创新，2024(1):31-34.
[57] 陈琼红，冀杰，种一帆，等.基于AOD-Net和SSD的雾天车辆和行人检测[J].重庆理工大学学报(自然科学),2021,35(5):108-117.
[58] 洪毕辉，李文彬，朱炜，等.基于改进的YOLOv3-SPP算法目标检测研究[J].兵器装备工程学报，2023,44(4):268-274.
[59] YAO X K,ZHANG Y C,YAO Y K,et al.Traffic Vehicle Detection Algorithm Based on YOLOv3[C]//2021 International Conference on Intelligent Transportation,Big Data & Smart City (ICITBS).Xi'an:IEEE,2021:47-50.
[60] 杨云坤，孙秀珍，向鹏程.改进的yolov5车辆行人检测方法在云南高速公路的应用[J].中国交通信息化，2023(11):92-95.
[61] 穆柯楠，王会峰，杨澜，等.基于多尺度边缘融合及 SURF 特征匹配的车辆检测及跟踪方法[J].交通信息与安全，2018,36(6):65-73.
[62] 丁飞，米冠宇，童恩，等.多通路高分辨率网络与注意力机制融合的车辆检测模型[J].汽车安全与节能学报，2022,13(1):122-130.
[63] 冯汝怡，李志斌，吴启范，等.航拍视频车辆检测目标关联与时空轨迹匹配[J].交通信息与安全，2021,39(2):61-69.
[64] 张浩，董锴龙，高尚兵，等.融合非临近跳连与多尺度残差结构的小目标车辆检测[J].中国图象图形学报，2023,28(12):3797-3809.
[65] 李畅，王一丁，孙芮，等.引入全局上下文模块和高效注意力机制的车辆跟踪算法[J].科学技术与工程，2022,22(11):4424-4433.
[66] 高铭阳，王风春，王菲，等.基于视频流信息融合的高速公路重点车辆检测与定位方法[J].中国交通信息化，2023(增刊1):255-256.
[67] 杨榆樟，王碧珺，梁洪健，等.基于Pony边缘检测算法的隧道车辆识别研究[J/OL].武汉理工大学学报(交通科学与工程版),1-14[2024-03-06].http://kns.cnki.net/kcms/detail/42.1824.U.20230718.1037.004.html.
[68] 徐达.高速公路隧道安全预警技术研究[D].杭州：杭州电子科技大学，2023.
[69] WANG H,CAI Y F,CHEN X B,et al.Night-time Vehicle Sensing in Far Infrared Image with Deep Learning[J].Journal of Sensors,2016,2016(1):3403451.
[70] LU Y F,YANG Q F,HAN J X,et al.A Robust Vehicle Detection Method in Thermal Images Based on Deep Learning[C]//2021 IEEE International Conference on Power,Intelligent Computing and Systems(ICPICS).Shenyang:IEEE,2021:386-390.
[71] 李涵宇.基于改进YOLO的车辆检测研究及车位检测系统的实现[D].长春：吉林大学，2022.
[72] 李东昌.基于无人机的地面停车场中目标车辆搜索系统的设计与实现[D].济南：山东大学，2022.
[73] CHEN R.Vehicle Target Detection in Special Parkinglot Based on Feature Clustering[C]//2021 7th International Symposium on Mechatronics and Industrial Informatics (ISMII).Zhuhai:IEEE,2021:240-245.
[74] LI Y,QI H Z,DAI J F,et al.Fully Convolutional Instance-aware Semantic Segmentation[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition.Honolulu:IEEE,2017:4438-4446.
[75] LI H C,XIONG P F,FAN H Q,et al.DFANet:Deep Feature Aggregation for Real-time Semantic Segmentation[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Long Beach:IEEE,2019:9514-9528.
[76] WANG Y,ZHOU Q,LIU J,et al.Lednet:A Lightweight Encoder-Decoder Network for Real-time Semantic Segmentation[C]//2019 IEEE International Conference on Image Processing(ICIP).Taipei:IEEE,2019:1860-1864.
[77] REN H,MANIVANNAN N,LEE G C,et al.Improving OCT B-scan of Interest Inference Performance Using TensorRT Based Neural Network Optimization[J].Investigative Ophthalmology & Visual Science,2020,61(7):1635.
[78] WEN L Y,DU D W,CAI Z W,et al.UA-DETRAC:A New Benchmark and Protocol for Multi-object Detection and Tracking[J].Computer Vision and Image Understanding,2020,193:102907.
[79] DU D W,QI Y K,YU H Y,et al.The Unmanned Aerial Vehicle Benchmark:Object Detection and Tracking[C]//15th European Conference on Computer Vision (ECCV).Munich:Springer,2018:375-391.
[80] YU F,XIAN W Q,CHEN Y Y,et al.BDD100K:A Diverse Driving Video Database with Scalable Annotation Tooling[EB/OL].(2018-05-12)[2024-03-10].https://arxiv.org/abs/1805.04687v1.
[81] GEIGER A,LENZ P,STILLER C,et al.The KITTI Vision Benchmark Suite[EB/OL].[2024-03-11].https://www.cvlibs.net/datasets/kitti/eval_object.php.
[82] YANG L J,LUO P,LOY C C,et al.A Large-scale Car Dataset for Fine-grained Categorization and Verification[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition.Boston:IEEE,2015:3973-3981.
[83] LIU X C,LIU W,MEI T,et al.A Deep Learning-based Approach to Progressive Vehicle Re-identification for Urban Surveillance[C]//14th European Conference.Amsterdam:Springer,2016:869-884.
[84] BOCHKOVSKIY A,WANG C Y,LIAO H Y M.YOLOv4:Optimal Speed and Accuracy of Object Detection[EB/OL].(2020-04-23)[2024-03-11].https://arxiv.org/abs/2004.10934.
基本信息:
中图分类号:U495;TP391.41;TP18
引用信息:
[1]游昊,吕文涛,叶丹,等.基于深度学习的车辆检测方法研究进展[J].无线电工程,2025,55(02):230-245.
基金信息:
国家自然科学基金(U1709219,61601410); 浙江省科技厅重点研发计划项目(2022C01079,2024C01060)~~
2024-09-18
2024-09-18
2024-09-18