Research on the Application of YOLO Object Detection Algorithm 
in Autonomous Driving Scenarios

doi:10.16638/j.cnki.1671-7988.2025.006.011

Abstract

Abstract: With the rapid development of autonomous driving technology, accurate and efficient object detection has become a key research direction in environmental perception technology. The you only look once (YOLO) series algorithm, as a single-stage algorithm, has shown great potential not only in autonomous driving, but also widely applied in various fields. This article first summarizes the object detection algorithms based on deep learning and reviews the development history of YOLO algorithm; afterwards, the commonly used evaluation indicators in the field of object detection are outlined, and the application of YOLOv1 to YOLOv10 algorithms in autonomous driving scenarios is discussed, with a focus on analyzing the application of YOLO algorithm in traffic sign, vehicle and pedestrian, road surface status, and lane lines detection; finally,looks forward to the development trends and potential optimization directions of YOLO detection algorithm in the field of autonomous driving in the future.

Key words: autonomous driving; object detection; YOLO algorithm; deep learning

摘要： 随着自动驾驶技术的迅速发展，准确高效的目标检测已成为环境感知技术中的关键研究方向。YOLO 系列算法作为一种单阶段算法，不仅在自动驾驶中展现了巨大的潜力，还被广泛应用于各个领域。文章首先总结了基于深度学习的目标检测算法，并回顾了 YOLO 算法的发展历程；然后，概述了目标检测领域常用的评估指标，并讨论了 YOLOv1 至 YOLOv10 算法在自动驾驶场景中的应用，重点分析了 YOLO 算法在交通标志、车辆与行人、路面状态及车道线检测中的应用情况。最后，展望了 YOLO 检测算法在未来自动驾驶领域的发展趋势及潜在优化方向。

关键词: 自动驾驶；目标检测；YOLO 算法；深度学习

FANG Hongsu1 , CHANG Cheng1 , SHI Xinyu 2 , XIONG Runlian1 , HE Mentao1. Research on the Application of YOLO Object Detection Algorithm in Autonomous Driving Scenarios[J]. Automobile Applied Technology, 2025, 50(6): 65-74.

方虹苏 1，常城 1，石鑫雨 2，熊润莲 1，贺门涛 1. 自动驾驶场景中 YOLO 目标检测算法的应用研究[J]. 汽车实用技术, 2025, 50(6): 65-74.

References

[ 1 ] 段续庭,周宇康,田大新,等.深度学习在自动驾驶领域应用综述[J].无人系统技术,2021,4(6):1-27. [ 2 ] 黄兴驰,申彩英.基于深度学习的自动驾驶目标检测方法综述[J].现代车用动力,2023(1):1-4. [ 3 ] 茅智慧,朱佳利,吴鑫,等.基于 YOLO 的自动驾驶目标检测研究综述[J].计算机工程与应用,2022,58(15): 68-77. [ 4 ] 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. [ 5 ] 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. [ 6 ] REDMON J,FARHADI A.YOLOv3:An Incremental Improvement[EB/OL].(2018-04-08)[2024-08-30].https: //arxiv.org/pdf/1804.02767.pdf. [ 7 ] BOCHKOVSKIY A,WANG C Y,LIAO H Y M.YOLOv4:Optimal Speed and Accuracy of Object Detection [EB/OL].(2024-03-21)[2024-08-30].https://iv.org/pdf/ 2004.10934.pdf. [ 8 ] GE Z,LIU S,WANG F,et al.YOLOX:Exceeding YOLO Series in 2021[EB/OL].(2024-05-23)[2024-08-30]. https://arxiv/org/pdf/2107.08430.pdf. [ 9 ] LI C Y,LI L L,JIANG H L,et al.YOLOv6:A SingleStage Object Detection Framework for Industrial Applications[EB/OL].(2024-12-21)[2024-08-30].https: //arxiv. org/pdf/2209.02976.pdf. [10] WANG C Y,BOCHKOVSKIY A,LIAO H Y M. YOLOv7:Trainable Bag-of-Freebies Sets New State-of-theArt for Real-Time Object Detectors[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE,2023:7464-7475. [11] DILLON R,JORDAN K,JACQUELINE H,et al.RealTime Flying Object Detection with YOLOv8[EB/OL]. (2023-05-17)[2024-08-30].https://arxiv.org/pdf/2305. 09972.pdf. [12] WANG C Y,YEH I H,LIAO H Y M,et al.YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information[EB/OL].(2024-05-21)[2024- 08-30].https://arxiv.org/pdf/2402.13616.pdf. [13] WANG A,CHEN H,LIU L H,et al.YOLOv10:RealTime End-to-End Object Detection[EB/OL].(2024-05- 30)[2024-08-30].https://doi.org/10.48550/arXiv.2405. 14458. [14] 彭湃,耿可可,王子威,等.智能汽车环境感知方法综述 [J].机械工程学报,2023,59(20):281-303. [15] 邵延华,张铎,楚红雨,等.基于深度学习的 YOLO目标检测综述[J].电子与信息学报,2022,44(10):3697-3708. [16] LIU W,ANGUELOV D,ERHAN D,et al.SSD:Single Shot MultiBox Detector[C]//Proceedings of the IEEE Conference on Computer Vision in 2016.Piscataway: IEEE,2016:21-37. [17] GIRSHICK R.Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision in 2015.Piscataway:IEEE,2015:1440-1448. [18] TAN M,PANG R,LE Q V.EfficientDet:Scalable and Efficient Object Detection[C]//Proceedings of the IEEE/ CVF Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE,2020:10781-10790. [19] LIU Z,MAO H,WU C Y,et al.ConvNeXt:Revisiting Spatial Convolutions for Vision[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE,2022:4814-4824.[20] CARION N,MASSA F,SYNNAEVE G,et al.End-toEnd Object Detection with Transformers[EB/OL]. (2020-05-27)[2024-08-30].https://arxiv.org/pdf/2005. 12872. [21] ZHU X,SU W,LU L,et al.Deformable DETR: Deformable Transformers for End-to-End Object Detection [EB/OL].(2021-04-26)[2024-08-30].https://ar xiv.org/ pdf/2010.04159. [22] DAI L,LIU G,HUANG L,et al.Feature Transfer Method for Infrared and Visible Image Fusion via Fuzzy Lifting Scheme[J].Infrared Physics & Technology, 2021,114:103621. [23] 郭璠,张泳祥,唐琎,等.YOLOv3-A:基于注意力机制的交通标志检测网络[J].通信学报,2021,42(1):87-99. [24] 罗玉涛,高强.基于通道注意力和特征增强的交通标志检测[J].华南理工大学学报(自然科学版),2023,51 (12):64-72. [25] 田鹏,毛力.改进 YOLOv8 的道路交通标志目标检测算法[J].计算机工程与应用,2024,60(8):202-212. [26] 熊恩杰,张荣芬,刘宇红,等.面向交通标志的 GhostYOLOv8 检测算法[J].计算机工程与应用,2023,59 (20):200-207. [27] 梁继然,陈壮,董国军,等.基于 Ghost 卷积和通道注意力机制级联结构的车辆检测方法研究[J].天津大学学报(自然科学与工程技术版),2023,56(2):193-199. [28] 蔡仁昊,程宁,彭志勇,等.基于深度学习的轻量化红外弱小车辆目标检测算法研究[J].红外与激光工程, 2022,51(12):357-367. [29] 康庄,杨杰,李桂兰,等.基于改进 YOLOv3的站口行人检测方法[J].铁道科学与工程学报,2021,18(1):55-63. [30] 宋子昂,刘惠临.基于多头自注意力机制和 PANet 的优化 YOLOv5 行人检测算法[J].宁夏师范学院学报, 2024,45(1):93-101. [31] 缪燕子,张宗伟,王贺升,等.基于 AC-YOLO 的路面落叶检测方法[J].控制与决策,2023,38(7):1878-1886. [32] 何铁军,李华恩.基于改进 YOLOv5 的路面病害检测模型[J].土木工程学报,2024,57(2):96-106. [33] 崔文靓,王玉静,康守强,等.基于改进 YOLOv3算法的公路车道线检测方法[J].自动化学报,2022,48(6): 1560-1568. [34] 张翔,唐小林,黄岩军.道路结构特征下的车道线智能检测[J].中国图象图形学报,2021,26(1):123-134. [35] CHENG T H,SONG L,GE Y X,et al.YOLO-World: Real-Time Open-Vocabulary Object Detection[EB/OL]. (2024-01-30)[2024-08-30].https://doi.org/10.48550/ar Xiv.2401.17270.