
浏览全部资源
扫码关注微信
太原工业学院 工程训练中心, 山西 太原 030008
张苏楠,男,博士,副教授,2020年于太原理工大学获得博士学位,主要从事数字孪生与机器视觉方面的研究。E-mail: zhangsn@tit.edu.cn
收稿:2026-03-23,
修回:2026-05-06,
纸质出版:2026-06-06
移动端阅览
张苏楠, 寇元超, 王喆, 等. 基于改进YOLOv11-OBB-SVDD的数字孪生智能车系统设计[J]. 液晶与显示, 2026,41(6):854-865.
ZHANG Sunan, KOU Yuanchao, WANG Zhe, et al. Design of digital twin smart car system based on improved YOLOv11-OBB-SVDD[J]. Chinese Journal of Liquid Crystals and Displays, 2026, 41(6): 854-865.
张苏楠, 寇元超, 王喆, 等. 基于改进YOLOv11-OBB-SVDD的数字孪生智能车系统设计[J]. 液晶与显示, 2026,41(6):854-865. DOI: 10.37188/CJLCD.2026-0052. CSTR: 32172.14.CJLCD.2026-0052.
ZHANG Sunan, KOU Yuanchao, WANG Zhe, et al. Design of digital twin smart car system based on improved YOLOv11-OBB-SVDD[J]. Chinese Journal of Liquid Crystals and Displays, 2026, 41(6): 854-865. DOI: 10.37188/CJLCD.2026-0052. CSTR: 32172.14.CJLCD.2026-0052.
随着智能驾驶和数字孪生技术的快速发展,构建高效、实时的车路协同系统成为研究热点。为此,本文设计了基于改进YOLOv11-OBB-SVDD的数字孪生智能车系统。该系统由物理智能车、虚拟智能车、智能可视化服务、孪生数据和动态实时连接5部分组成。首先,物理智能车搭载视觉传感器实时采集赛道图像,实现自主路径识别;在赛道上方部署工业相机感知智能车在赛道中图像。然后,建立与物理智能车一致的虚拟模型实现虚实映射,利用YOLOv11-OBB检测物理智能车的位置与车身偏转角度;为提高对尺寸较小智能车的检测性能,采用基于频率感知特征融合(FreqFusion)的特征融合方法对模型进行改进。最后,虚拟智能车通过位置与车身偏转角度结合赛道信息,利用支持向量数据描述(SVDD)算法检测车辆偏离赛道风险;通过动态实时连接向物理智能车发送控制信号,智能可视化服务提供智能车可视化动态监控,孪生数据汇聚数字孪生智能车系统多维多尺度数据。实验结果表明,提出的改进YOLOv11-OBB对物理智能车的检测精确率、召回率、IOU阈值为0.5时的平均精度均值分别达到了94.4%、93.0%、92.2%;SVDD检测智能车正常行驶与偏离赛道风险的准确率、查准率、查全率分别达到94.5%、95.4%、93.5%。整个系统实时性高,可以准确实现智能车自主循迹与数字孪生各模块的功能。
With the rapid development of intelligent driving and digital twin technology, the efficient and real-time vehicle-road cooperative system has become a research focus. A digital twin smart car system based on improved YOLOv11-OBB-SVDD is designed in this paper. The system consists of five parts: physical smart car, virtual smart car, intelligent visualization service, twin data and dynamic real-time connection. Firstly, a physical smart car is equiped with visual sensors to capture track images in real time for autonomous path recognition; an industrial camera is mounted above the track to perceive the images of the smart car in the track. Then, a virtual model consistent with the physical smart car is established to enable bidirectional synchronization between the digital and physical domains. YOLOv11-OBB is used to detect the position of the physical smart car and the deflection angle of the body to realize the virtual-real mapping. To enhance the detection performance of small-sized smart cars in images, a frequency-aware feature fusion(FreqFusion) method is proposed to improve the model and further refine accurate virtual-to-real mapping. Finally, the virtual twin unit integrates vehicle coordinates, deflection angles and track topological information, and leverages Support Vector Data Description(SVDD) to identify track departure risks. Real-time communication links transmit corresponding control commands back to the physical intelligent vehicle. At the same time, the intelligent visualization service provides the visual dynamic monitoring of the smart car, and the multi-dimensional and multi-scale data of the digital twin smart car system are aggregated by twin data. Experimental results indicate that the proposed improvement of YOLOv11-OBB has achieved an average accuracy of 94.4%, 93.0%, and 92.2% respectively for the detection accuracy, recall rate, and mean average precision when the IOU threshold is 0.5 for the physical smart car. The SVDD-based anomaly detection system achieves an accuracy of 94.5%, a precision of 95.4%, and a recall of 93.5% in identifying both normal driving behavior and track deviation risks in smart car. The entire system operates smoothly and can accurately implement the functions of smart car autonomous tracking and digital twin modules.
WU N F , SUN Y X , HU J T , et al . Intelligent nanophotonics: when machine learning sheds light [J]. eLight , 2025 , 5 ( 1 ): 5 . doi: 10.1186/s43593-025-00085-x http://dx.doi.org/10.1186/s43593-025-00085-x
崔勇 , 袁志鸿 , 迟清凯 , 等 . 基于智能车的高还原度虚拟仿真实验平台设计 [J]. 实验技术与管理 , 2023 , 40 ( 4 ): 133 - 137,143 .
CUI Y , YUAN Z H , CHI Q K , et al . Design of highly reductive virtual simulation experiment platform based on intelligent vehicles [J]. Experimental Technology and Management , 2023 , 40 ( 4 ): 133 - 137, 143 . (in Chinese)
李成勇 , 谭寒钟 , 王莎 , 等 . 基于OpenMV的智能“寻的”小车控制系统 [J]. 液晶与显示 , 2020 , 35 ( 8 ): 870 - 876 . doi: 10.37188/yjyxs20203508.0870 http://dx.doi.org/10.37188/yjyxs20203508.0870
LI C Y , TAN H Z , WANG S , et al . OpenMV-based intelligent “find” trolley control system [J]. Chinese Journal of Liquid Crystals and Displays , 2020 , 35 ( 8 ): 870 - 876 . (in Chinese) . doi: 10.37188/yjyxs20203508.0870 http://dx.doi.org/10.37188/yjyxs20203508.0870
陶飞 , 刘蔚然 , 张萌 , 等 . 数字孪生五维模型及十大领域应用 [J]. 计算机集成制造系统 , 2019 , 25 ( 1 ): 1 - 18 .
TAO F , LIU W R , ZHANG M , et al . Five-dimension digital twin model and its ten applications [J]. Computer Integrated Manufacturing Systems , 2019 , 25 ( 1 ): 1 - 18 . (in Chinese)
俞洋 , 李峰 , 缪奕扬 . 基于机器视觉的全元素赛道智能小车实验系统设计与应用 [J]. 中南民族大学学报(自然科学版) , 2022 , 41 ( 6 ): 689 - 696 .
YU Y , LI F , MIAO Y Y , et al . Design and application of all-element track intelligent car experimental system based on machine vision [J]. Journal of South-Central Minzu University (Natural Science Edition) , 2022 , 41 ( 6 ): 689 - 696 . (in Chinese)
王培丞 , 高博 , 宫珣 . 基于循迹智能车的新生项目式课程教学探索与实践 [J]. 实验室研究与探索 , 2024 , 43 ( 8 ): 157 - 160,170 .
WANG P C , GAO B , GONG X . Exploration and practice of project-based course teaching for freshmen based on tracking intelligent vehicles [J]. Research and Exploration in Laboratory , 2024 , 43 ( 8 ): 157 - 160, 170 . (in Chinese)
包启龙 , 景会成 , 张靖轩 , 等 . 一种改进Canny算子的图像边缘检测方法 [J]. 现代电子技术 , 2024 , 47 ( 23 ): 36 - 42 . doi: 10.16652/j.issn.1004-373x.2024.23.006 http://dx.doi.org/10.16652/j.issn.1004-373x.2024.23.006
BAO Q L , JING H C , ZHANG J X , et al . Image edge detection method based on improved Canny operator [J]. Modern Electronics Technique , 2024 , 47 ( 23 ): 36 - 42 . (in Chinese) . doi: 10.16652/j.issn.1004-373x.2024.23.006 http://dx.doi.org/10.16652/j.issn.1004-373x.2024.23.006
LOVE A , BEHSERESHT S , PASTRANA O A V , et al . Hybrid physical-virtual digital twin system for additive manufacturing [J]. Journal of Advanced Manufacturing Systems , 2025 , 24 ( 1 ): 1 - 20 . doi: 10.1142/s0219686725500015 http://dx.doi.org/10.1142/s0219686725500015
陈航 , 严帅 , 薛伟钊 , 等 . 基于千兆以太网的多节点数据采集系统 [J]. 仪表技术与传感器 , 2021 ( 12 ): 71 - 74,80 .
CHEN H , YAN S , XUE W Z , et al . Multi-node data acquisition system based on gigabit Ethernet [J]. Instrument Technique and Sensor , 2021 ( 12 ): 71 - 74, 80 . (in Chinese)
刘洪笑 , 向勉 , 谭建军 , 等 . 基于LSTM的ZigBee网络中通信信号识别算法 [J]. 计算机仿真 , 2023 , 40 ( 9 ): 339 - 343 .
LIU H X , XIANG M , TAN J J , et al . Communication signal recognition algorithm in ZigBee network based on long and short-term memory [J]. Computer Simulation , 2023 , 40 ( 9 ): 339 - 343 . (in Chinese)
ZHOU Z Y , WANG L L , LIU G J , et al . A facile photonics reconfigurable memristor with dynamically allocated neurons and synapses functions [J]. Light: Science Applications , 2025 , 14 ( 1 ): 269 . doi: 10.1038/s41377-025-01928-5 http://dx.doi.org/10.1038/s41377-025-01928-5
荀欢欢 . 基于数字孪生的舰船上层建筑运维系统 [J]. 舰船科学技术 , 2023 , 45 ( 3 ): 133 - 136 .
XUN H H . Design of operation and maintenance system for ship superstructure based on digital twin [J]. Ship Science and Technology , 2023 , 45 ( 3 ): 133 - 136 . (in Chinese)
RASHMI S , SRINATH S , DESHMUKH S , et al . Cephalometric landmark annotation using transfer learning: Detectron2 and YOLOv8 baselines on a diverse cephalometric image dataset [J]. Computers in Biology and Medicine , 2024 , 183 : 109318 . doi: 10.1016/j.compbiomed.2024.109318 http://dx.doi.org/10.1016/j.compbiomed.2024.109318
王文坤 , 谢辉 , 姜吴瑾 , 等 . 融合混合注意力的轻量化柑橘成熟度检测算法 [J]. 液晶与显示 , 2026 , 41 ( 4 ): 549 - 564 .
WANG W K , XIE H , JIANG W J , et al . Lightweight citrus maturity detection algorithm with hybrid attention fusion [J]. Chinese Journal of Liquid Crystals and Displays , 2026 , 41 ( 4 ): 549 - 564 . (in Chinese)
吕学涵 , 李富 , 祁铭瑞 , 等 . 基于改进YOLOv11s的无人机小目标检测算法 [J]. 液晶与显示 , 2025 , 40 ( 11 ): 1744 - 1756 . doi: 10.37188/cjlcd.2025-0193 http://dx.doi.org/10.37188/cjlcd.2025-0193
LÜ X H , LI F , QI M R , et al . Target detection algorithm based on improved YOLOv11s UAV aerial image [J]. Chinese Journal of Liquid Crystals and Displays , 2025 , 40 ( 11 ): 1744 - 1756 . (in Chinese) . doi: 10.37188/cjlcd.2025-0193 http://dx.doi.org/10.37188/cjlcd.2025-0193
殷旭鹏 , 赵兴强 . YOLOv11-MAS:一种高效的PCB缺陷检测算法 [J]. 计算机工程与应用 , 2025 , 61 ( 17 ): 102 - 111 .
YIN X P , ZHAO X Q . YOLOv11-MAS: Efficient PCB defect detection algorithm [J]. Computer Engineering and Applications , 2025 , 61 ( 17 ): 102 - 111 . (in Chinese)
郑冉 , 张富凯 , 袁冠 , 等 . 基于YOLOv11_OBB的煤矿钻杆计数方法 [J]. 工矿自动化 , 2025 , 51 ( 5 ): 72 - 79,95 .
ZHENG R , ZHANG F K , YUAN G , et al . Method for counting coal mine drill pipes based on YOLOv11_OBB [J]. Journal of Mine Automation , 2025 , 51 ( 5 ): 72 - 79, 95 . (in Chinese)
CHEN L W , FU Y , GU L , et al . Frequency-aware feature fusion for dense image prediction [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2024 , 46 ( 12 ): 10763 - 10780 . doi: 10.1109/tpami.2024.3449959 http://dx.doi.org/10.1109/tpami.2024.3449959
ZHANG S N , JIA B , GAO Y X . A novel approach to porcine abnormal sounds recognition based on improved Multi-SVDD [J]. PLoS One , 2025 , 20 ( 9 ): e0332996 . doi: 10.1371/journal.pone.0332996 http://dx.doi.org/10.1371/journal.pone.0332996
陈名渝 , 谢玥辰 , 吕雄涛 , 等 . 冷轧钢表面与内部缺陷检测研究 [J]. 中国光学(中英文) , 2024 , 17 ( 4 ): 823 - 833 . doi: 10.37188/co.2023-0189 http://dx.doi.org/10.37188/co.2023-0189
CHEN M Y , XIE Y C , LV X T , et al . Detection of surface and internal defects in cold rolled steel [J]. Chinese Optics , 2024 , 17 ( 4 ): 823 - 833 . (in Chinese) . doi: 10.37188/co.2023-0189 http://dx.doi.org/10.37188/co.2023-0189
雷帮军 , 余翱 , 吴正平 , 等 . 改进YOLOv8n的无人机航拍小目标检测算法 [J]. 现代电子技术 , 2025 , 48 ( 3 ): 26 - 34 .
LEI B J , YU A , WU Z P , et al . Improved small object detection algorithm based on YOLOv8n for UAV aerial photography [J]. Modern Electronic Technique , 2025 , 48 ( 3 ): 26 - 34 . (in Chinese)
0
浏览量
189
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621