
浏览全部资源
扫码关注微信
1.陕西理工大学 机械工程学院, 陕西 汉中 723001
2.陕西汉江机床有限责任公司, 陕西 汉中 723301
李奥,男,硕士研究生,2019年于安阳学院获得学士学位,主要从事先进制造技术及装备方面的研究。E-mail:2509260778@qq.com
王明武,男,硕士,副教授,2007年于郑州轻工业大学获得硕士学位,主要从事先进工业自动化技术集成与应用方面的研究。E-mail:wangmingwu@163.com
收稿:2026-04-06,
修回:2026-04-16,
纸质出版:2026-05-05
移动端阅览
李奥, 王明武, 王楠, 等. 基于改进YOLOv11n的轻量化锥筒识别算法[J]. 液晶与显示, 2026,41(5):659-674.
LI Ao, WANG Mingwu, WANG Nan, et al. Lightweight cone detection algorithm based on an improved YOLOv11n[J]. Chinese Journal of Liquid Crystals and Displays, 2026, 41(5): 659-674.
李奥, 王明武, 王楠, 等. 基于改进YOLOv11n的轻量化锥筒识别算法[J]. 液晶与显示, 2026,41(5):659-674. DOI: 10.37188/CJLCD.2026-0067. CSTR: 32172.14.CJLCD.2026-0067.
LI Ao, WANG Mingwu, WANG Nan, et al. Lightweight cone detection algorithm based on an improved YOLOv11n[J]. Chinese Journal of Liquid Crystals and Displays, 2026, 41(5): 659-674. DOI: 10.37188/CJLCD.2026-0067. CSTR: 32172.14.CJLCD.2026-0067.
针对当前市面上锥筒回收装置自动化程度低、检测精度不足,且因参数量大造成移动端设备部署困难等问题,提出了一种基于改进YOLOv11n的轻量化识别算法RGLU-YOLOv11n。首先,结合RepConv和TransNet的CGLU(Convolutional Gated Linera Unit)重构C3K2模块,降低复杂模型复杂度并提高检测速度;其次,引入Ghost卷积和自适应下采样(Adaptive Downsampling,ADown),设计一种轻量化的幽灵下采样模块(Ghost-ADown),在保持特征丰富度的同时显著降低了下采样过程中的计算冗余;然后,引入一种轻量化共享卷积检测头(Lightweight Shared Convolutional Detection,LSCD),在保持检测精度的同时实现模型轻量化,使模型更加适合部署在资源受限的边缘设备;最后,针对CIoU损失函数在检测时泛化性弱和收敛速度慢的问题,引入Focaler-IoU和MPDIoU,设计Focaler-MPDIoU损失函数替代原有模型的损失函数,以提高模型精度并加快边界框回归速度。实验结果表明:该模型较基准模型YOLOv11n精确率、召回率、平均精度均值mAP0.5分别提升了1.1%、1.4%和1.6%,参数量和模型存储体积显著降低35.3%和41.5%,表明该模型在显著减少计算开销的同时,依旧维持了较高的识别准确率,符合移动端及嵌入式设备的部署需求。
To address the issues of low automation, insufficient detection accuracy, and difficulty in deploying on mobile devices due to large parameter counts in current cone recycling devices, this paper proposes a lightweight recognition algorithm named RGLU-YOLOv11n based on an improved YOLOv11n. First, RepConv and TransNet’s CGLU (Convolutional Gated Linear Unit) are integrated to reconstruct the C3K2 module, reducing model complexity and improving detection speed. Second, Ghost convolution and adaptive downsampling (ADown) are introduced to design a lightweight Ghost-ADown module, which notably reduces computational redundancy during downsampling while preserving feature richness. Third, a Lightweight Shared Convolutional Detection(LSCD) head, is introduced to achieve model lightweighting while maintaining detection accuracy, making the model more suitable for deployment on resource-constrained edge devices. Finally, to address the issues of weak generalization and slow convergence of the CIoU loss function during detection, Focaler-IoU and MPDIoU are introduced to design a Focaler-MPDIoU loss function, replacing the original loss function to improve model accuracy and accelerate bounding box regression. Experimental results show that compared with the baseline YOLOv11n model, the proposed model achieves improvements of 1.1%, 1.4% and 1.6% in precision, recall and mAP@0.5, respectively, while reducing parameters and model size by 35.3% and 41.5%, respectively. These results demonstrate that the proposed model maintains high recognition accuracy while significantly reducing network computational load, meeting the deployment requirements for mobile and embedded devices.
张轩铭 . 高速公路交通机电监控技术应用研究 [J]. 运输经理世界 , 2025 ( 32 ): 141 - 143 .
ZHANG X M . Research on the application of highway traffic electromechanical monitoring technology [J]. Transport Manager World , 2025 ( 32 ): 141 - 143 . (in Chinese)
张政 , 孙鹏 , 王立勇 , 等 . 基于边缘卷积的交通锥筒点云数据分割方法 [J]. 电子测量技术 , 2023 , 46 ( 20 ): 98 - 103 .
ZHANG Z , SUN P , WANG L Y , et al . Segmentation method via point cloud of traffic cones based on edge convolution [J]. Electronic Measurement Technology , 2023 , 46 ( 20 ): 98 - 103 . (in Chinese)
吴泽东 . 基于机器视觉的交通锥筒自动收放机的研究 [D]. 汉中 : 陕西理工大学 , 2024 .
WU Z D . Research on automatic traffic cone recorder based on machine vision [D]. Hanzhong : Shaanxi University of Technology , 2024 . (in Chinese)
杨彬彬 , 高中强 . 基于YOLOv8的智能视频监控目标识别系统设计 [J]. 电脑编程技巧与维护 , 2026 ( 2 ): 128 - 130 .
YANG B B , GAO Z Q . Design of intelligent video surveillance target recognition system based on YOLOv8 [J]. Computer Programming Skills & Maintenance , 2026 ( 2 ): 128 - 130 . (in Chinese)
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 (CVPR) . Las Vegas : IEEE , 2016 : 779 - 788 . doi: 10.1109/cvpr.2016.91 http://dx.doi.org/10.1109/cvpr.2016.91
REDMON J , FARHADI A . YOLOv3: an incremental improvement [J/OL]. arXiv , 2018 : 1804 . 02767 . doi: 10.1109/cvpr.2017.690 http://dx.doi.org/10.1109/cvpr.2017.690
BOCHKOVSKIY A , WANG C Y , LIAO H Y M . YOLOv4: optimal speed and accuracy of object detection [J/OL]. arXiv , 2020 : 2004 . 10934 . doi: 10.48550/arXiv.2004.10934 http://dx.doi.org/10.48550/arXiv.2004.10934
JOCHER G . YOLOv5 [EB/OL]. ( 2020-06-19 )[ 2023-12-01 ]. https://github.com/ultralytics/yolov5 https://github.com/ultralytics/yolov5 .
LI C Y , LI L L , JIANG H L , et al . YOLOv6: a single-stage object detection framework for industrial applications [J/OL]. arXiv , 2022 : 2209 . 02976 .
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]// Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Vancouver : IEEE , 2023 : 7464 - 7475 . doi: 10.1109/cvpr52729.2023.00721 http://dx.doi.org/10.1109/cvpr52729.2023.00721
刘博文 , 徐卫平 , 徐钦 , 等 . 基于改进YOLOX的猕猴桃分类识别与空间定位 [J]. 国外电子测量技术 , 2024 , 43 ( 4 ): 133 - 142 .
LIU B W , XU W P , WU Q , et al . Classification identification and spatial localization of kiwifruit based on the improved YOLOX [J]. Foreign Electronic Measurement Technology , 2024 , 43 ( 4 ): 133 - 142 . (in Chinese)
吴泽东 , 王明武 , 韩继科 , 等 . 小型交通锥筒自动收放机设计与研究 [J]. 陕西理工大学学报(自然科学版) , 2023 , 39 ( 6 ): 24 - 31 .
WU Z D , WANG M W , HAN J K , et al . Design and research of small traffic cone automatic receiver [J]. Journal of Shaanxi University of Technology (Natural Science Edition) , 2023 , 39 ( 6 ): 24 - 31 . (in Chinese)
SU Q H , WANG H D , XIE M , et al . Real‐time traffic cone detection for autonomous driving based on YOLOv4 [J]. IET Intelligent Transport Systems , 2022 , 16 ( 10 ): 1380 - 1390 . doi: 10.1049/itr2.12212 http://dx.doi.org/10.1049/itr2.12212
李旭 , 李刚 , 李永明 , 等 . 轻量化的YOLOv8锥桶检测算法研究 [J]. 重庆理工大学学报(自然科学) , 2024 , 38 ( 7 ): 71 - 77 .
LI X , LI G , LI Y M , et al . Research on lightweight YOLOv8 cone bucket detection algorithm [J]. Journal of Chongqing University of Technology (Natural Science) , 2024 , 38 ( 7 ): 71 - 77 . (in Chinese)
KATSAMENIS I , KAROLOU E E , DAVRADOU A , et al . TraCon: a novel dataset for real-time traffic cones detection using deep learning [C]// Novel & Intelligent Digital Systems: Proceedings of the 2nd International Conference . Cham : Springer , 2022 : 382 - 391 . doi: 10.1007/978-3-031-17601-2_37 http://dx.doi.org/10.1007/978-3-031-17601-2_37
李春晖 , 吕岩 , 孟祥来 , 等 . 基于YOLOv8的油气管道漏磁检测缺陷智能识别技术研究 [J]. 仪器仪表学报 , 2025 , 46 ( 2 ): 247 - 254 .
LI C H , LYU Y , MENG X L , et al . Research on intelligent defect recognition in oil and gas pipeline magnetic flux leakage detection based on YOLOv8 [J]. Chinese Journal of Scientific Instrument , 2025 , 46 ( 2 ): 247 - 254 . (in Chinese)
HUANG J L , YAO S W , WANG J Y , et al . Intelligent identification of mines and tailings pond based on the improved YOLOv8 model [J]. Science of Surveying and Mapping , 2025 , 50 ( 7 ): 70 - 82 . (in Chinese)
SHI D . TransNeXt: robust foveal visual perception for vision transformers [C]. 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle : IEEE , 2023 : 17773 - 17783 . doi: 10.1109/cvpr52733.2024.01683 http://dx.doi.org/10.1109/cvpr52733.2024.01683
刘兆龙 , 曹伟 , 高军伟 . 基于改进YOLOv7的小目标焊点缺陷检测算法 [J]. 液晶与显示 , 2024 , 39 ( 10 ): 1332 - 1340 . doi: 10.37188/cjlcd.2024-0051 http://dx.doi.org/10.37188/cjlcd.2024-0051
LIU Z L , CAO W , GAO J W . Defect detection of small object solder joints based on improved YOLOv7 [J]. Chinese Journal of Liquid Crystals and Displays , 2024 , 39 ( 10 ): 1332 - 1340 . (in Chinese) . doi: 10.37188/cjlcd.2024-0051 http://dx.doi.org/10.37188/cjlcd.2024-0051
蔡忠祺 , 林珊玲 , 林坚普 , 等 . 基于改进YOLOv8n-Pose的疲劳驾驶检测 [J]. 液晶与显示 , 2025 , 40 ( 4 ): 617 - 629 . doi: 10.37188/cjlcd.2024-0192 http://dx.doi.org/10.37188/cjlcd.2024-0192
CAI Z Q , LIN S L , LIN J P , et al . Fatigue driving detection based on improved YOLOv8n-Pose [J]. Chinese Journal of Liquid Crystals and Displays , 2025 , 40 ( 4 ): 617 - 629 . (in Chinese) . doi: 10.37188/cjlcd.2024-0192 http://dx.doi.org/10.37188/cjlcd.2024-0192
WANG C Y , YEH I H , LIAO H Y M . YOLOv9: learning what you want to learn using programmable gradient information [C]. 18th European Conference on Computer Vision . Milan : Springer , 2024 : 1 - 21 . doi: 10.1007/978-3-031-72751-1_1 http://dx.doi.org/10.1007/978-3-031-72751-1_1
SHEN Q , ZHANG L , ZHANG Y X , et al . Distracted driving behavior detection algorithm based on lightweight StarDL-YOLO [J]. Electronics , 2024 , 13 ( 16 ): 3216 . doi: 10.3390/electronics13163216 http://dx.doi.org/10.3390/electronics13163216
LI J W , LIU S T , CHEN D , et al . APD-YOLOv7: enhancing sustainable farming through precise identification of agricultural pests and diseases using a novel diagonal difference ratio IOU loss [J]. Sustainability , 2024 , 16 ( 20 ): 8855 . doi: 10.3390/su16208855 http://dx.doi.org/10.3390/su16208855
REZATOFIGHI H , TSOI N , GWAK J , et al . Generalized intersection over union: a metric and a loss for bounding box regression [C]. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Long Beach : IEEE , 2019 : 658 - 666 . doi: 10.1109/cvpr.2019.00075 http://dx.doi.org/10.1109/cvpr.2019.00075
MA S L , XU Y . MPDIoU: a loss for efficient and accurate bounding box regression [J/OL]. arXiv , 2023 : 2307 . 07662 .
ZHANG H , ZHANG S J . Focaler-IoU: more focused intersection over union loss [J/OL]. arXiv , 2024 : 2401 . 10525 .
JALALI B , MACPHEE C . VEViD: vision enhancement via virtual diffraction and coherent detection [J]. eLight , 2022 , 2 : 24 . doi: 10.1186/s43593-022-00034-y http://dx.doi.org/10.1186/s43593-022-00034-y
刘彦磊 , 李孟喆 , 王宣宣 . 轻量型YOLOv5s车载红外图像目标检测 [J]. 中国光学(中英文) , 2023 , 16 ( 5 ): 1045 - 1055 . doi: 10.37188/co.2022-0254 http://dx.doi.org/10.37188/co.2022-0254
LIU Y L , LI M Z , WANG X X . Lightweight YOLOv5s vehicle infrared image target detection [J]. Chinese Optics , 2023 , 16 ( 5 ): 1045 - 1055 . (in Chinese) . doi: 10.37188/co.2022-0254 http://dx.doi.org/10.37188/co.2022-0254
WANG Z K , HU S H , WANG X T , et al . YOLOv13-cone-lite: an enhanced algorithm for traffic cone detection in autonomous formula racing cars [J]. Applied Sciences , 2025 , 15 ( 17 ): 9501 . doi: 10.3390/app15179501 http://dx.doi.org/10.3390/app15179501
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
LIANG Y H , WANG J , XUE K W , et al . High-clockrate free-space optical in-memory computing [J]. Light: Science & Applications , 2026 , 15 : 115 . doi: 10.1038/s41377-026-02206-8 http://dx.doi.org/10.1038/s41377-026-02206-8
0
浏览量
131
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