TireYOLO:轮胎胎侧压印文字检测算法
作者:
作者单位:

安徽工程大学 计算机与信息学院

中图分类号:

TP751;TP183

基金项目:

国家自然科学基金(62302011);安徽未来技术研究院企业合作项目(2023qyhz11); 安徽工程大学校企合作项目(HX-2023-09-050)


TireYOLO: Algorithm for detecting text embossed on the sidewall of tyres
Author:
Affiliation:

School of Computer and information,Anhui Polytechnic University

Fund Project:

National Natural Science Foundation of China, No. 62302011; Anhui Institute of Future Technology Enterprise Cooperation Project (2023qyhz11); School-enterprise Cooperation Project of Anhui Polytechnic University (HX-2023-09-05)

  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献
  • | |
  • 引证文献
  • | |
  • 文章评论
    摘要:

    针对轮胎胎侧压印文字区域受到深色背景干扰,现有算法检测效果较差,无法准确执行检测任务的难题,本文提出了一种改进YOLOv8s的轮胎胎侧压印文字区域检测算法TireYOLO,用于检测轮胎胎侧压印文字区域。首先,提出了一种新的轻量化特征提取模块RepNCSPELAN4_CAA,用于替换YOLOv8s原有的主干网络的C2f模块,通过CAA注意力机制更好的捕捉上下文特征信息,提高了模型的精度的同时降低了计算代价。其次,为了在保持轻量化的同时更好的进行特征融合,采用了一种动态采样的轻量化大感受野特征融合颈部结构DyLKVHSPAN,通过改进HSFPN网络结构,提出了一种高效特征融合网络HSPAN,同时通过Dysample上采样算子进行动态采样,并且提出一种大感受野的特征融合模块UniLKVoVCSP,使DyLKVHSPAN在保持轻量化的同时利用大感受野更好融合特征。最后,提出了一种低计算量检测头DWLHead,重新设计了原有检测头的结构,在降低计算量的基础上提高了检测性能。实验结果表明,与YOLOv8s相比,本文提出的TireYOLO在轮胎胎侧关键信息所在区域目标检测的 mAP@0.5:0.95 上提高了2.5个百分点,在轻量化的效果上,参数量降低了48.4%,计算量降低了49.6% ,证明了本文所提出的算法在检测轮胎侧文字区域方面的优越性。

    Abstract:

    To address the problem that existing algorithms cannot accurately perform the detection task of tire side pressure marking text area due to interference from dark background, this paper proposes a tire side pressure marking text area detection algorithm TireYOLO based on the improved YOLOv8s. Firstly, a lightweight feature extraction module RepNCSPELAN4_CAA is proposed to replace the C2f module in the main body network of YOLOv8s, which can capture contextual feature information better through the CAA attention mechanism and improve model accuracy while reducing computational cost. Secondly, in order to better fuse features while keeping lightweight, a dynamic sampling lightweight large receptive field feature fusion neck structure DyLKVHSPAN is adopted, and an efficient feature fusion network HSPAN is proposed by improving the HSFPN network structure. At the same time, a large receptive field feature fusion module UniLKVoVCSP is proposed to dynamically sample features through the Dysample upsampling operator, so that DyLKVHSPAN can fuse features better with large receptive field while keeping lightweight. Finally, a low computational cost detection head DWLHead is proposed, which redesigns the structure of the original detection head to improve detection performance while reducing computational cost. Experimental results show that compared with YOLOv8s, the TireYOLO algorithm improves the mAP0.5:0.95 of the key information area detection in tire side by 2.5 percentage points, reduces the number of parameters by 48.4%, and reduces the computational cost by 49.6%, verifying the superiority of the proposed algorithm in detecting tire side text area.

    参考文献
    贾雪峰,冯启章,刘献栋等.爆裂轮胎精确建模及其动态特性仿真方法研究[J].汽车工程,2023,45(05):854-864+872
    JIA X F, FENG Q Z, LIU X D. Research on Accurate Modeling and Simulation Method of Dynamic Characteristics for Automotive Tire Blow-out Process[J]. Automotive Engineering,2023,45(05):854-864+872.
    秦增辉,宋月涛,李明等.汽车轮胎质量问题与对策的研究[J].橡塑技术与装备,2022,48(09):25-27.
    QIN Z H, SONG Y T, LI M, Research on quality problems and countermeasures of automobile tires[J]. China Rubber/Plastics Technology and Equipment,2022,48(09):25-27.
    黄彩萍,谢鑫,周永康等.基于改进掩码-区域卷积神经网络的混凝土病害实例分割[J].桥梁建设,2023,53(06):63-70.
    HUANG C P, XIE X, ZHOU Y K. Instance Segmentation of Concrete Defects Based on Improved Mask-RCNN[J]. Bridge Construction,2023,53(06):63-70.
    李雪松,张锲石,宋呈群,等.自动驾驶场景下的轨迹预测技术综述[J].计算机工程,2023,49(05):1-11.
    LI Xuesong,ZHANG Chishe,SONG Chengqun,et al. Review of Trajectory Prediction Technology in Autonomous Driving Scenes [J]. Computer Engineering,2023,49(05):1-11.
    邓天民,谭思奇,蒲龙忠.基于改进YOLOv8s的交通信号灯识别方法[J].计算机工程,2022,48(09):55-62.
    Deng Tianmin,Tan Siqi,Pu Longzhong. Traffic Light recognition method based on improved YOLOv8s[J].Computer Engineering,2022,48(09):55-62.
    Wang Z ,Leng Z ,Zhang Z .Corrigendum to “A Weakly-Supervised transformer-based hybrid network with multi-attention for pavement crack detection” [Constr. Build. Mater. vol. 411, 12 January 2024, 134134][J].Construction and Building Materials,2024,411134677-.
    Paul S A ,Lam S P ,M. T S D , et al.MSD-NAS: multi-scale dense neural architecture search for real-time pedestrian lane detection[J].Applied Intelligence,2023,53(21):25787-25801.
    张晨梦,周健,陈颖.一种基于R-CNN的轮胎压印字符识别方法[J].南京工程学院学报(自然科学版),2020,18(02):50-54.
    ZHANG C M, ZHOU J, CHEN Y. A Method for Recognizing Tire Imprint Characters Based on R-CNN[J]. Journal of Nanjing Institute of Technology(Natural Science Edition) ,2020,18(02):50-54.
    曲星华.汽车轮胎字符识别方法研究及分组系统设计[D].沈阳工业大学,2023.DOI:10.27322/d.cnki.gsgyu.2023.000146.
    Qu Xinghua. Research on Character Recognition Methods for Automobile Tiresand Design of Grouping System [D]. S Shenyang University of Technology, 2023. DOI:10.27322/d.cnki.gsgyu.2023.000146.
    马超伟,张浩,马新明,等.基于改进YOLOv8的轻量化小麦病害检测方法[J].农业工程学报,2024,40(05):187-195.
    马超伟,张浩,马新明,等.基于改进YOLOv8的轻量化小麦病害检测方法[J].农业工程学报,2024,40(05):187-195.MA Chaowei, ZHANG Hao, MA Xinming, et al. Method for the lightweight detection of wheat disease using improvedYOLOv8[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2024, 40(5): 187-195.
    姜香菊,冯海照,李涛.基于FasterNet和YOLOv8s改进的铁路异物入侵快速检测方法[J/OL].北京交通大学学报:1-14[2024-05-22].http://kns.cnki.net/kcms/detail/11.5258.u.20240417.1059.002.html.
    姜香菊,冯海照,李涛.基于FasterNet和YOLOv8s改进的铁路异物入侵快速检测方法[J/OL].北京交通大学学报:1-14[2024-05-22].http://kns.cnki.net/kcms/detail/11.5258.u.20240417.1059.002.html.Jiang X J, Feng H Z, Li T. Improved fast detection of foreign object intrusion in railroads based on fasternet and YOLOv8s [J]. JOURNAL OF BEIJING JIAOTONG UNIVERSITY, 1-14[2024-05-22].http://kns.cnki.net/kcms/detail/11.5258.u.20240417.1059.002.html.
    Wang C Y, Yeh I H, Liao H Y M. YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information[J]. arXiv preprint arXiv:2402.13616, 2024.
    Cai X, Lai Q, Wang Y, et al. Poly Kernel Inception Network for Remote Sensing Detection[J]. arXiv preprint arXiv:2403.06258, 2024.
    Lin T Y, Dollár P, Girshick R, et al. Feature pyramid networks for object detection[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 2117-2125.
    Liu S, Qi L, Qin H, et al. Path aggregation network for instance segmentation[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 8759-8768.
    Li H, Li J, Wei H, et al. Slim-neck by GSConv: A better design paradigm of detector architectures for autonomous vehicles[J]. arXiv preprint arXiv:2206.02424, 2022.
    Kang M, Ting C M, Ting F F, et al. ASF-YOLO: A novel YOLO model with attentional scale sequence fusion for cell instance segmentation[J]. Image and Vision Computing, 2024, 147: 105057.
    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. 2020: 10781-10790.
    LIU W, LU H, FU H, et al. Learning to Upsample by Learning to Sample[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. 2023: 6027-6037.
    Ding X, Zhang Y, Ge Y, et al. Unireplknet: A universal perception large-kernel convnet for audio, video, point cloud, time-series and image recognition[J]. arXiv preprint arXiv:2311.15599, 2023.
    Hu J, Shen L, Sun G. Squeeze-and-excitation networks[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 7132-7141.
    李吴洁,危疆树,王玉超,等.基于改进YOLOv8的柑橘病虫害检测[J/OL].南京农业大学学报,1-12[2024-04-06].
    LI Wujie,GUI Jiangshu,WANG Yuchao,et al. Detection of citrus pests and diseases based on improved YOLOv8 [J/OL]. Journal of Nanjing Agricultural University,1-12[2024-04-06].
    Wang J, Chen K, Xu R, et al. Carafe: Content-aware reassembly of features[C]//Proceedings of the IEEE/CVF international conference on computer vision. 2019: 3007-3016.
    SHI W, Caballero J, Huszár F, et al. Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 1874-1883.
    Chen Y, Zhang C, Chen B, et al. Accurate leukocyte detection based on deformable-DETR and multi-level feature fusion for aiding diagnosis of blood diseases[J]. Computers in Biology and Medicine, 2024, 170: 107917.
    杨琚钱,胡平,戴家树.基于Yolov8-scG神经网络的电动车头盔佩戴检测算法[J/OL].重庆工商大学学报(自然科学版),1-10[2024-08-14].
    YANG Juqian,HU Ping,DAI Jiashu. An electric vehicle helmet wear detection algorithm based on Yolov8-scG neural network[J/OL]. Journal of Chongqing Technology and Business University(Natural Science Edition), 1-10[2024-08-14].
    李茂,肖洋轶,宗望远,等.基于改进YOLOv8模型的轻量化板栗果实识别方法[J].农业工程学报,2024,40(01):201-209.
    LI Mao,XIAO Yangyi,ZONG Wangyuan,et al. Insulator Defect Detection Based on Lightweight GCP-YOLOv8s [J]. Transactions of the Chinese Society of Agricultural Engineering,2024,40(01):201-209.
    罗亮,郎霄,祖国庆,等.一种基于改进YOLOv8的气缸套缺陷检测方法[J/OL].中国机械工程,1-12[2024-08-14].
    LUO Liang,LANG Xiao,ZUO Qing,et al. A Cylinder liner defect detection method based on improved YOLOv8 [J]. China Mechanical Engineering,2024,40(01):201-209.
    文思予,张上,张朝阳,等.基于改进YOLOv8s的多尺度检测算法[J].现代电子技术,2024,47(15):133-138.
    WEN Siyu,ZHANG Shang,ZHANG Chaoyang,et al. Multi-scale object detection algorithm based on improved YOLOv8s [J]. Modern Electronics Technique,2024,47(15):133-138.
    Wang P, Zhang C, Qi F, et al. A single-shot arbitrarily-shaped text detector based on context attended multi-task learning[C]//Proceedings of the 27th ACM international conference on multimedia. 2019: 1277-1285.
    Liao M, Wan Z, Yao C, et al. Real-time scene text detection with differentiable binarization[C]//Proceedings of the AAAI conference on artificial intelligence. 2020, 34(07): 11474-11481.
    相似文献
    引证文献
    引证文献 [0]
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

李萌阳,严楠. TireYOLO:轮胎胎侧压印文字检测算法[J].南京信息工程大学学报,,():

复制
分享
文章指标
  • 点击次数:13
  • 下载次数: 0
  • HTML阅读次数: 0
  • 引用次数: 0
历史
  • 收稿日期:2024-09-18
  • 最后修改日期:2024-12-02
  • 录用日期:2024-12-02

地址:江苏省南京市宁六路219号    邮编:210044

联系电话:025-58731025    E-mail:nxdxb@nuist.edu.cn

南京信息工程大学学报 ® 2025 版权所有  技术支持:北京勤云科技发展有限公司