PSG-Yolov5: A Paradigm for Traffic Sign Detection and Recognition Algorithm Based on Deep Learning

被引:23
|
作者
Hu, Jie [1 ]
Wang, Zhanbin [1 ]
Chang, Minjie [1 ]
Xie, Lihao [1 ]
Xu, Wencai [1 ]
Chen, Nan [1 ]
机构
[1] Wuhan Univ Technol, Coll Automot Engn, Wuhan 430070, Peoples R China
来源
SYMMETRY-BASEL | 2022年 / 14卷 / 11期
关键词
traffic sign detection; deep learning; small object detection; multi-scale fusion;
D O I
10.3390/sym14112262
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
With the gradual popularization of autonomous driving technology, how to obtain traffic sign information efficiently and accurately is very important for subsequent decision-making and planning tasks. Traffic sign detection and recognition (TSDR) algorithms include color-based, shape-based, and machine learning based. However, the algorithms mentioned above are insufficient for traffic sign detection tasks in complex environments. In this paper, we propose a traffic sign detection and recognition paradigm based on deep learning algorithms. First, to solve the problem of insufficient spatial information in high-level features of small traffic signs, the parallel deformable convolution module (PDCM) is proposed in this paper. PDCM adaptively acquires the corresponding receptive field preserving the integrity of the abstract information through symmetrical branches thereby improving the feature extraction capability. Simultaneously, we propose sub-pixel convolution attention module (SCAM) based on the attention mechanism to alleviate the influence of scale distribution. Distinguishing itself from other feature fusion, our proposed method can better focus on the information of scale distribution through the attention module. Eventually, we introduce GSConv to further reduce the computational complexity of our proposed algorithm, better satisfying industrial application. Experimental results demonstrate that our proposed methods can effectively improve performance, both in detection accuracy and mAP@0.5. Specifically, when the proposed PDCM, SCAM, and GSConv are applied to the Yolov5, it achieves 89.2% mAP@0.5 in TT100K, which exceeds the benchmark network by 4.9%.
引用
收藏
页数:16
相关论文
共 50 条
  • [21] DeepSign: Deep Learning based Traffic Sign Recognition
    Li, Dong
    Zhao, Dongbin
    Chen, Yaran
    Zhang, Qichao
    2018 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2018,
  • [22] The Research on Traffic Sign Recognition Based on Deep Learning
    Li, Chen
    Yang, Cheng
    2016 16TH INTERNATIONAL SYMPOSIUM ON COMMUNICATIONS AND INFORMATION TECHNOLOGIES (ISCIT), 2016, : 156 - 161
  • [23] Indian traffic sign detection and recognition using deep learning
    Megalingam, Rajesh Kannan
    Thanigundala, Kondareddy
    Musani, Sreevatsava Reddy
    Nidamanuru, Hemanth
    Gadde, Lokesh
    INTERNATIONAL JOURNAL OF TRANSPORTATION SCIENCE AND TECHNOLOGY, 2023, 12 (03) : 683 - 699
  • [24] A lightweight algorithm for small traffic sign detection based on improved YOLOv5s
    Cai, Kunhui
    Yang, Jingmin
    Ren, Jinghui
    Zhang, Wenjie
    SIGNAL IMAGE AND VIDEO PROCESSING, 2024, 18 (05) : 4821 - 4829
  • [25] Lightweight traffic sign detection algorithm based on improved YOLOv5 in snowy environments
    Wang, Zhanyu
    Qu, Mengmeng
    Wang, Ning
    Liu, Lintao
    Su, Hongyang
    SIGNAL IMAGE AND VIDEO PROCESSING, 2025, 19 (05)
  • [26] Traffic sign detection and recognition based on MMS data using YOLOv4-Tiny algorithm
    Gezgin, Hilal
    Alkan, Reha Metin
    Neural Computing and Applications, 2024, 36 (33) : 20633 - 20651
  • [27] Efficient traffic sign recognition with YOLOv5
    Nacir, Omran
    Amna, Maraoui
    Imen, Werda
    Hamdi, Belgacem
    International Journal of Powertrains, 2024, 13 (03) : 269 - 286
  • [28] Improved Traffic Sign Recognition Algorithm Based on YOLOV4-Tiny
    Zong, Haile
    Qi, Chengming
    INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE, 2023, 37 (01)
  • [29] Improved traffic sign recognition algorithm based on YOLOv4-tiny
    Sharma, Vipul Kumar
    Dhiman, Pankaj
    Rout, Ranjeet Kumar
    JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2023, 91
  • [30] Road traffic sign recognition algorithm based on improved YOLOv4
    Li D.
    Su Z.
    Liu Y.
    Guangxue Jingmi Gongcheng/Optics and Precision Engineering, 2023, 31 (09): : 1366 - 1378