A Classification Method for Helmet Wearing State Based on Progressive Multi-Granularity Training Strategy

被引:0
|
作者
Zhang, Yi-Jia [1 ]
Xiao, Fusu [1 ]
Lu, Zhe-Ming [2 ]
机构
[1] Zhejiang Sci Tech Univ, Sch Informat Sci & Engn, Hangzhou 330114, Peoples R China
[2] Zhejiang Univ, Sch Aeronaut & Astronaut, Hangzhou 310000, Peoples R China
来源
IEEE ACCESS | 2024年 / 12卷
关键词
fine-grained classification; PMG-Helmet; Helmet wearing state; weight allocation; mutual channel loss;
D O I
10.1109/ACCESS.2024.3474433
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In many construction sites, whether to wear the safety helmet directly affects the life safety of workers. Therefore, monitoring the wearing state of safety helmets has become an important auxiliary means of construction safety. However, most current safety helmet wearing state monitoring algorithms only distinguish workers who are wearing safety helmets from those who are not, which has high detection limitations and algorithm performance needs to be improved. In this paper, we innovatively apply fine-grained classification algorithms to classify the wearing state of safety helmets, and propose a progressive multi-granularity training strategy based safety helmet wearing state classification algorithm PMG-Helmet (Progressive Multi-granularity for Helmet, PMG-Helmet) for the six classification dataset of safety helmet wearing state. This algorithm achieves multi-granularity classification of helmet wearing state through a puzzle generator and a progressive training strategy, and introduces the MC-Loss(Mutual Channel Loss) function designed specifically for fine-grained classification tasks to improve algorithm performance. In the algorithm inference stage, this paper normalized the weights of the outputs of each stage of the PMG-Helmet algorithm, resulting in better combination accuracy. The experimental results show that the accuracy of this algorithm on the six classification dataset is 93.36%. Specifically, in order to further investigate the effectiveness of the algorithm, this study conducted separate studies on the finer subcategories of "wearing the helmet correctly" and "wearing the helmet but not fastening the chin strap" during the experimental phase, achieving an accuracy of 90.11%.
引用
收藏
页码:146397 / 146408
页数:12
相关论文
共 50 条
  • [21] Password region attribute classification based on multi-granularity cascade fusion
    Yu, Wei
    Liu, Cheng
    Ni, Lvlin
    Shi, Yu
    Ji, Qingbing
    CONNECTION SCIENCE, 2025, 37 (01)
  • [22] The Method of Analysis Granularity Determination for Multi-granularity Time Series
    Chen, Hailan
    Gao, Xuedong
    Du, Qiangbo
    2018 8TH INTERNATIONAL CONFERENCE ON LOGISTICS, INFORMATICS AND SERVICE SCIENCES (LISS), 2018,
  • [23] Multi-granularity sequence generation for hierarchical image classification
    Liu, Xinda
    Wang, Lili
    COMPUTATIONAL VISUAL MEDIA, 2024, 10 (02) : 243 - 260
  • [24] Multi-granularity sequence generation for hierarchical image classification
    Xinda Liu
    Lili Wang
    Computational Visual Media, 2024, 10 : 243 - 260
  • [25] Multi-granularity classification rule discovery using ERID
    Im, Seunghyun
    Ras, Zbigniew W.
    Tsay, Li-Shiang
    ROUGH SETS AND KNOWLEDGE TECHNOLOGY, 2008, 5009 : 491 - +
  • [26] Hierarchical classification with exponential weighting of multi-granularity paths
    Wang, Yibin
    Zhu, Qing
    Cheng, Yusheng
    INFORMATION SCIENCES, 2024, 675
  • [27] Multi-granularity classification of upper gastrointestinal endoscopic images
    Wei, Hua
    Yi, Dongyang
    Hu, Shuyu
    Zhu, Guobin
    Ding, Yi
    Pang, Minghui
    NEUROCOMPUTING, 2025, 626
  • [28] Multi-scale network via progressive multi-granularity attention for fine-grained visual classification
    An, Chen
    Wang, Xiaodong
    Wei, Zhiqiang
    Zhang, Ke
    Huang, Lei
    APPLIED SOFT COMPUTING, 2023, 146
  • [29] Research on the multi-granularity method of role engineering
    Jiao, Yongmei
    Zhang, Menghan
    Wu, Yu
    FRONTIERS IN COMPUTATIONAL NEUROSCIENCE, 2022, 16
  • [30] Research on Text Classification by Fusing Multi-Granularity Information
    Xin, Miaomiao
    Ma, Li
    Hu, Bofa
    Computer Engineering and Applications, 2023, 59 (09) : 104 - 111