Highly Discriminative Driver Distraction Detection Method Based on Swin Transformer

被引:1
|
作者
Zhang, Ziyang [1 ,2 ]
Yang, Lie [1 ,3 ]
Lv, Chen [1 ,3 ]
机构
[1] Jilin Univ, State Key Lab Automot Simulat & Control, Changchun 130012, Peoples R China
[2] North China Univ Technol, Brunel London Sch, Beijing 100144, Peoples R China
[3] Nanyang Technol Univ, Sch Mech & Aerosp Engn, Singapore 639798, Singapore
来源
VEHICLES | 2024年 / 6卷 / 01期
关键词
Swin Transformer; driver distraction detection; SC loss; center vector shift; discriminative feature learning; COGNITIVE DISTRACTION;
D O I
10.3390/vehicles6010006
中图分类号
TH [机械、仪表工业];
学科分类号
0802 ;
摘要
Driver distraction detection not only helps to improve road safety and prevent traffic accidents, but also promotes the development of intelligent transportation systems, which is of great significance for creating a safer and more efficient transportation environment. Since deep learning algorithms have very strong feature learning abilities, more and more deep learning-based driver distraction detection methods have emerged in recent years. However, the majority of existing deep learning-based methods are optimized only through the constraint of classification loss, making it difficult to obtain features with high discrimination, so the performance of these methods is very limited. In this paper, to improve the discrimination between features of different classes of samples, we propose a high-discrimination feature learning strategy and design a driver distraction detection model based on Swin Transformer and the highly discriminative feature learning strategy (ST-HDFL). Firstly, the features of input samples are extracted through the powerful feature learning ability of Swin Transformer. Then, the intra-class distance of samples of the same class in the feature space is reduced through the constraint of sample center distance loss (SC loss), and the inter-class distance of samples of different classes is increased through the center vector shift strategy, which can greatly improve the discrimination of different class samples in the feature space. Finally, we have conducted extensive experiments on two publicly available datasets, AUC-DD and State-Farm, to demonstrate the effectiveness of the proposed method. The experimental results show that our method can achieve better performance than many state-of-the-art methods, such as Drive-Net, MobileVGG, Vanilla CNN, and so on.
引用
收藏
页码:140 / 156
页数:17
相关论文
共 50 条
  • [1] Effective grasp detection method based on Swin transformer
    Zhang, Jing
    Tang, Yulin
    Luo, Yusong
    Du, Yukun
    Chen, Mingju
    JOURNAL OF ELECTRONIC IMAGING, 2024, 33 (03) : 33008
  • [2] A Novel Effective Vehicle Detection Method Based on Swin Transformer in Hazy Scenes
    Sun, Zaiming
    Liu, Chang'an
    Qu, Hongquan
    Xie, Guangda
    MATHEMATICS, 2022, 10 (13)
  • [3] Driver Distraction Detection Method Based on Continuous Head Pose Estimation
    Zhao, Zuopeng
    Xia, Sili
    Xu, Xinzheng
    Zhang, Lan
    Yan, Hualin
    Xu, Yi
    Zhang, Zhongxin
    COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE, 2020, 2020
  • [4] FPT: Fine-Grained Detection of Driver Distraction Based on the Feature Pyramid Vision Transformer
    Wang, HaiTao
    Chen, Jie
    Huang, ZhiXiang
    Li, Bing
    Lv, JianMing
    Xi, JingMin
    Wu, BoCai
    Zhang, Jun
    Wu, ZhongCheng
    IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2023, 24 (02) : 1594 - 1608
  • [5] ST-LaneNet: Lane Line Detection Method Based on Swin Transformer and LaneNet
    Du, Yufeng
    Zhang, Rongyun
    Shi, Peicheng
    Zhao, Linfeng
    Zhang, Bin
    Liu, Yaming
    CHINESE JOURNAL OF MECHANICAL ENGINEERING, 2024, 37 (01)
  • [6] ST-LaneNet: Lane Line Detection Method Based on Swin Transformer and LaneNet
    Yufeng Du
    Rongyun Zhang
    Peicheng Shi
    Linfeng Zhao
    Bin Zhang
    Yaming Liu
    Chinese Journal of Mechanical Engineering, 2024, 37 (01) : 143 - 158
  • [7] ST-LaneNet: Lane Line Detection Method Based on Swin Transformer and LaneNet
    Yufeng Du
    Rongyun Zhang
    Peicheng Shi
    Linfeng Zhao
    Bin Zhang
    Yaming Liu
    Chinese Journal of Mechanical Engineering, 37
  • [8] An Enhancement of the Driver Distraction Detection and Evaluation Method Based on Computational Intelligence Algorithms
    Aksjonov, Andrei
    Nedoma, Pavel
    Vodovozov, Valery
    Petlenkov, Eduard
    2018 IEEE 16TH INTERNATIONAL CONFERENCE ON INDUSTRIAL INFORMATICS (INDIN), 2018, : 201 - 206
  • [9] Driver Distraction Behavior Detection Framework Based on the DWPose Model, Kalman Filtering, and Multi-Transformer
    Shi, Xiaofen
    IEEE ACCESS, 2024, 12 : 80579 - 80589
  • [10] Driver distraction detection using semi-supervised lightweight vision transformer
    Mohammed, Adam A. Q.
    Geng, Xin
    Wang, Jing
    Ali, Zafar
    ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2024, 129