Gaze Zone Classification for Driving Studies Using YOLOv8 Image Classification

被引:0
|
作者
Hermens, Frouke [1 ]
Anker, Wim [1 ]
Noten, Charmaine [1 ]
机构
[1] Open Univ Netherlands, Dept Comp Sci, Valkenburgerweg 177, NL-6419 AT Heerlen, Netherlands
关键词
gaze zone; drivers; YOLOv8; image classification; GLANCE BEHAVIOR; HEAD POSE; DRIVERS; NETWORKS; TRACKING; CRASHES; EYES;
D O I
10.3390/s24227254
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
Gaze zone detection involves estimating where drivers look in terms of broad categories (e.g., left mirror, speedometer, rear mirror). We here specifically focus on the automatic annotation of gaze zones in the context of road safety research, where the system can be tuned to specific drivers and driving conditions, so that an easy to use but accurate system may be obtained. We show with an existing dataset of eye region crops (nine gaze zones) and two newly collected datasets (12 and 10 gaze zones) that image classification with YOLOv8, which has a simple command line interface, achieves near-perfect accuracy without any pre-processing of the images, as long as a model is trained on the driver and conditions for which annotation is required (such as whether the drivers wear glasses or sunglasses). We also present two apps to collect the training images and to train and apply the YOLOv8 models. Future research will need to explore how well the method extends to real driving conditions, which may be more variable and more difficult to annotate for ground truth labels.
引用
收藏
页数:21
相关论文
共 50 条
  • [31] Detection of Elbow OCD in the Ultrasound Image by Artificial Intelligence Using YOLOv8
    Inui, Atsuyuki
    Mifune, Yutaka
    Nishimoto, Hanako
    Mukohara, Shintaro
    Fukuda, Sumire
    Kato, Tatsuo
    Furukawa, Takahiro
    Tanaka, Shuya
    Kusunose, Masaya
    Takigami, Shunsaku
    Ehara, Yutaka
    Kuroda, Ryosuke
    APPLIED SCIENCES-BASEL, 2023, 13 (13):
  • [32] Strawberry Detection and Ripeness Classification Using YOLOv8+ Model and Image Processing Method
    Wang, Chenglin
    Wang, Haoming
    Han, Qiyu
    Zhang, Zhaoguo
    Kong, Dandan
    Zou, Xiangjun
    AGRICULTURE-BASEL, 2024, 14 (05):
  • [33] An improved YOLOv8 algorithm for small object detection in autonomous driving
    Cao, Jie
    Zhang, Tong
    Hou, Liang
    Nan, Ning
    JOURNAL OF REAL-TIME IMAGE PROCESSING, 2024, 21 (04)
  • [34] SES-YOLOv8n: automatic driving object detection algorithm based on improved YOLOv8
    Sun, Yang
    Zhang, Yuhang
    Wang, Haiyang
    Guo, Jianhua
    Zheng, Jiushuai
    Ning, Haonan
    SIGNAL IMAGE AND VIDEO PROCESSING, 2024, 18 (05) : 3983 - 3992
  • [35] Observational Supervision for Medical Image Classification Using Gaze Data
    Saab, Khaled
    Hooper, Sarah M.
    Sohoni, Nimit S.
    Parmar, Jupinder
    Pogatchnik, Brian
    Wu, Sen
    Dunnmon, Jared A.
    Zhang, Hongyang R.
    Rubin, Daniel
    Re, Christopher
    MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2021, PT II, 2021, 12902 : 603 - 614
  • [36] YOLOv8-SAB: Terahertz Image Detection Network Based on Shuffle Attention and YOLOv8
    Jiang, Yu
    Li, Yizhang
    Wang, Zhongmin
    Qi, Feng
    Wang, Fenggui
    Liu, Yongsheng
    Chen, Tao
    IEEE ACCESS, 2024, 12 : 133328 - 133338
  • [37] TOFD Image Features Recognition Based on Improved YOLOv8
    Ren, Xukai
    Du, Xiyong
    Yu, Huanwei
    Chang, Zhiyu
    Wang, Guobiao
    2024 IEEE 19TH CONFERENCE ON INDUSTRIAL ELECTRONICS AND APPLICATIONS, ICIEA 2024, 2024,
  • [38] Fruit ripeness identification using YOLOv8 model
    Bingjie Xiao
    Minh Nguyen
    Wei Qi Yan
    Multimedia Tools and Applications, 2024, 83 : 28039 - 28056
  • [39] Fruit ripeness identification using YOLOv8 model
    Xiao, Bingjie
    Nguyen, Minh
    Yan, Wei Qi
    MULTIMEDIA TOOLS AND APPLICATIONS, 2024, 83 (09) : 28039 - 28056
  • [40] Detecting chestnuts using improved lightweight YOLOv8
    Li M.
    Xiao Y.
    Zong W.
    Song B.
    Nongye Gongcheng Xuebao/Transactions of the Chinese Society of Agricultural Engineering, 2024, 40 (01): : 201 - 209