Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Graph-Tabular Latent Fusion for Non-Contact Body Temperature Prediction from Thermal Facial Landmarks.

Sensors (Basel, Switzerland)·2026
Same author

Diabetic retinopathy classification network with multi-frequency contextual attention module.

Medical engineering & physics·2026
Same author

Marine Oil Pollution Monitoring Based on a Morphological Attention U-Net Using SAR Images.

Sensors (Basel, Switzerland)·2024
Same author

Mobility-Aware Resource Allocation in IoRT Network for Post-Disaster Communications with Parameterized Reinforcement Learning.

Sensors (Basel, Switzerland)·2023
Same author

Classification of basal stem rot using deep learning: a review of digital data collection and palm disease classification methods.

PeerJ. Computer science·2023
Same author

Correction: Alkhaleefah et al. Connected-SegNets: A Deep Learning Model for Breast Tumor Segmentation from X-ray Images. <i>Cancers</i> 2022, <i>14</i>, 4030.

Cancers·2023

Related Experiment Video

Updated: Oct 27, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

4.6K

Optimally-Weighted Image-Pose Approach (OWIPA) for Distracted Driver Detection and Classification.

Hong Vin Koay1, Joon Huang Chuah1, Chee-Onn Chow1

  • 1Department of Electrical Engineering, Faculty of Engineering, University of Malaya, Kuala Lumpur 50603, Malaysia.

Sensors (Basel, Switzerland)
|July 24, 2021
PubMed
Summary

This study introduces a new method for detecting distracted drivers using pose estimation and an ensemble of ResNets. The Optimally-weighted Image-Pose Approach (OWIPA) achieved 94.28% accuracy, improving driver safety.

Keywords:
convolutional neural network (CNN)deep learningdistraction classificationdistraction detectionintellegent transport system (ITS)optimally-weighted image-pose approach (OWIPA)pose estimation

More Related Videos

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.9K
Tactile Vibrating Toolkit and Driving Simulation Platform for Driving-Related Research
07:15

Tactile Vibrating Toolkit and Driving Simulation Platform for Driving-Related Research

Published on: December 18, 2020

4.7K

Related Experiment Videos

Last Updated: Oct 27, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

4.6K
Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.9K
Tactile Vibrating Toolkit and Driving Simulation Platform for Driving-Related Research
07:15

Tactile Vibrating Toolkit and Driving Simulation Platform for Driving-Related Research

Published on: December 18, 2020

4.7K

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Road Safety

Background:

  • Distracted driving is a major cause of road accidents.
  • Existing distraction detection methods primarily use convolutional neural networks (CNNs) and recurrent neural networks (RNNs).
  • Research on detecting distracted drivers using pose estimation techniques is limited.

Purpose of the Study:

  • To develop an effective distracted driver detection system utilizing pose estimation.
  • To introduce the Optimally-weighted Image-Pose Approach (OWIPA), an ensemble of ResNets for enhanced distraction classification.
  • To evaluate the performance of the proposed approach on a standard distracted driver dataset.

Main Methods:

  • Generated pose estimation images using HRNet and ResNet.
  • Employed ResNet101 for original image classification and ResNet50 for pose estimation image classification.
  • Implemented an ensemble method (OWIPA) that optimally weights predictions from both models using grid search.

Main Results:

  • The proposed OWIPA achieved an accuracy of 94.28% on the AUC Distracted Driver Dataset.
  • The ensemble approach demonstrated superior performance compared to individual model predictions.
  • Pose estimation significantly contributed to improving the accuracy of distracted driver detection.

Conclusions:

  • The OWIPA method, combining original and pose estimation images, is highly effective for distracted driver detection.
  • Pose estimation offers a promising avenue for advancing driver safety technologies.
  • This research provides a robust framework for developing next-generation driver monitoring systems.