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

Association Areas of the Cortex01:21

Association Areas of the Cortex

6.1K
Association areas are regions of the cerebral cortex that do not have a specific sensory or motor function. Instead, they integrate and interpret information from various sources to enable higher cognitive processes such as memory, learning, and decision-making. Some key association areas include the following:
Prefrontal Association Area: This area is located in the frontal lobe and is involved in planning, decision-making, and moderating social behavior. It connects with primary motor areas,...
6.1K
Depth Perception and Spatial Vision01:15

Depth Perception and Spatial Vision

861
Depth perception is the ability to perceive objects three-dimensionally. It relies on two types of cues: binocular and monocular. Binocular cues depend on the combination of images from both eyes and how the eyes work together. Since the eyes are in slightly different positions, each eye captures a slightly different image. This disparity between images, known as binocular disparity, helps the brain interpret depth. When the brain compares these images, it determines the distance to an object.
861
Force Classification01:22

Force Classification

1.4K
Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
1.4K

You might also read

Related Articles

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

Sort by
Same author

"Humanoids will soon replace most human workers": A debate.

Science robotics·2026
Same author

Development and Evaluation of a Treadmill-Based Video-See-Through and Optical-See-Through Mixed Reality Systems for Obstacle Negotiation Training.

IEEE transactions on visualization and computer graphics·2024
Same author

Investigation on image signal receiving performance of photodiodes and solar panel detectors in an underground facility visible light communication system.

Optics express·2021
Same author

A Multimodal, Adjustable Sensitivity, Digital 3-Axis Skin Sensor Module.

Sensors (Basel, Switzerland)·2020
Same author

A Preliminary Experimental Analysis of In-Pipe Image Transmission Based on Visible Light Relay Communication.

Sensors (Basel, Switzerland)·2019
Same author

A Coordinated Wheeled Gas Pipeline Robot Chain System Based on Visible Light Relay Communication and Illuminance Assessment.

Sensors (Basel, Switzerland)·2019

Related Experiment Video

Updated: Sep 1, 2025

Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery
05:12

Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery

Published on: August 12, 2021

2.1K

Single Camera Face Position-Invariant Driver's Gaze Zone Classifier Based on Frame-Sequence Recognition Using 3D

Catherine Lollett1, Mitsuhiro Kamezaki2, Shigeki Sugano1

  • 1Graduate School of Creative Science and Engineering, Waseda University, Tokyo 169-8555, Japan.

Sensors (Basel, Switzerland)
|August 12, 2022
PubMed
Summary

Estimating driver gaze is challenging due to varying conditions. Three-dimensional Convolutional Neural Networks (3D CNNs) improve head pose estimation, outperforming 2D CNNs for driver monitoring systems.

Keywords:
convolutional neural networksdriver monitoringgaze classification

More Related Videos

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

4.0K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

623

Related Experiment Videos

Last Updated: Sep 1, 2025

Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery
05:12

Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery

Published on: August 12, 2021

2.1K
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

4.0K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

623

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Automotive Safety

Background:

  • Accurate driver gaze estimation is crucial for automotive safety but faces challenges like occlusions, illumination variations, and diverse head poses.
  • Per-frame recognition systems lack temporal context, leading to misclassifications in dynamic driving scenarios.
  • Monitoring driver attention to critical areas (e.g., mirrors, navigation) is essential for preventing accidents.

Purpose of the Study:

  • To develop and evaluate a robust head pose estimation method for drivers under various real-world conditions.
  • To reduce misclassifications in driver gaze detection, particularly when the driver's face is at different distances from the camera.
  • To compare the performance of 3D Convolutional Neural Networks (CNNs) against 2D CNNs for driver head direction detection.

Main Methods:

  • Implementation and evaluation of a head pose detection model utilizing Three-dimensional Convolutional Neural Networks (3D CNNs).
  • 3D CNNs were employed to extract spatio-temporal features from adjacent video frames, capturing motion dynamics.
  • The model was trained to detect head direction towards common driver-checked regions at varying camera distances.

Main Results:

  • The 3D CNN model achieved a mean average recall of 87.02%.
  • The baseline 2D CNN model achieved a mean average recall of 74.96%.
  • The proposed 3D CNN approach demonstrated superior performance compared to the 2D CNN per-frame recognition method.

Conclusions:

  • 3D CNNs effectively capture spatio-temporal information, enhancing driver head pose estimation accuracy in challenging driving scenarios.
  • The proposed 3D CNN-based method significantly outperforms 2D CNNs for detecting driver head direction at varying distances.
  • This approach offers a promising solution for improving driver monitoring systems and enhancing road safety.