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 Experiment Video

Updated: Jun 20, 2026

Driving Simulation in the Clinic: Testing Visual Exploratory Behavior in Daily Life Activities in Patients with Visual Field Defects
11:12

Driving Simulation in the Clinic: Testing Visual Exploratory Behavior in Daily Life Activities in Patients with Visual Field Defects

Published on: September 18, 2012

Naturalistic driving data extraction and processing for studying driver head scanning behavior at intersections.

Shrinivas Pundlik1,2, Seonggyu Choe3,4, Patrick Baker3,4

  • 1Schepens Eye Research Institute of Mass Eye & Ear, 20 Staniford Street, Boston, MA, 02114, USA. Shrinivas_Pundlik@meei.harvard.edu.

Scientific Reports
|June 18, 2026
PubMed
Summary

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

Driving with autism spectrum disorder: Exploring the impact of tactile hazard warnings on gaze behavior and hazard responses.

Vision research·2026
Same author

A randomized crossover clinical trial of multi-periscopic and Fresnel peripheral prism glasses for hemianopia.

Optometry and vision science : official publication of the American Academy of Optometry·2026
Same author

Reinforcement-Based Head Scan Training for Drivers With Homonymous Visual Field Loss: Improves Blind-Side Detection.

Archives of physical medicine and rehabilitation·2026
Same author

Head Scanning by Drivers With Left Homonymous Visual Field Loss: A Naturalistic Driving Pilot Study.

The American journal of occupational therapy : official publication of the American Occupational Therapy Association·2026
Same author

Use and preferences of advanced driver assistance systems by drivers with homonymous visual field loss.

Disability and rehabilitation. Assistive technology·2026
Same author

Real-world driving behaviors in individuals with homonymous visual field loss: insights from a naturalistic driving study.

Accident; analysis and prevention·2026
Same journal

Correction: A method for supervoxel-wise association studies of age and other non-imaging variables from coronary computed tomography angiograms.

Scientific reports·2026
Same journal

Poly(bromophenol blue)/CoSn(OH)<sub>6</sub> cubic particles modified pencil graphite electrode for electrochemical determination of diphenhydramine.

Scientific reports·2026
Same journal

Dietary Chlorella, Spirulina, and acidifier modulate jejunal cytokine-related gene expression in broiler chickens.

Scientific reports·2026
Same journal

Perceived physical activity barriers in university students: associations with fatigue and eating behaviours.

Scientific reports·2026
Same journal

Refuge limitation structures habitat use in agricultural landscapes: evidence from Sunda pangolins.

Scientific reports·2026
Same journal

Lightweight stateless transaction verification with outsourced witness updates for UTXO blockchains.

Scientific reports·2026
See all related articles
This summary is machine-generated.

This study introduces an automated pipeline for analyzing naturalistic driving (ND) data at intersections. The system accurately characterizes intersection scenes and driver behavior, enabling deeper insights into real-world driving.

Area of Science:

  • Transportation Engineering
  • Human Factors and Ergonomics
  • Computer Vision and AI

Background:

  • Naturalistic driving (ND) studies provide unparalleled insights into real-world driver behavior.
  • Traditional analysis of ND data is labor-intensive and time-consuming.
  • Characterizing complex intersection environments and driver interactions presents significant challenges.

Purpose of the Study:

  • To develop and validate an automated data processing pipeline for naturalistic driving (ND) studies.
  • To characterize intersection scenes and driver behaviors using in-car and forward-facing video data.
  • To enable the automated analysis of large-scale ND datasets for enhanced driver behavior research.

Main Methods:

  • An in-car recording system captured vehicle speed, location, cabin, and front-scene videos.
Keywords:
Deep learning computer vision modelsDriving conditions characterizationHead scanning at intersectionsIntersection bounds detectionNaturalistic drivingVisual impairment

More Related Videos

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

Related Experiment Videos

Last Updated: Jun 20, 2026

Driving Simulation in the Clinic: Testing Visual Exploratory Behavior in Daily Life Activities in Patients with Visual Field Defects
11:12

Driving Simulation in the Clinic: Testing Visual Exploratory Behavior in Daily Life Activities in Patients with Visual Field Defects

Published on: September 18, 2012

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

  • Intersection events were identified, and video segments were processed for scene characteristics (signage, maneuvers, traffic density).
  • An AI model estimated driver head pose for wide-angle head turns; performance was evaluated against manual annotations.

    • Main Results:

    • The pipeline achieved high accuracy in detecting signage (99%) and vehicle maneuvers (95%).
    • Precise estimation of intersection entry/exit with a median error of 1.1 meters and 0.23 seconds.
    • Strong correlation (R=0.73) between estimated and annotated traffic density; head pose estimation showed a mean absolute error of 6.75°.

    Conclusions:

    • The developed automated pipeline significantly enhances the efficiency of analyzing naturalistic driving data.
    • This approach allows for the detailed study of driver behaviors at intersections, previously unachievable.
    • The system holds potential for large-scale deployment in traffic safety and driver behavior research.