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

Depth Perception and Spatial Vision01:15

Depth Perception and Spatial Vision

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.

You might also read

Related Articles

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

Sort by
Same author

A Comprehensive Exploration of Fidelity Quantification in Computer-Generated Images.

Sensors (Basel, Switzerland)·2024
Same author

Impact Evaluation of Cyberattacks on Connected and Automated Vehicles in Mixed Traffic Flow and Its Resilient and Robust Control Strategy.

Sensors (Basel, Switzerland)·2023
Same author

Deep Learning Sensor Fusion for Autonomous Vehicle Perception and Localization: A Review.

Sensors (Basel, Switzerland)·2020
Same author

Fault Detection and Isolation via the Interacting Multiple Model Approach Applied to Drive-By-Wire Vehicles.

Sensors (Basel, Switzerland)·2018

Related Experiment Video

Updated: Jun 13, 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

Scenario-Driven Synthetic Data Generation Framework for Visual Perception Evaluation Under Adverse Driving

Wei Xu1,2, Dominique Gruyer1, Alexandra Duminil1

  • 1Perceptions, Interactions, Behaviour and Simulations of Road and Street Users Laboratory (PICS-L), Department of Components and Systems (COSYS), Gustave Eiffel University, 77454 Marne-la-Vallée, France.

Sensors (Basel, Switzerland)
|June 12, 2026
PubMed
Summary

This study introduces a flexible framework for creating synthetic datasets to evaluate autonomous vehicle visual perception systems. The generated data improves model robustness and generalization, overcoming real-world data collection challenges.

Keywords:
ODD and OEDRadverse conditionsautonomous drivingscenario-based frameworksynthetic datasetsvisual perception evaluation

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

A Gaze-Contingent Display Framework for Perceptual Learning Research with Simulated Central Vision Loss
07:12

A Gaze-Contingent Display Framework for Perceptual Learning Research with Simulated Central Vision Loss

Published on: April 11, 2025

Related Experiment Videos

Last Updated: Jun 13, 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

A Gaze-Contingent Display Framework for Perceptual Learning Research with Simulated Central Vision Loss
07:12

A Gaze-Contingent Display Framework for Perceptual Learning Research with Simulated Central Vision Loss

Published on: April 11, 2025

Area of Science:

  • Computer Vision
  • Robotics
  • Artificial Intelligence

Background:

  • Autonomous vehicle development requires extensive visual perception data across varied conditions.
  • Real-world data collection is expensive, time-consuming, and often impractical for diverse scenarios.
  • Existing methods may not adequately cover the operational design domains of automated driving functions.

Purpose of the Study:

  • To propose a modular, scenario-driven framework for generating synthetic datasets for evaluating visual perception systems.
  • To ensure the generated datasets align with automated driving functions' operational boundaries and detection-response requirements.
  • To demonstrate the framework's flexibility and effectiveness through instantiation with specific platforms.

Main Methods:

  • A three-stage framework: scenario configuration, simulation-based data generation, and post-processing.
  • Integration with Pro-SiVIC and RTMaps for data generation and management.
  • Evaluation of synthetic data fidelity and perception performance against real-world conditions.
  • Training perception models using baseline, transfer-learning, and mixed-training strategies.

Main Results:

  • The generated synthetic dataset exhibits high quality and fidelity.
  • The synthetic data effectively evaluates visual perception functions under simulated adverse weather.
  • Training with synthetic data enhances the robustness and generalization capabilities of perception models.
  • Experimental results confirm the framework's utility in improving model performance.

Conclusions:

  • The proposed framework provides a viable solution for generating high-quality synthetic data for autonomous vehicle perception systems.
  • Synthetic data generated by this framework is effective for evaluating perception performance and improving model robustness.
  • This approach addresses the limitations of real-world data collection, facilitating more comprehensive system development and validation.