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 Videos

Ensuring SOTIF: Enhanced object detection techniques for autonomous driving.

Sifen Wang1, Zhangyu Wang2, Sheng Hong3

  • 1School of Transportation Science and Engineering, Beihang University, China; Beijing Institute of Control Engineering, Beijing 100190, China.

Accident; Analysis and Prevention
|May 10, 2025
PubMed
Summary
This summary is machine-generated.

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

A novel copper oxide/titanium membrane integrated with peroxymonosulfate activation for efficient phenolic pollutants degradation.

Journal of colloid and interface science·2023
Same author

SARS-CoV-2 main protease cleaves MAGED2 to antagonize host antiviral defense.

mBio·2023
Same author

The Effect of Low-Dose Esketamine on Postoperative Neurocognitive Dysfunction in Elderly Patients Undergoing General Anesthesia for Gastrointestinal Tumors: A Randomized Controlled Trial.

Drug design, development and therapy·2023
Same author

The mechanisms of Huangqi Guizhi Wuwu decoction in treating ischaemic stroke based on network pharmacology and experiment verification.

Pharmaceutical biology·2023
Same author

The tumor-stroma ratio and the immune microenvironment improve the prognostic prediction of pancreatic ductal adenocarcinoma.

Discover oncology·2023
Same author

Chromosome-level Asian elephant genome assembly and comparative genomics of long-lived mammals reveal the common substitutions for cancer resistance.

Aging cell·2023
Same journal

Assessing autonomous driving performance and environmental influencing factors using real-world operational trajectory data.

Accident; analysis and prevention·2026
Same journal

Multi-scale modeling of electric vehicle fatal crash risk: uncovering spatial heterogeneity and infrastructure-land use coupling mechanisms.

Accident; analysis and prevention·2026
Same journal

Differential sensitivity of self-reported driving and collision measures to aspects of shiftwork, sleep, and fatigue.

Accident; analysis and prevention·2026
Same journal

Delving into the visual attention of pedestrians during street crossing under time pressure: An eye-tracking approach.

Accident; analysis and prevention·2026
Same journal

Differentiating high-frequency and high-severity hotspots: A robust risk-evolution-volume (REV) framework.

Accident; analysis and prevention·2026
Same journal

Modeling takeover decisions in driving automation: a multilevel drift-diffusion model (MDDM) framework integrating human, system, and environmental factors.

Accident; analysis and prevention·2026
See all related articles

This study enhances autonomous driving safety by improving object detection. A modified YOLOv5 algorithm with prediction extension boxes boosts perception accuracy and target coverage, addressing Safety of the Intended Functionality concerns.

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Autonomous Systems

Background:

  • Neural networks in autonomous driving face interpretability challenges, impacting Safety of the Intended Functionality (SOTIF).
  • Current object detection methods may not always guarantee accurate perceptual results, posing risks in safety-critical applications.
  • Ensuring reliable perception is crucial for the safe operation of autonomous vehicles.

Purpose of the Study:

  • To propose an enhanced object detection algorithm for autonomous driving.
  • To improve the accuracy and reliability of perception systems.
  • To address and mitigate Safety of the Intended Functionality (SOTIF) issues arising from perception inaccuracies.

Main Methods:

  • Utilized the YOLOv5 one-stage object detection algorithm as a baseline.
Keywords:
Autonomous DrivingObject detectionPrediction extension boxSOTIF

Related Experiment Videos

  • Introduced a novel prediction extension box to the YOLOv5 architecture.
  • Incorporated considerations for target coverage range and redundancy in the detection process.

    • Main Results:

    • The proposed algorithm significantly increased the coverage range of detected targets.
    • The enhanced model demonstrated improved accuracy in the perception system.
    • The modifications contributed to guaranteeing the safety of image perception.

    Conclusions:

    • The developed object detection algorithm enhances perception safety in autonomous driving.
    • The prediction extension box effectively addresses SOTIF concerns by improving target detection.
    • This approach offers a promising solution for safer autonomous vehicle perception systems.