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

Real-time traffic sign recognition based on a general purpose GPU and deep-learning.

Kwangyong Lim1, Yongwon Hong1, Yeongwoo Choi2

  • 1Department of Computer Science, Yonsei University, 50 Yonsei-ro Seodaemun-gu, Seoul, Republic of Korea.

Plos One
|March 7, 2017
PubMed
Summary

This study introduces a robust real-time traffic sign detection and recognition system using General Purpose Graphics Processing Units (GPGPU). The method excels in varying light conditions, achieving high accuracy for safer autonomous driving.

Related Concept Videos

Parallel Processing01:20

Parallel Processing

839
The brain processes sensory information rapidly due to parallel processing, which involves sending data across multiple neural pathways at the same time. This method allows the brain to manage various sensory qualities, such as shapes, colors, movements, and locations, all concurrently. For instance, when observing a forest landscape, the brain simultaneously processes the movement of leaves, the shapes of trees, the depth between them, and the various shades of green. This enables a quick and...
839

You might also read

Related Articles

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

Sort by
Same author

A Review on the Current Research and Industrialization Status of Edible Insect Protein.

Food science of animal resources·2026
Same author

Market Status of Meat Analogs and Their Impact on Livestock Industries.

Food science of animal resources·2026
Same author

The Color-Developing Methods for Cultivated Meat and Meat Analogues: A Mini-Review.

Food science of animal resources·2026
Same author

Current Research, Industrialization Status, and Future Perspective of Cultured Meat.

Food science of animal resources·2026
Same author

Study on the Digestion-Induced Changes in the Characteristics and Bioactivity of Korean Native and Overseas Cattle-Derived Peptides.

Food science of animal resources·2026
Same author

Current Technologies and Future Perspective in Meat Analogs Made from Plant, Insect, and Mycoprotein Materials: A Review.

Food science of animal resources·2026

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Autonomous Systems

Background:

  • Traditional traffic sign recognition methods struggle with illumination variations.
  • Low light and high light variance conditions limit the effectiveness of existing algorithms.
  • Real-time processing is crucial for practical applications like autonomous driving.

Purpose of the Study:

  • To develop a robust real-time traffic sign detection and recognition system.
  • To overcome limitations of previous methods in adverse illumination conditions.
  • To enhance processing speed using GPGPU acceleration.

Main Methods:

  • Implemented a General Purpose Graphics Processing Unit (GPGPU)-based approach for real-time processing.
  • Developed a hierarchical model for region detection and recognition.

Related Experiment Videos

  • Ensured robustness against illumination changes through a novel algorithm design.

    • Main Results:

    • Achieved stable and accurate traffic sign detection and recognition in low illumination environments.
    • Demonstrated real-time performance for both detection and hierarchical recognition.
    • Attained a 0.97 F1-score on a dataset adhering to Vienna Convention traffic rules (Germany, South Korea).

    Conclusions:

    • The proposed GPGPU-based method offers a significant improvement for real-time traffic sign recognition.
    • The system's robustness to illumination changes enhances its reliability for autonomous systems.
    • High F1-score validates the effectiveness of the hierarchical model and GPGPU acceleration.