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

Man vs. computer: benchmarking machine learning algorithms for traffic sign recognition.

J Stallkamp1, M Schlipsing, J Salmen

  • 1Institut für Neuroinformatik, Ruhr-Universität Bochum, Universitätsstrasse 150, 44780 Bochum, Germany. johannes.stallkamp@ini.rub.de

Neural Networks : the Official Journal of the International Neural Network Society
|March 8, 2012
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

Imaging for local recurrence of breast cancer.

Journal of cancer research and clinical oncology·2024
Same author

To which extent do breast cancer survivors feel well informed about disease and treatment 5 years after diagnosis?

Breast cancer research and treatment·2020
Same author

Bone-Targeted Therapy.

Geburtshilfe und Frauenheilkunde·2015
Same author

Evaluation of two different analytical methods for circulating tumor cell detection in peripheral blood of patients with primary breast cancer.

BioMed research international·2014
Same author

Shape Memory Microactuator for Surgical Instruments.

Biomedizinische Technik. Biomedical engineering·2013
Same author

Treatment of pregnancy-associated breast cancer.

Expert opinion on pharmacotherapy·2009
Same journal

Q-learning based asynchronous Boolean control networks stabilization with data loss.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

New results on prescribed-time synchronization of complex networks via intermittent control.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Variance-constrained multi-view ensemble broad network for imbalanced data.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Dynamic analysis and reliable mechanical optimization application of ring HNN effected with a memristive neuron.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

DAFF-Net: A detection and search method for small-scale low surface brightness galaxies.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Quasi-synchronization for complex networks with hybrid pinning intermittent control.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

Computer algorithms now outperform humans in recognizing German traffic signs. Convolutional neural networks (CNNs) achieved higher accuracy on a large dataset, surpassing human test subjects in a benchmark competition.

Area of Science:

  • Computer Vision
  • Machine Learning
  • Pattern Recognition

Background:

  • Traffic sign recognition is challenging for computers due to real-world variations like illumination, weather, and occlusions.
  • While humans easily recognize traffic signs, developing accurate computer systems remains a complex pattern recognition problem.
  • Existing image processing and machine learning algorithms are continuously improved, but systematic comparisons are scarce.

Purpose of the Study:

  • To assess the current performance of state-of-the-art machine learning algorithms in traffic sign classification.
  • To establish a benchmark for traffic sign recognition by comparing algorithmic performance against human capabilities.
  • To present a comprehensive, publicly available dataset for evaluating traffic sign recognition systems.

Main Methods:

Related Experiment Videos

  • Development and utilization of a public dataset containing over 50,000 images of German road signs across 43 classes.
  • Evaluation of various machine learning algorithms, with a focus on Convolutional Neural Networks (CNNs).
  • Direct comparison of algorithmic performance against human subject performance on the same dataset.

Main Results:

  • Convolutional Neural Networks (CNNs) demonstrated particularly high classification accuracies in the benchmark.
  • The study found that CNNs outperformed human test subjects in recognizing German traffic signs within the dataset.
  • The dataset and competition results provide a clear status quo for traffic sign recognition technology.

Conclusions:

  • Advanced machine learning algorithms, especially CNNs, have reached and surpassed human-level performance in traffic sign recognition.
  • The presented dataset and benchmark results are valuable resources for future research and development in autonomous driving and intelligent transportation systems.
  • Further research can build upon these findings to refine algorithms for even more robust and accurate real-world traffic sign detection and classification.