Multi-column deep neural network for traffic sign classification

Dan Cireşan, Ueli Meier, Jonathan Masci, Jürgen Schmidhuber

Research output: Contribution to journalArticlepeer-review

689 Scopus citations

Abstract

We describe the approach that won the final phase of the German traffic sign recognition benchmark. Our method is the only one that achieved a better-than-human recognition rate of 99.46%. We use a fast, fully parameterizable GPU implementation of a Deep Neural Network (DNN) that does not require careful design of pre-wired feature extractors, which are rather learned in a supervised way. Combining various DNNs trained on differently preprocessed data into a Multi-Column DNN (MCDNN) further boosts recognition performance, making the system insensitive also to variations in contrast and illumination. © 2012 Elsevier Ltd.
Original languageEnglish (US)
Pages (from-to)333-338
Number of pages6
JournalNeural Networks
Volume32
DOIs
StatePublished - Aug 1 2012
Externally publishedYes

ASJC Scopus subject areas

  • Artificial Intelligence
  • Cognitive Neuroscience

Fingerprint

Dive into the research topics of 'Multi-column deep neural network for traffic sign classification'. Together they form a unique fingerprint.

Cite this