Multi-column deep neural network for traffic sign classification

Dan Cireşan; Ueli Meier; Jonathan Masci; Jürgen Schmidhuber

doi:10.1016/j.neunet.2012.02.023

Multi-column deep neural network for traffic sign classification

Dan Cireşan, Ueli Meier, Jonathan Masci, Jürgen Schmidhuber

Research output: Contribution to journal › Article › peer-review

806 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 language	English (US)
Pages (from-to)	333-338
Number of pages	6
Journal	Neural Networks
Volume	32
DOIs	https://doi.org/10.1016/j.neunet.2012.02.023
State	Published - Aug 1 2012
Externally published	Yes

Bibliographical note

Generated from Scopus record by KAUST IRTS on 2022-09-14

ASJC Scopus subject areas

Artificial Intelligence
Cognitive Neuroscience

Access to Document

10.1016/j.neunet.2012.02.023

Cite this

@article{8ae353ce1bd64d43ba6afea0415d8e05,

title = "Multi-column deep neural network for traffic sign classification",

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. {\textcopyright} 2012 Elsevier Ltd.",

author = "Dan Cire{\c s}an and Ueli Meier and Jonathan Masci and J{\"u}rgen Schmidhuber",

note = "Generated from Scopus record by KAUST IRTS on 2022-09-14",

year = "2012",

month = aug,

day = "1",

doi = "10.1016/j.neunet.2012.02.023",

language = "English (US)",

volume = "32",

pages = "333--338",

journal = "Neural Networks",

issn = "0893-6080",

publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Multi-column deep neural network for traffic sign classification

AU - Cireşan, Dan

AU - Meier, Ueli

AU - Masci, Jonathan

AU - Schmidhuber, Jürgen

N1 - Generated from Scopus record by KAUST IRTS on 2022-09-14

PY - 2012/8/1

Y1 - 2012/8/1

N2 - 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.

AB - 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.

UR - https://linkinghub.elsevier.com/retrieve/pii/S0893608012000524

UR - http://www.scopus.com/inward/record.url?scp=84861776914&partnerID=8YFLogxK

U2 - 10.1016/j.neunet.2012.02.023

DO - 10.1016/j.neunet.2012.02.023

M3 - Article

SN - 0893-6080

VL - 32

SP - 333

EP - 338

JO - Neural Networks

JF - Neural Networks

ER -

Multi-column deep neural network for traffic sign classification

Abstract

Bibliographical note

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this