Traffic sign recognition with multi-scale convolutional networks

Pierre Sermanet; Yann Lecun

doi:10.1109/IJCNN.2011.6033589

Traffic sign recognition with multi-scale convolutional networks

Pierre Sermanet, Yann Lecun

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

We apply Convolutional Networks (ConvNets) to the task of traffic sign classification as part of the GTSRB competition. ConvNets are biologically-inspired multi-stage architectures that automatically learn hierarchies of invariant features. While many popular vision approaches use hand-crafted features such as HOG or SIFT, ConvNets learn features at every level from data that are tuned to the task at hand. The traditional ConvNet architecture was modified by feeding 1^nd stage features in addition to 2^nd stage features to the classifier. The system yielded the 2nd-best accuracy of 98.97% during phase I of the competition (the best entry obtained 98.98%), above the human performance of 98.81%, using 3232 color input images. Experiments conducted after phase 1 produced a new record of 99.17% by increasing the network capacity, and by using greyscale images instead of color. Interestingly, random features still yielded competitive results (97.33%).

Original language	English (US)
Title of host publication	2011 International Joint Conference on Neural Networks, IJCNN 2011 - Final Program
Pages	2809-2813
Number of pages	5
DOIs	https://doi.org/10.1109/IJCNN.2011.6033589
State	Published - 2011
Event	2011 International Joint Conference on Neural Network, IJCNN 2011 - San Jose, CA, United States Duration: Jul 31 2011 → Aug 5 2011

Publication series

Name	Proceedings of the International Joint Conference on Neural Networks

Other

Other	2011 International Joint Conference on Neural Network, IJCNN 2011
Country	United States
City	San Jose, CA
Period	7/31/11 → 8/5/11

ASJC Scopus subject areas

Software
Artificial Intelligence

Access to Document

10.1109/IJCNN.2011.6033589

Fingerprint Dive into the research topics of 'Traffic sign recognition with multi-scale convolutional networks'. Together they form a unique fingerprint.

Cite this

Traffic sign recognition with multi-scale convolutional networks. / Sermanet, Pierre; Lecun, Yann.

2011 International Joint Conference on Neural Networks, IJCNN 2011 - Final Program. 2011. p. 2809-2813 6033589 (Proceedings of the International Joint Conference on Neural Networks).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Sermanet, P & Lecun, Y 2011, Traffic sign recognition with multi-scale convolutional networks. in 2011 International Joint Conference on Neural Networks, IJCNN 2011 - Final Program., 6033589, Proceedings of the International Joint Conference on Neural Networks, pp. 2809-2813, 2011 International Joint Conference on Neural Network, IJCNN 2011, San Jose, CA, United States, 7/31/11. https://doi.org/10.1109/IJCNN.2011.6033589

@inproceedings{73987af8e88944228e60360906075114,

title = "Traffic sign recognition with multi-scale convolutional networks",

abstract = "We apply Convolutional Networks (ConvNets) to the task of traffic sign classification as part of the GTSRB competition. ConvNets are biologically-inspired multi-stage architectures that automatically learn hierarchies of invariant features. While many popular vision approaches use hand-crafted features such as HOG or SIFT, ConvNets learn features at every level from data that are tuned to the task at hand. The traditional ConvNet architecture was modified by feeding 1nd stage features in addition to 2nd stage features to the classifier. The system yielded the 2nd-best accuracy of 98.97% during phase I of the competition (the best entry obtained 98.98%), above the human performance of 98.81%, using 3232 color input images. Experiments conducted after phase 1 produced a new record of 99.17% by increasing the network capacity, and by using greyscale images instead of color. Interestingly, random features still yielded competitive results (97.33%).",

author = "Pierre Sermanet and Yann Lecun",

year = "2011",

doi = "10.1109/IJCNN.2011.6033589",

language = "English (US)",

isbn = "9781457710865",

series = "Proceedings of the International Joint Conference on Neural Networks",

pages = "2809--2813",

booktitle = "2011 International Joint Conference on Neural Networks, IJCNN 2011 - Final Program",

}

TY - GEN

T1 - Traffic sign recognition with multi-scale convolutional networks

AU - Sermanet, Pierre

AU - Lecun, Yann

PY - 2011

Y1 - 2011

N2 - We apply Convolutional Networks (ConvNets) to the task of traffic sign classification as part of the GTSRB competition. ConvNets are biologically-inspired multi-stage architectures that automatically learn hierarchies of invariant features. While many popular vision approaches use hand-crafted features such as HOG or SIFT, ConvNets learn features at every level from data that are tuned to the task at hand. The traditional ConvNet architecture was modified by feeding 1nd stage features in addition to 2nd stage features to the classifier. The system yielded the 2nd-best accuracy of 98.97% during phase I of the competition (the best entry obtained 98.98%), above the human performance of 98.81%, using 3232 color input images. Experiments conducted after phase 1 produced a new record of 99.17% by increasing the network capacity, and by using greyscale images instead of color. Interestingly, random features still yielded competitive results (97.33%).

AB - We apply Convolutional Networks (ConvNets) to the task of traffic sign classification as part of the GTSRB competition. ConvNets are biologically-inspired multi-stage architectures that automatically learn hierarchies of invariant features. While many popular vision approaches use hand-crafted features such as HOG or SIFT, ConvNets learn features at every level from data that are tuned to the task at hand. The traditional ConvNet architecture was modified by feeding 1nd stage features in addition to 2nd stage features to the classifier. The system yielded the 2nd-best accuracy of 98.97% during phase I of the competition (the best entry obtained 98.98%), above the human performance of 98.81%, using 3232 color input images. Experiments conducted after phase 1 produced a new record of 99.17% by increasing the network capacity, and by using greyscale images instead of color. Interestingly, random features still yielded competitive results (97.33%).

UR - http://www.scopus.com/inward/record.url?scp=80054736963&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80054736963&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2011.6033589

DO - 10.1109/IJCNN.2011.6033589

M3 - Conference contribution

AN - SCOPUS:80054736963

SN - 9781457710865

T3 - Proceedings of the International Joint Conference on Neural Networks

SP - 2809

EP - 2813

BT - 2011 International Joint Conference on Neural Networks, IJCNN 2011 - Final Program

T2 - 2011 International Joint Conference on Neural Network, IJCNN 2011

Y2 - 31 July 2011 through 5 August 2011

ER -