Multi-column deep neural network for traffic sign classification

被引：631

作者：

Ciresan, Dan ^{[1
]}

Meier, Ueli ^{[1
]}

Masci, Jonathan ^{[1
]}

Schmidhuber, Juergen ^{[1
]}

机构：

[1] IDSIA USI SUPSI Galleria 2, CH-6928 Manno Lugano, Switzerland

来源：

NEURAL NETWORKS | 2012年 / 32卷

关键词：

Deep neural networks; Image classification; Traffic signs; Image preprocessing; OBJECT RECOGNITION; MODEL;

D O I：

10.1016/j.neunet.2012.02.023

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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. (C) 2012 Elsevier Ltd. All rights reserved.

引用

页码：333 / 338

页数：6

共 27 条

[1]

[Anonymous], P INT C ART NEUR NET

[2]

[Anonymous], 2010, VERS 7 10 0 R2010A

[3]

[Anonymous], 2011, 22 INT JT C ART INT, DOI 10.5555/2283516.2283603

[4]

[Anonymous], 2006, Pattern recognition and machine learning

[5]

Behnke S., 2003, Lecture Notes in Computer Science, V2766

[6]

Ciresan D, 2011, 2011 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), P1918, DOI 10.1109/IJCNN.2011.6033458

[7] Deep, Big, Simple Neural Nets for Handwritten Digit Recognition [J].

Ciresan, Dan Claudiu ;

Meier, Ueli ;

Gambardella, Luca Maria ;

Schmidhuber, Juergen .

NEURAL COMPUTATION, 2010, 22 (12) :3207-3220

[8]

Duin RPW, 2002, INT C PATT RECOG, P765, DOI 10.1109/ICPR.2002.1048415

[9] NEOCOGNITRON - A SELF-ORGANIZING NEURAL NETWORK MODEL FOR A MECHANISM OF PATTERN-RECOGNITION UNAFFECTED BY SHIFT IN POSITION [J].

FUKUSHIMA, K .

BIOLOGICAL CYBERNETICS, 1980, 36 (04) :193-202

[10] IMPROVING MODEL ACCURACY USING OPTIMAL LINEAR-COMBINATIONS OF TRAINED NEURAL NETWORKS [J].

HASHEM, S ;

SCHMEISER, B .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1995, 6 (03) :792-794

← 1 2 3 →