An efficient traffic sign recognition based on graph embedding features

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Traffic sign recognition (TSR) is one of the significant modules of an intelligent transportation system. It instantly assists the drivers to efficiently recognize the traffic sign. Recognition of traffic sign is a large-scale feature learning problem with different real-world appearances. The main goal of this paper is to develop an efficient TSR method, which can run on an ordinary personal computer (PC). In the proposed method, GIST descriptors of the traffic sign images are extracted and subjected to graph-based linear discriminant analysis to reduce the dimension. Moreover, it effectively learns the discriminative subspace through the graph structure with increased computational efficiency. An efficient TSR module is built by conducting series of experiments using support vector machine, extreme learning machine, and k-nearest neighbor (k-NN) classifiers on available public datasets. Our approach achieved the highest recognition accuracy of 96.33 and 97.79% using k-NN classifier for German Traffic Sign Recognition Benchmark (GTSRB) and Belgium Traffic Sign Classification Benchmark (BelgiumTSC), respectively. Also it achieved 99.1% accuracy for a subcategory of GTSRB traffic signs and able to predict the class of unknown traffic sign within 0.0019 s on an ordinary PC. Hence, it can be used in real-world driver assistance system.

Original languageEnglish
Pages (from-to)1-13
Number of pages13
JournalNeural Computing and Applications
DOIs
Publication statusPublished - 04-07-2019

Fingerprint

Traffic signs
Personal computers
Classifiers
Discriminant analysis
Computational efficiency
Support vector machines
Learning systems

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence

Cite this

@article{06b1d556d8544d63a1c1a025142c072d,
title = "An efficient traffic sign recognition based on graph embedding features",
abstract = "Traffic sign recognition (TSR) is one of the significant modules of an intelligent transportation system. It instantly assists the drivers to efficiently recognize the traffic sign. Recognition of traffic sign is a large-scale feature learning problem with different real-world appearances. The main goal of this paper is to develop an efficient TSR method, which can run on an ordinary personal computer (PC). In the proposed method, GIST descriptors of the traffic sign images are extracted and subjected to graph-based linear discriminant analysis to reduce the dimension. Moreover, it effectively learns the discriminative subspace through the graph structure with increased computational efficiency. An efficient TSR module is built by conducting series of experiments using support vector machine, extreme learning machine, and k-nearest neighbor (k-NN) classifiers on available public datasets. Our approach achieved the highest recognition accuracy of 96.33 and 97.79{\%} using k-NN classifier for German Traffic Sign Recognition Benchmark (GTSRB) and Belgium Traffic Sign Classification Benchmark (BelgiumTSC), respectively. Also it achieved 99.1{\%} accuracy for a subcategory of GTSRB traffic signs and able to predict the class of unknown traffic sign within 0.0019 s on an ordinary PC. Hence, it can be used in real-world driver assistance system.",
author = "Anjan Gudigar and Shreesha Chokkadi and U. Raghavendra and Acharya, {U. Rajendra}",
year = "2019",
month = "7",
day = "4",
doi = "10.1007/s00521-017-3063-z",
language = "English",
pages = "1--13",
journal = "Neural Computing and Applications",
issn = "0941-0643",
publisher = "Springer London",

}

An efficient traffic sign recognition based on graph embedding features. / Gudigar, Anjan; Chokkadi, Shreesha; Raghavendra, U.; Acharya, U. Rajendra.

In: Neural Computing and Applications, 04.07.2019, p. 1-13.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An efficient traffic sign recognition based on graph embedding features

AU - Gudigar, Anjan

AU - Chokkadi, Shreesha

AU - Raghavendra, U.

AU - Acharya, U. Rajendra

PY - 2019/7/4

Y1 - 2019/7/4

N2 - Traffic sign recognition (TSR) is one of the significant modules of an intelligent transportation system. It instantly assists the drivers to efficiently recognize the traffic sign. Recognition of traffic sign is a large-scale feature learning problem with different real-world appearances. The main goal of this paper is to develop an efficient TSR method, which can run on an ordinary personal computer (PC). In the proposed method, GIST descriptors of the traffic sign images are extracted and subjected to graph-based linear discriminant analysis to reduce the dimension. Moreover, it effectively learns the discriminative subspace through the graph structure with increased computational efficiency. An efficient TSR module is built by conducting series of experiments using support vector machine, extreme learning machine, and k-nearest neighbor (k-NN) classifiers on available public datasets. Our approach achieved the highest recognition accuracy of 96.33 and 97.79% using k-NN classifier for German Traffic Sign Recognition Benchmark (GTSRB) and Belgium Traffic Sign Classification Benchmark (BelgiumTSC), respectively. Also it achieved 99.1% accuracy for a subcategory of GTSRB traffic signs and able to predict the class of unknown traffic sign within 0.0019 s on an ordinary PC. Hence, it can be used in real-world driver assistance system.

AB - Traffic sign recognition (TSR) is one of the significant modules of an intelligent transportation system. It instantly assists the drivers to efficiently recognize the traffic sign. Recognition of traffic sign is a large-scale feature learning problem with different real-world appearances. The main goal of this paper is to develop an efficient TSR method, which can run on an ordinary personal computer (PC). In the proposed method, GIST descriptors of the traffic sign images are extracted and subjected to graph-based linear discriminant analysis to reduce the dimension. Moreover, it effectively learns the discriminative subspace through the graph structure with increased computational efficiency. An efficient TSR module is built by conducting series of experiments using support vector machine, extreme learning machine, and k-nearest neighbor (k-NN) classifiers on available public datasets. Our approach achieved the highest recognition accuracy of 96.33 and 97.79% using k-NN classifier for German Traffic Sign Recognition Benchmark (GTSRB) and Belgium Traffic Sign Classification Benchmark (BelgiumTSC), respectively. Also it achieved 99.1% accuracy for a subcategory of GTSRB traffic signs and able to predict the class of unknown traffic sign within 0.0019 s on an ordinary PC. Hence, it can be used in real-world driver assistance system.

UR - http://www.scopus.com/inward/record.url?scp=85021782757&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85021782757&partnerID=8YFLogxK

U2 - 10.1007/s00521-017-3063-z

DO - 10.1007/s00521-017-3063-z

M3 - Article

AN - SCOPUS:85021782757

SP - 1

EP - 13

JO - Neural Computing and Applications

JF - Neural Computing and Applications

SN - 0941-0643

ER -