Local texture patterns for traffic sign recognition using higher order spectra

Research output: Contribution to journalArticle

17 Citations (Scopus)

Abstract

Traffic sign recognition (TSR) is considered as one of the most important modules of driver assistance system (DAS). It can be used as a decision supporting tool for driver and autonomous vehicles. Eventually, TSR is a large-scale feature learning problem and hence attracted the attention of researchers recently. The essential parameters such as huge training dataset size, recognition accuracy and computational complexity need to be considered while designing a practical TSR system. In this paper, we have used higher order spectra (HOS) coupled with texture based features to develop an efficient TSR model. These features represent the shape and content of the traffic signs clearly. Then a subspace learning method with graph embedding under linear discriminant analysis framework is used to increase the discrimination power between various traffic symbols. As a result the proposed method attained a maximum recognition accuracy of 98.89%. The proposed method is evaluated using two publicly available datasets such as, Belgium traffic sign classification (BTSC) and German traffic sign recognition benchmark (GTSRB). Our experimental results demonstrate that the proposed approach is computationally efficient and shows promising recognition accuracy.

Original languageEnglish
Pages (from-to)202-210
Number of pages9
JournalPattern Recognition Letters
Volume94
DOIs
Publication statusPublished - 15-07-2017

Fingerprint

Traffic signs
Textures
Discriminant analysis
Computational complexity

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

@article{1eba0dd1d3854e95943b3f2c1a901dfc,
title = "Local texture patterns for traffic sign recognition using higher order spectra",
abstract = "Traffic sign recognition (TSR) is considered as one of the most important modules of driver assistance system (DAS). It can be used as a decision supporting tool for driver and autonomous vehicles. Eventually, TSR is a large-scale feature learning problem and hence attracted the attention of researchers recently. The essential parameters such as huge training dataset size, recognition accuracy and computational complexity need to be considered while designing a practical TSR system. In this paper, we have used higher order spectra (HOS) coupled with texture based features to develop an efficient TSR model. These features represent the shape and content of the traffic signs clearly. Then a subspace learning method with graph embedding under linear discriminant analysis framework is used to increase the discrimination power between various traffic symbols. As a result the proposed method attained a maximum recognition accuracy of 98.89{\%}. The proposed method is evaluated using two publicly available datasets such as, Belgium traffic sign classification (BTSC) and German traffic sign recognition benchmark (GTSRB). Our experimental results demonstrate that the proposed approach is computationally efficient and shows promising recognition accuracy.",
author = "Anjan Gudigar and Shreesha Chokkadi and U. Raghavendra and Acharya, {U. Rajendra}",
year = "2017",
month = "7",
day = "15",
doi = "10.1016/j.patrec.2017.02.016",
language = "English",
volume = "94",
pages = "202--210",
journal = "Pattern Recognition Letters",
issn = "0167-8655",
publisher = "Elsevier",

}

Local texture patterns for traffic sign recognition using higher order spectra. / Gudigar, Anjan; Chokkadi, Shreesha; Raghavendra, U.; Acharya, U. Rajendra.

In: Pattern Recognition Letters, Vol. 94, 15.07.2017, p. 202-210.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Local texture patterns for traffic sign recognition using higher order spectra

AU - Gudigar, Anjan

AU - Chokkadi, Shreesha

AU - Raghavendra, U.

AU - Acharya, U. Rajendra

PY - 2017/7/15

Y1 - 2017/7/15

N2 - Traffic sign recognition (TSR) is considered as one of the most important modules of driver assistance system (DAS). It can be used as a decision supporting tool for driver and autonomous vehicles. Eventually, TSR is a large-scale feature learning problem and hence attracted the attention of researchers recently. The essential parameters such as huge training dataset size, recognition accuracy and computational complexity need to be considered while designing a practical TSR system. In this paper, we have used higher order spectra (HOS) coupled with texture based features to develop an efficient TSR model. These features represent the shape and content of the traffic signs clearly. Then a subspace learning method with graph embedding under linear discriminant analysis framework is used to increase the discrimination power between various traffic symbols. As a result the proposed method attained a maximum recognition accuracy of 98.89%. The proposed method is evaluated using two publicly available datasets such as, Belgium traffic sign classification (BTSC) and German traffic sign recognition benchmark (GTSRB). Our experimental results demonstrate that the proposed approach is computationally efficient and shows promising recognition accuracy.

AB - Traffic sign recognition (TSR) is considered as one of the most important modules of driver assistance system (DAS). It can be used as a decision supporting tool for driver and autonomous vehicles. Eventually, TSR is a large-scale feature learning problem and hence attracted the attention of researchers recently. The essential parameters such as huge training dataset size, recognition accuracy and computational complexity need to be considered while designing a practical TSR system. In this paper, we have used higher order spectra (HOS) coupled with texture based features to develop an efficient TSR model. These features represent the shape and content of the traffic signs clearly. Then a subspace learning method with graph embedding under linear discriminant analysis framework is used to increase the discrimination power between various traffic symbols. As a result the proposed method attained a maximum recognition accuracy of 98.89%. The proposed method is evaluated using two publicly available datasets such as, Belgium traffic sign classification (BTSC) and German traffic sign recognition benchmark (GTSRB). Our experimental results demonstrate that the proposed approach is computationally efficient and shows promising recognition accuracy.

UR - http://www.scopus.com/inward/record.url?scp=85014384362&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85014384362&partnerID=8YFLogxK

U2 - 10.1016/j.patrec.2017.02.016

DO - 10.1016/j.patrec.2017.02.016

M3 - Article

AN - SCOPUS:85014384362

VL - 94

SP - 202

EP - 210

JO - Pattern Recognition Letters

JF - Pattern Recognition Letters

SN - 0167-8655

ER -