Simplified neural networks with smart detection for road traffic sign recognition

Wei Jong Yang, Chia Chun Luo, Pau-Choo Chung, Jar-Ferr Yang

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

Improving driver’s safety is the main goal of the advanced driver assistance system, which has been widely deployed for proactive driving security in recent years. For road driving, the advanced driver assistance system should visually recognize circular prohibition and triangular warning traffic signs to help drivers to grab complete traffic conditions. In this paper, we proposed a low-computation neural assistance system for traffic sign recognition. First, we proposed shaped-based detection algorithms to detect the regions, which are with circle and triangular traffic signs in designated regions of interest. For classification to those detected regions, we then suggest a convolutional neural network to achieve about 5% improvement of top 1 accuracy compared with LeNet model in German traffic sign recognition benchmarks dataset. For real applications, we also establish a Taiwanese traffic sign database to train the proposed neural network. The simulation results on self-collect driving videos demonstrate that the proposed traffic sign recognition system achieved above 97% recognition rate can be effectively adopted in ADAS applications.

Original languageEnglish
Title of host publicationLecture Notes in Networks and Systems
PublisherSpringer
Pages237-249
Number of pages13
DOIs
Publication statusPublished - 2020 Jan 1

Publication series

NameLecture Notes in Networks and Systems
Volume69
ISSN (Print)2367-3370
ISSN (Electronic)2367-3389

Fingerprint

Traffic signs
Neural networks
Advanced driver assistance systems

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Signal Processing
  • Control and Systems Engineering

Cite this

Yang, W. J., Luo, C. C., Chung, P-C., & Yang, J-F. (2020). Simplified neural networks with smart detection for road traffic sign recognition. In Lecture Notes in Networks and Systems (pp. 237-249). (Lecture Notes in Networks and Systems; Vol. 69). Springer. https://doi.org/10.1007/978-3-030-12388-8_17
Yang, Wei Jong ; Luo, Chia Chun ; Chung, Pau-Choo ; Yang, Jar-Ferr. / Simplified neural networks with smart detection for road traffic sign recognition. Lecture Notes in Networks and Systems. Springer, 2020. pp. 237-249 (Lecture Notes in Networks and Systems).
@inbook{2b333cefb92b4e0a9576b321cbb6a2d1,
title = "Simplified neural networks with smart detection for road traffic sign recognition",
abstract = "Improving driver’s safety is the main goal of the advanced driver assistance system, which has been widely deployed for proactive driving security in recent years. For road driving, the advanced driver assistance system should visually recognize circular prohibition and triangular warning traffic signs to help drivers to grab complete traffic conditions. In this paper, we proposed a low-computation neural assistance system for traffic sign recognition. First, we proposed shaped-based detection algorithms to detect the regions, which are with circle and triangular traffic signs in designated regions of interest. For classification to those detected regions, we then suggest a convolutional neural network to achieve about 5{\%} improvement of top 1 accuracy compared with LeNet model in German traffic sign recognition benchmarks dataset. For real applications, we also establish a Taiwanese traffic sign database to train the proposed neural network. The simulation results on self-collect driving videos demonstrate that the proposed traffic sign recognition system achieved above 97{\%} recognition rate can be effectively adopted in ADAS applications.",
author = "Yang, {Wei Jong} and Luo, {Chia Chun} and Pau-Choo Chung and Jar-Ferr Yang",
year = "2020",
month = "1",
day = "1",
doi = "10.1007/978-3-030-12388-8_17",
language = "English",
series = "Lecture Notes in Networks and Systems",
publisher = "Springer",
pages = "237--249",
booktitle = "Lecture Notes in Networks and Systems",

}

Yang, WJ, Luo, CC, Chung, P-C & Yang, J-F 2020, Simplified neural networks with smart detection for road traffic sign recognition. in Lecture Notes in Networks and Systems. Lecture Notes in Networks and Systems, vol. 69, Springer, pp. 237-249. https://doi.org/10.1007/978-3-030-12388-8_17

Simplified neural networks with smart detection for road traffic sign recognition. / Yang, Wei Jong; Luo, Chia Chun; Chung, Pau-Choo; Yang, Jar-Ferr.

Lecture Notes in Networks and Systems. Springer, 2020. p. 237-249 (Lecture Notes in Networks and Systems; Vol. 69).

Research output: Chapter in Book/Report/Conference proceedingChapter

TY - CHAP

T1 - Simplified neural networks with smart detection for road traffic sign recognition

AU - Yang, Wei Jong

AU - Luo, Chia Chun

AU - Chung, Pau-Choo

AU - Yang, Jar-Ferr

PY - 2020/1/1

Y1 - 2020/1/1

N2 - Improving driver’s safety is the main goal of the advanced driver assistance system, which has been widely deployed for proactive driving security in recent years. For road driving, the advanced driver assistance system should visually recognize circular prohibition and triangular warning traffic signs to help drivers to grab complete traffic conditions. In this paper, we proposed a low-computation neural assistance system for traffic sign recognition. First, we proposed shaped-based detection algorithms to detect the regions, which are with circle and triangular traffic signs in designated regions of interest. For classification to those detected regions, we then suggest a convolutional neural network to achieve about 5% improvement of top 1 accuracy compared with LeNet model in German traffic sign recognition benchmarks dataset. For real applications, we also establish a Taiwanese traffic sign database to train the proposed neural network. The simulation results on self-collect driving videos demonstrate that the proposed traffic sign recognition system achieved above 97% recognition rate can be effectively adopted in ADAS applications.

AB - Improving driver’s safety is the main goal of the advanced driver assistance system, which has been widely deployed for proactive driving security in recent years. For road driving, the advanced driver assistance system should visually recognize circular prohibition and triangular warning traffic signs to help drivers to grab complete traffic conditions. In this paper, we proposed a low-computation neural assistance system for traffic sign recognition. First, we proposed shaped-based detection algorithms to detect the regions, which are with circle and triangular traffic signs in designated regions of interest. For classification to those detected regions, we then suggest a convolutional neural network to achieve about 5% improvement of top 1 accuracy compared with LeNet model in German traffic sign recognition benchmarks dataset. For real applications, we also establish a Taiwanese traffic sign database to train the proposed neural network. The simulation results on self-collect driving videos demonstrate that the proposed traffic sign recognition system achieved above 97% recognition rate can be effectively adopted in ADAS applications.

UR - http://www.scopus.com/inward/record.url?scp=85062920973&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062920973&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-12388-8_17

DO - 10.1007/978-3-030-12388-8_17

M3 - Chapter

AN - SCOPUS:85062920973

T3 - Lecture Notes in Networks and Systems

SP - 237

EP - 249

BT - Lecture Notes in Networks and Systems

PB - Springer

ER -

Yang WJ, Luo CC, Chung P-C, Yang J-F. Simplified neural networks with smart detection for road traffic sign recognition. In Lecture Notes in Networks and Systems. Springer. 2020. p. 237-249. (Lecture Notes in Networks and Systems). https://doi.org/10.1007/978-3-030-12388-8_17