Researching | Traffic Sign Recognition Based on Improved Neural Networks

Laser & Optoelectronics Progress, Volume. 56, Issue 19, 191002(2019)

Traffic Sign Recognition Based on Improved Neural Networks

Ying Tong^* and Huicheng Yang

Author Affiliations

College of Electrical Engineering, Anhui Polytechnic University, Wuhu, Anhui 241000, China

show less

Abstract Get PDF(in Chinese)

Figures&Tables (14)

References (22)

Paper Information

Figures & Tables(14)

Fig. 1. Flow chart of YOLOv2 algorithm

Download full size

Fig. 2. YOLOv2 network structure

Download full size

Fig. 3. Inception modules. (a) Module A; (b) module B

Download full size

Fig. 4. NYOLOv2 structural diagram

Download full size

Fig. 5. Three super classification examples of traffic signs. (a) Mandatory; (b) prohibitory; (c) danger

Download full size

Fig. 6. Comparison of loss function curves

Download full size

Fig. 7. Examples of detecting the loss function using YOLOv2

Download full size

Fig. 8. Examples of detecting the loss function using NYOLOv2

Download full size

Fig. 9. PR curves of three super categories. (a) Mandatory; (b) prohibitory; (c) danger

Download full size

Table 1. Precisions and recall rate values at different time thresholds
View table
Table 1. Precisions and recall rate values at different time thresholds
Threshold t 0.10 0.20 0.40 0.50 0.60 0.65
Precision 0.7554 0.8699 0.9543 0.9648 09874 1.000
Recall 0.9568 0.9396 0.9102 0.8650 0.7959 0.6203

Table 2. Comparison of different architecture performances
View table
Table 2. Comparison of different architecture performances
Method mAP FPS
YOLOv2 76.8 40.0
NYOLOv2 83.2 55.0

Table 3. Comparison of classification results of three methods

Table 3. Comparison of classification results of three methods

Method	Prohibitory		Mandatory		Danger		Time /s
Method	Precision /%	Recall /%		Precision /%	Recall /%	Precision /%	Recall /%
YOLO	98.55	92.15	96.68	70.56	90.89	78.11	0.221
YOLOv2	99.06	87.64	98.24	69.06	97.65	75.03	0.154
NYOLOv2	99.13	91.23	99.12	72.66	98.00	80.21	0.015

Table 4. Comparison of processing time and performance of different methods
View table
Table 4. Comparison of processing time and performance of different methods
Method Precision /% Recall /% Time /s
Ref. [1] 89.17 92.15 0.280
Ref. [19] 91.00 94.00 0.190
NYOLOv2 (t=0.4) 95.43 91.02 0.015
NYOLOv2 (t=0.5) 96.48 92.50 0.015

Table 5. AUC values and processing time for different methods
View table
Table 5. AUC values and processing time for different methods
Method Prohibitory /% Mandatory /% Danger /% Time /s
Ref. [11] 95.46 93.45 91.12 0.300
Ref. [13] 95.41 92.00 91.85 0.400-1.000
Ref. [14] 100.00 100.00 99.91 3.533
NYOLOv2 96.21 97.96 92.44 0.015

Tools

Get Citation

Copy Citation Text

Ying Tong, Huicheng Yang. Traffic Sign Recognition Based on Improved Neural Networks[J]. Laser & Optoelectronics Progress, 2019, 56(19): 191002

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites

Paper Information

Category: Image Processing

Received: Mar. 11, 2019

Accepted: Apr. 12, 2019

Published Online: Oct. 12, 2019

The Author Email: Ying Tong (864844537@qq.com)

DOI:10.3788/LOP56.191002

Topics

laser devices and laser physics

Lasers and Laser Optics

laser manufacturing

Instrumentation, Measurement and Metrology