|
|
Bimonthly Since 1986 |
ISSN 1004-9037
|
|
|
|
|
Publication Details |
Edited by: Editorial Board of Journal of Data Acquisition and Processing
P.O. Box 2704, Beijing 100190, P.R. China
Sponsored by: Institute of Computing Technology, CAS & China Computer Federation
Undertaken by: Institute of Computing Technology, CAS
Published by: SCIENCE PRESS, BEIJING, CHINA
Distributed by:
China: All Local Post Offices
|
|
|
|
|
|
|
|
|
|
Abstract
The traffic sign identification and recognition system are the process of detecting the traffic signs present on the roadside. At present, the world is developing with new technologies but the accident rate is highly increasing. The main cause is driver’s failure in interpreting the traffic sign boards. In this paper, a new method of traffic sign identification and recognition system is proposed to reduce the accident rate. The implementation of the proposed system uses Deep Neural Network (DNN) and an object detection algorithm called YOLO V5 (You Only Look Once) algorithm. This method is trained with dataset from Kaggle called traffic signs dataset in YOLO format. This system enhances the driver interactivity while driving a vehicle. As a result, it improves the attentiveness of the driver by displaying signs by producing alarm sound with improved precision rate compared to the traditional methods. A comparison of simulation results shows the effectiveness of the system.
Keyword
Traffic sign identification and recognition system, Object detection algorithm, DNN, YOLO V5 algorithm, Kaggle.
PDF Download (click here)
|
|
|
|
|