Research and Implementation of Road Traffic Sign IdentiFIcation System

Chien-Chung Wu, Shiue-Ling Wu
2019 Journal of network intelligence  
It is helpful to enhance traffic safety by driving information which is provided by the roadside traffic signs. However, as the traffic sign information cannot be seen immediately while driving, drivers always ignore a lot of important driving information. To solve this problem, an automatic traffic sign identification system which took road as an example was proposed. The system has been developed with image recognition technology and can provide the identification result of related driving
more » ... ormation to drivers. The system proposed in this study was divided into two parts. Firstly, through the brightness of the image, the possible traffic sign image and its position could be quickly detected with the classifier trained by Haar Cascade in Haar-like with AdaBoost method. Secondly, the detected images could be classified by the convolutional neural network (CNN) classifier designed with GoogLeNet Network Architecture in TensorFlow library and Python program language. To speed up the recognition process and the correctness of recognition result, a method was proposed in this study to avoid analyzing those areas without traffic signs. In the method, the collected road videos were divided into 12 regions to find out the non-traffic sign areas. After carrying out this method, the recognition speed has been improved 11.24 frame/sec from to 12.04 frame/sec. Besides, the precision of the system can be improved from 80.97
dblp:journals/jni/WuW19 fatcat:uygqcbzaurbpxiel3k3gp6ssba