基于TensorFlow的交通标志识别方法研究  

Research on Traffic Sign Recognition Method Based on TensorFlow

作　　者：王全[1] 梁敬文 WANG Quan;LIANG Jing-wen(School of Computer Science and Engineering,Xi'an Technological University,Xi'an 710021,China)

机构地区：[1]西安工业大学计算机科学与工程学院

出　　处：《价值工程》2019年第27期204-206,共3页Value Engineering

基　　金：西安工业大学校长基金项目(0852-302020615)

摘　　要：交通标志识别系统是智能驾驶系统的重要组成部分;本文分析了现有方法存在的问题,基于TensorFlow框架搭建了改进的卷积神经网络,用于识别交通标志;整个系统在TensorFlow上实现,使用行车记录仪采集的视频验证了本文的算法,结果表明本文算法有一定的实用性,而且在准确率,鲁棒性和实时性等方面也表现较好。Traffic sign recognition system is an important part of intelligent driving system. This paper analyzes the problems existing in the existing methods. Based on the TensorFlow framework, an improved convolutional neural network is built to identify traffic signs. Finally,the whole system is implemented based on TensorFlow, and the algorithm is verified by the collected video in the traffic recorder. The results show that the algorithm is practical, and has excellent performance in accuracy, stability and real-time.

关 键 词：交通标志识别 卷积神经网络 TENSOR FLOW 

分 类 号：TP391[自动化与计算机技术—计算机应用技术] U461.6[自动化与计算机技术—计算机科学与技术]