一种融合加权ELM和AdaBoost的交通标志识别算法

发布时间：2018-01-04 20:30

本文关键词：一种融合加权ELM和AdaBoost的交通标志识别算法　出处：《小型微型计算机系统》2017年09期 　论文类型：期刊论文

【摘要】：作为一种新型的单隐层前馈型神经网络,极限学习机(Extreme Learning Machine:ELM)相比于传统的神经网络学习算法具有参数设置少、泛化性能强、训练和识别速度快等优点.为了有效提高交通标志的识别速度和识别率,提出一种基于加权ELM和AdaBoost融合优化的交通标志识别新算法.该算法通过迭代更新原始ELM的训练权重,并利用加权后的ELM作为AdaBoost的弱分类器,最终通过加权多数表决得到最优强分类器.最终实验结果表明,该算法能够取得的交通标志总识别率为99.12%,且单张交通标志的识别时间为7.1ms,可以满足实时识别应用的需求,较好的改善了交通标志的识别性能.
[Abstract]:As a new type of single hidden layer feedforward neural network. Compared with the traditional neural network learning algorithm, extreme Learning Machine: ELM has less parameter setting and better generalization performance. In order to improve the recognition speed and recognition rate of traffic signs effectively. A new traffic sign recognition algorithm based on weighted ELM and AdaBoost fusion optimization is proposed, which updates the training weight of the original ELM iteratively. The weighted ELM is used as the weak classifier of AdaBoost, and the optimal classifier is obtained by the weighted majority vote. Finally, the experimental results show that. The total recognition rate of traffic signs obtained by this algorithm is 99.12, and the recognition time of single traffic signs is 7.1 Ms, which can meet the needs of real-time recognition applications. Better performance of traffic sign recognition is improved.
【作者单位】：天津大学电子信息工程学院;
【基金】：国家自然科学基金项目(61372145)资助天津大学自主创新基金项目(2015XZC-0005)资助
【分类号】：TP18;U495
【正文快照】： 1引言交通标志识别系统是现代智能交通系统的重要组成部分,同时也是汽车智能辅助驾驶系统和谷歌等无人驾驶汽车技术的核心模块之一.它能实时检测、识别驾驶环境中位于道路前方和两旁的交通标志并做出相应的安全预警提示,对汽车的安全驾驶起到至关重要的作用.由于道路交通环境

【相似文献】