计算机工程与应用 ›› 2007, Vol. 43 ›› Issue (28): 230-232.

• 工程与应用 • 上一篇    下一篇

基于Adaboost方法的高速公路事件检测

张良春,夏利民   

  1. 中南大学 信息科学与工程学院,长沙 410075
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2007-10-01 发布日期:2007-10-01
  • 通讯作者: 张良春

Freeway incident detection based on Adaboost method

ZHANG Liang-chun,XIA Li-min   

  1. Department of Information Science and Engineering,Central South University,Changsha 410075,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-10-01 Published:2007-10-01
  • Contact: ZHANG Liang-chun

摘要: 阐述Adaboost方法原理及算法,提出采用Adaboost方法结合神经网络算法进行高速公路事件检测,给出了基于Adaboost方法的事件检测算法。该算法可以明显提升神经网络算法性能,适合进行高速公路事件检测,仿真实验结果表明了该算法的有效性和可行性。

关键词: Adaboost, 高速公路事件检测, 神经网络

Abstract: This paper describes the principle and algorithm of Adaboost method,and evaluates the adaptability of applying Adaboost algorithm combined with neural network to freeway incident detection.An improved freeway incident-detection algorithm is presented based on Adaboost method,which can highly enhance the performance of neural network algorithm and assesses the effectiveness of its application to freeway incident detection.The result of simulation experiment shows the algorithm’s validity and feasibility.

Key words: Adaboost, freeway incident detection, neural network