计算机工程与应用 ›› 2008, Vol. 44 ›› Issue (2): 215-217.

• 工程与应用 • 上一篇    下一篇

基于Boosting学习的靶子自动检测算法研究

肖 潇,赵明昌   

  1. 桂林电子科技大学 计算机与控制学院,广西 桂林 541004
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2008-01-11 发布日期:2008-01-11
  • 通讯作者: 肖 潇

Research on algorithm of automatic detection of target based on Boosting

XIAO Xiao,ZHAO Ming-chang   

  1. School of Computer Science and Control,Guilin University of Electronic Technology,Guilin,Guangxi 541004,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2008-01-11 Published:2008-01-11
  • Contact: XIAO Xiao

摘要: 提出了一种实弹射击演习中的靶子自动检测方法,适合于野外复杂背景下的靶子图像处理,所有图像由固定在枪柄上的摄像头统一采集。利用经典的Boosting学习算法,将图像中靶子的特征提取出来,对图片的训练集进行训练,并从训练中学习到一个强的分类器,从而实现了靶子所在区域的自动化检测。并将方法用于一个具体实例,实验结果证明了所提方法的有效性。

关键词: 自动检测, 分类器, 模板

Abstract: This paper presents a new method of automatic detection on target from image captured by outdoor firing training system with complex background.All the images are picked up by a camera on pikestaff.Boosting learning algorithm is used here to extra the features of target from the images of target.And then train the training samples to gain a strong classifier,which can help to detect the location of target more accurately.We try to apply the method to a relevant example,and the result of the trial indicates the validity of the method.

Key words: auto detection, classifier, template