交通运输系统工程与信息

交通运输系统工程与信息 ›› 2012, Vol. 12 ›› Issue (4): 84-92.

• 智能交通系统与信息技术 • 上一篇    下一篇

基于改进的颜色特征和直方图更新的Mean-Shift算法

刘康亚1，孙首群*1，刘硕研2，王冰2，吕晓军2   

  1. 1.上海理工大学 机械工程学院，上海 200093; 2.中国铁道科学研究院 电子所，北京 100081
  • 收稿日期:2012-05-08 修回日期:2012-06-06 出版日期:2012-08-25 发布日期:2012-09-07
  • 作者简介:刘康亚(1988-)，男，山东菏泽人，硕士生.
  • 基金资助:

    铁道科学研究院院基金资助项目(1151GC1103); 铁道部专项资金支持课题研究项目(J2011X007); 国家“863”高科技计划资助项目(2009AA11Z211); 上海市教委重点学科建设项目(J50503).

Target Tracking Mean-Shift Algorithm Based on Improved Color Feature and Histogram Updating

LIU Kang-ya1, SUN Shou-qun 1, LIU Shuo-yan2, WANG Bing2, LV Xiao-jun2   

  1. 1.College of Mechanical Engineering, University of Shanghai for Science & Technology, Shanghai 200093, China; 2. Institute of Computing Technologies of China Academy of Railway Science, Beijing 100081, China
  • Received:2012-05-08 Revised:2012-06-06 Online:2012-08-25 Published:2012-09-07

PDF

摘要：

为了提高复杂环境下智能视频监控对运动目标跟踪的可靠性，提出一种基于改进的颜色特征和直方图更新的Mean-Shift跟踪算法.该算法利用像素点局部颜色变化作为跟踪目标像素点特征，弥补单一颜色值特征对目标表征的不足；并根据Mean-Shift跟踪结果和目标匹配程度对目标直方图进行更新，保证在目标姿态和大小发生变化时目标特征直方图的有效性.实验结果表明：与传统Mean-Shift算法相比，改进的颜色特征减小了相似背景像素对运动目标的干扰，目标直方图的更新提高了Mean-Shift算法对目标姿态和大小改变的鲁棒性.算法提高了基于颜色特征的Mean-Shift算法对复杂环境中运动目标进行实时跟踪的可靠性.

关键词: 智能交通, 运动目标跟踪, mean-shift算法, 运动目标, 颜色分布特征, 直方图更新

Abstract:

In this paper, a target tracking algorithm of meanshift based on improved color feature and histogram updating is proposed to enhance efficiency of intelligent video surveillance in complicated scene. The variety of color around a pixel is taken as the feature of the pixel to improve the single color’s capability of expressing the target. The probability density of image is easily forecasted based on the histogram to enhance the efficiency of meanshift. The histogram of target is updated based on matching degree between the target and the result of meanshift. The experimental data indicates that the improved color feature can avoid interference of similar pixel of background and that the updating of histogram can solve the problem of the change of target’s size. This algorithm can improve mean-shift’s validity of the realtime target tracking in the complicated scene.

Key words: intelligent transportation, tracking of moving target, meanshift algorithm, moving target, feature of color’s distributing, updating of histogram

中图分类号: