计算机工程与应用 ›› 2011, Vol. 47 ›› Issue (28): 176-178.

• 图形、图像、模式识别 • 上一篇    下一篇

马尔可夫随机场理论在目标跟踪中的应用

楚 瀛,符 杨   

  1. 上海电力学院 电力与自动化工程学院,上海 200090
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2011-10-01 发布日期:2011-10-01

Study on method of object tracking based Markov random field

CHU Ying,FU Yang   

  1. School of Electric Power and Automation Engineering,Shanghai University of Electric Power,Shanghai 200090,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-10-01 Published:2011-10-01

摘要: 在目标跟踪问题中,被跟踪目标的尺度变化、旋转变化和遮挡都会造成跟踪精确度的降低或目标的丢失。针对这些问题,提出了一种基于马尔可夫随机场的目标跟踪方法,将运动目标跟踪问题看作是前景和背景的二值分类问题,建立前景背景分割的马尔可夫随机场模型,从而实现对前景背景的分类,以完成对运动目标的跟踪。试验证明,这种方法可以有效地克服前景目标的尺度变化和旋转变化以及遮挡给目标跟踪带来的困难。

关键词: 目标跟踪, 马尔可夫随机场, 尺度变化, 旋转变化, 遮挡

Abstract: Scale change,rotate change and occluding of moving object can cause to the failure of object tracking.For solving these problem,this paper proposes a method based Markov random field.The problem of object tracking is considered as a binary label problem and Markov random fields of foreground segment is modeled. Experierments demonstrate this model is robust for scale change,rotate change and occluding.

Key words: object tracking, Markov random field, scale change, rotate change, occluding