计算机工程与应用 ›› 2012, Vol. 48 ›› Issue (9): 185-188.

• 图形、图像、模式识别 • 上一篇    下一篇

双目视觉的弱点动目标粒子滤波跟踪定位研究

周同驰1,艾斯卡尔·艾木都拉1,杨 强1,王荣栓2   

  1. 1.新疆大学 信息科学与工程学院,乌鲁木齐 830046
    2.天津市雅浪通讯,天津 300384
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2012-03-21 发布日期:2012-04-11

Study on dim moving point target’s particle filter tracking and orientation based on binocular vision

ZHOU Tongchi1, Askar Hamdulla1, YANG Qiang1, WANG Rongshuan2   

  1. 1.Institute of Information Science and Engineering, Xinjiang University, Urumqi 830046, China
    2.Yalong Communication, Tianjin 300384, China
  • Received:1900-01-01 Revised:1900-01-01 Online:2012-03-21 Published:2012-04-11

摘要: 在研究红外图像序列的弱点动目标粒子滤波跟踪算法和双目立体视觉摄像机标定算法的基础上,基于双目视觉设计了双目图像序列弱点动目标的跟踪、空间定位系统。仿真实验表明:对粒子基于估计参数后的密度函数分配权重的算法,提高了图像跟踪精度,采用线性三角定位方法,有效地实现目标空间定位。

关键词: 红外图像序列, 弱点动目标, 粒子滤波, 双目视觉

Abstract: This paper designs an experimental system for tracking and spatial localization of a dim moving point target in binocular image sequences based on the research of particle filter tracking algorithm and the binocular vision camera calibration algorithm. Experimental results show: after estimating the density function’s parameters, the algorithm which distributes the weight to particle according to PDF advances the precision of image tracking; the method which adopts linear triangulation principle to extract the target’s spatial localization is effective.

Key words: Infrared(IR) image sequence, dim moving point target, particle filter, binocular vision