作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2009, Vol. 35 ›› Issue (18): 31-33. doi: 10.3969/j.issn.1000-3428.2009.18.011

• 博士论文 • 上一篇    下一篇

基于多关联模板匹配的火箭目标跟踪算法

尹宏鹏,柴 毅,屈剑锋,翟茹玲   

  1. (重庆大学自动化学院,重庆 400044)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2009-09-20 发布日期:2009-09-20

Rocket Target Tracking Algorithm Based onMultiple Related Template Matching

YIN Hong-peng, CHAI Yi, QU Jian-feng, ZHAI Ru-ling   

  1. (College of Automation, Chongqing University, Chongqing 400044)
  • Received:1900-01-01 Revised:1900-01-01 Online:2009-09-20 Published:2009-09-20

摘要: 针对火箭目标在复杂场景的跟踪问题,提出一种基于多关联模板匹配的模板匹配策略,通过仿射变换从上帧最优模板中产生多关联模板以自适应火箭目标的大小和姿态改变,提高算法的匹配精度。采用Kalman滤波器对火箭飞行进行轨迹预测。多个火箭飞行录像跟踪实验表明,该算法具有很好的匹配精度与实时性,对火箭目标的状态、大小变化与云层遮挡现象具有较好的鲁棒性。

关键词: 火箭目标跟踪, 多关联模板, 模板匹配, Kalman滤波器, 轨迹预测

Abstract: Aiming at the tracking problem of the rocket target in complex scene, this paper proposes a template matching strategy based on multiple related template matching. This strategy can improve the track accuracy by getting the best template from the previous frame using the mapping transform, which can fit rocket’s size and state automatically. The Kalman filter is used to predict the track of the rocket. Several tracking experiments show the approach is accurate and fast, and it has a better robust performance during the state changing, the size changing and the shelter instance.

Key words: rocket target tracking, multiple related template, template matching, Kalman filter, track prediction

中图分类号: