在海上智能交通中,对移动船舶的目标跟踪会受到背景颜色、物体遮挡、亮度等问题的影响,从而降低了跟踪率,因此在实际的工程应用中需要过滤不利因素,得到更有利的目标特征。本文将粒子滤波应用于移动视频目标跟踪的智能过滤中,并对粒子滤波进行优化,最后通过对比实验来说明优化后的算法鲁棒性强、系统的估计误差更小。
Moving video target tracking is a hot research topic in the field of machine vision. In the sea of intelligent transportation, the target tracking of moving ship will be affected by background color, object occlusion, brightness and other issues. Therefore, it was necessary to filter these factors to get more characteristics of the target. In this paper, the particle filter was applied to the intelligent filtering of moving video object tracking. The particle filter was optimized. Finally, the comparison experiments showed that the optimized algorithm was robust, and the system error was smaller.
2017,39(1A): 112-114 收稿日期:2016-11-01
DOI:10.3404/j.issn.1672-7619.2017.1A.038
分类号:U665.26A
作者简介:李倩(1982-),女,硕士,讲师,研究方向为计算机科学与技术研究。
参考文献:
[1] GORDON N. A hybrid bootstrap filter for target tracking in clutter[J]. IEEE Transactions on Aerospace & Electronic Systems, 1997, 33(1):353-358.
[2] 焦安霞, 姜弢. 视频序列中动目标快速跟踪新算法的研究[J]. 应用科技, 2008, 35(12):7-10.
[3] 邓文坛, 张三同, 余纯. 一种改进的粒子滤波跟踪算法的研究[J]. 自动化技术与应用, 2008, 27(3):84-87.
[4] 李巍, 赵英凯, 钱厚亮. 一种基于纹理和颜色的目标跟踪方法[J]. 计算机仿真, 2011, 28(1):273-276.