基于粒子滤波的多自由度运动目标跟踪

王国良; 刘金国

doi:10.3788/OPE.20111904.0864

您当前的位置：

首页 >

文章列表页 >

基于粒子滤波的多自由度运动目标跟踪

信息科学 | 更新时间：2020-08-12

- 基于粒子滤波的多自由度运动目标跟踪
- Moving object tracking with multi-degree-of-freedom based on particle filters
- 光学精密工程 2011年19卷第4期页码：864-869
- 作者机构：
  
  中国科学院长春光学精密机械与物理研究所,吉林长春 130033
- 作者简介：
- 基金信息：
  
  中国科学院"();优秀博士学位论文、院长奖获得者科研启动专项基金"();资助项目()
- DOI：10.3788/OPE.20111904.0864
  中图分类号： TP391.4
- 收稿日期：2010-04-30，
  
  修回日期：2010-08-06，
  
  网络出版日期：2011-04-26，
  
  纸质出版日期：2011-04-26
- 稿件说明：
移动端阅览
王国良, 刘金国. 基于粒子滤波的多自由度运动目标跟踪[J]. 光学精密工程, 2011,19(4): 864-869

WANG Guo-liang, LIU Jin-guo. Moving object tracking with multi-degree-of-freedom based on particle filters[J]. Editorial Office of Optics and Precision Engineering, 2011,19(4): 864-869
王国良, 刘金国. 基于粒子滤波的多自由度运动目标跟踪[J]. 光学精密工程, 2011,19(4): 864-869 DOI： 10.3788/OPE.20111904.0864.

WANG Guo-liang, LIU Jin-guo. Moving object tracking with multi-degree-of-freedom based on particle filters[J]. Editorial Office of Optics and Precision Engineering, 2011,19(4): 864-869 DOI： 10.3788/OPE.20111904.0864.

摘要

为了在复杂背景下跟踪视频序列中的多自由度运动目标

基于粒子滤波理论提出了一种多自由度运动目标的稳健跟踪算法。首先

采用均值漂移算法目标模型与候选模型的相似度作为观测值的构造基础;然后

在核函数下颜色直方图的基础上

对目标的中心位置和表征目标形状的协方差矩阵进行更新

从而自适应地调整核函数带宽的大小

修正跟踪窗口的尺寸

实现对多自由度运动目标的跟踪。在粒子滤波中

取粒子数

为100

目标参考区域中心在

轴上的坐标分量随机游动的方差为5

参考区域在

轴上的尺度及角度随机游动的方差为0.1;在不同场景和不同目标的跟踪实验中

提出的算法能够稳健、可靠地跟踪多自由度运动目标

对目标尺度和角度变化具有良好的适应性。

Abstract

In order to robustly track the multi-degree-of-freedom moving objects in video sequences at a complex background

a tracking algorithm for multi-degree-of-freedom moving objects was proposed based on the particle filter principle. Firstly

the similarity of a target model and a candidate model was taken as the structural basis of observation by using mean shift algorithm. Then

based on the kernel-color histogram

the center position of the object and the covariance matrix that described the shape of the object were updated to adjust kernel-bandwidth and modify the size of tracking window

then to implement the tracking for multi-degree-of-freedom moving objects. In particle filter

the number of particles is to be 100

the variance of coordinate components is 5 in the covariance matrix

and the variance of scale and angle components is 0.1. Tracking experiments for various objects in different scenarios show that the proposed algorithm can track multi-degree-of-freedom moving objects steadily

and can adapt to the change of scales and angles for objects.

关键词

Keywords

references

GREIFFENHAGEN M, RAMESH V, COMANICIU D, et al.. Statistical modeling and performance characterization of a real-time dual camera surveillance system [J]. IEEE International Conference on Computer Vision and Pattern Recognition, 2000(2):2335-2342.[2] MENSER B,BRUNIG M. Face detection and tracking for video coding applications . In Asilomar Conference on Signals, Systems, and Computers. USA: IEEE Press, 2000,1:49-53.[3] 吴川,杨冬,郝志成. 基于粒子滤波的彩色图像跟踪[J]. 光学精密工程,2009,17(10):2542-2547. WU CH, YANG D, HAO ZH CH. Color image tracking algorithm based on particle filter [J]. Opt. Precision Eng., 2009,17(10):2542-2547. (in Chinese)[4] 陈谋,姜长生. 自适应模糊逻辑的多模型跟踪[J]. 光学精密工程,2009,17(4):867-873. CHEN M, JING CH SH. Multiple model tracking based on adaptive fuzzy logic [J]. Opt. Precision Eng., 2009,17(4):867-873. (in Chinese)[5] 陈爱华,孟勃,朱明,等. 多模式融合的目标跟踪算法[J]. 光学精密工程,2009,17(1):185-190. CHEN AI H, MENG B, ZHU M, et al.. Multi-pattern fusion algorithm for target tracking [J]. Opt. Precision Eng., 2009,17(1):185-190. (in Chinese)[6] 赵其杰,屠大维,高健,等. 基于Kalman滤波的视觉预测目标跟踪及其应用[J]. 光学精密工程,2008,16(5):937-942. ZHAO Q J, TU D W, GAO J, et al.. Kalman filter based vision predicting and object tracking method and its application[J]. Opt. Precision Eng., 2008,16(5):937-942. (in Chinese)[7] 赵鹏,沈庭芝,单宝堂. 一种基于粒子滤波的无人机电视引导系统目标跟踪算法[J]. 光学精密工程,2008,16(1):134-140. ZHAO P, SHEN T ZH, SH B T. An object tracking algorithm for TV guiding system of UAV based on particle filter [J]. Opt. Precision Eng., 2008,16(1):134-140. (in Chinese)[8] GORDON N, SALMOND D, SMITH A. Novel approach to nonlinear/non-gaussian baysian state estimation [J]. IEE Proceedings on Radar and Signal Processing, 1993, 140(2):107-113.[9] LIU J S, CHEN R. Sequential Monte Carlo methods for dynamical systems [J]. J. of the American Statistical Association, 1998,93(5):1032-1044.[10] ISARD M, BLAKE A. CONDENSATION-Conditional density propagation for visual tracking [J]. Int. J. Comput. Vis.,1998,29(1):5-28.[11] SANJEEV ARULAMPALAM M, MASKELL S, GORDON N, et al.. A tutorial on particle filters for online nonlinear/non-gaussian bayesial tracking [J]. IEEE Trans. On Signal Proc., 2002,50(2):174-188.[12] CRISAN D, DOUCET A. A survey of convergence results on particle filtering methods for practitioners [J]. IEEE Transactions on Signal Processing, 2002,50(3):736-746.[13] DOUCET A, GODSILL S,ANDRIEU C. On sequential monte carlo sampling methods for Bayesian filtering [J]. Statistics and Computing, 2000,10(3):197-208.[14] KASS M, WITKIN A, TERZOPOULOS D. Snake: active contour models [J]. International Journal of Computer Vision, 1987,1(4): 321-331.[15] COMANICIU D,MEER P. Mean shift: A Robust application toward feature space analysis [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002,24(5):603-619.

浏览量

318

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于仿射变换与均匀采样建模的目标跟踪

基于知识蒸馏的Transformer视觉跟踪器

针对RGBT跟踪的特殊属性的跨模态交互融合网络

XY工作台六自由度误差在线测量和补偿

基于显著性区域加权的相关滤波目标跟踪