Object tracking based on affine transform and uniform sampling

ZHAO Peng-peng; CUI Shao-hui; GAO Min; FANG Dan

doi:10.3788/OPE.20152313.0777

您当前的位置：

首页 >

文章列表页 >

Object tracking based on affine transform and uniform sampling

更新时间：2020-08-13

- Object tracking based on affine transform and uniform sampling
- Optics and Precision Engineering Vol. 23, Issue 10z, Pages: 776-782(2015)
- 作者机构：
  
  军械工程学院导弹工程系,河北石家庄,050003
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20152313.0777
  CLC： TP391.4
- Received：02 June 2015，
  
  Revised：30 June 2015，
  
  Published：14 November 2015
- 稿件说明：
移动端阅览
赵鹏鹏, 崔少辉, 高敏等. 基于仿射变换与均匀采样建模的目标跟踪[J]. 光学精密工程, 2015,23(10z): 776-782

ZHAO Peng-peng, CUI Shao-hui, GAO Min etc. Object tracking based on affine transform and uniform sampling[J]. Editorial Office of Optics and Precision Engineering, 2015,23(10z): 776-782
赵鹏鹏, 崔少辉, 高敏等. 基于仿射变换与均匀采样建模的目标跟踪[J]. 光学精密工程, 2015,23(10z): 776-782 DOI： 10.3788/OPE.20152313.0777.

ZHAO Peng-peng, CUI Shao-hui, GAO Min etc. Object tracking based on affine transform and uniform sampling[J]. Editorial Office of Optics and Precision Engineering, 2015,23(10z): 776-782 DOI： 10.3788/OPE.20152313.0777.

摘要

针对图像跟踪过程中目标发生的缩放、旋转以及斜切等几何变换

提出了基于仿射变换与均匀采样建模的目标跟踪方法。以粒子滤波算法为基本框架

使用6个仿射参数作为状态变量来预测目标可能发生的几何形变

并通过对仿射参数所表示的区域进行均匀采样实现对目标以及候选目标的建模。然后选用合适的相似性度量函数计算两组采样点之间的灰度差异以建立观测模型

从而得到状态变量的最优估计

实现目标的稳定跟踪。实验结果表明:视频序列的跟踪误差在10 pixel以内

优于传统目标跟踪方法以及其他基于仿射变换与特征建模的跟踪方法。该方法能够在复杂环境下稳定跟踪发生几何形变的目标。

Abstract

A target tracking method based on the affine transformation and uniform sampling was proposed to solve the issues that targets may generate different geometric transformations such as scaling

rotating and beveling in the process of image tracking. Based on the particle filter algorithm

six affine parameters were set as the stable variables to predict likely deformation of the target. Then

the target modeling and candidate target modeling were constructed by uniform sampling in the affine parameter area. A similarity measuring function was selected for calculation of gray differences between two sampling sites to create a monitoring model

thus the optimal estimation of the state variables was obtained and then stable tracking of the target was realized. The simulation experiment demonstrates that the proposed method can stably track geometric deformation targets

and the deviation is less than 10 pixel. The robustness and accuracy of the method are definitely superior to that of traditional target tracking method as well as other tracking method based on affine transformation and feature modeling.

关键词

Keywords

references

孙斌,黄神治. 移动背景下运动目标检测与跟踪技术研究[J]. 电子测量与仪器学报,2011,25(3):206-210. SUN B,HUANG SH ZH.Target detection and tracking under moving background[J].Journal of Electronic Measurement and Instrument,2011,25(3):206-210.(in Chinese)

刘瑞兰,陈小惠. 基于模糊交互多模型的机动目标被动跟踪算法[J]. 电子测量与仪器学报,2012,26(10):846-850. LIU R L,CHEN X H.Maneuvering target tracking algorithm based on fuzzy interacting multiple mode[J].Journal of Electronic Measurement and Instrument,2012,26(10):846-850.(in Chinese)

JEYAKAR J, BABU R V, RAMAKRISHNAN K R. Robust object tracking with background-weighted local Kernels[J]. Computer Vision and Image Understanding, 2008, 112(3):296-309.

BABU R V, PEREZ P, BOUTHEMY P. Robust tracking with motion estimation and local Kernel-based color modeling[J]. Image and Vision Computing, 2007, 25(8):1205-1216.

袁广林,薛模根,谢恺,等. 基于核函数粒子滤波和多特征自适应融合的目标跟踪[J]. 计算机辅助设计与图形学学报 2009,21(12):1774-1784. YUAN G L, XUE M G, XIE K, et al.. Kernel-based particle filter for target tracking with adaptive multiple features fusion[J]. Journal of Computer-Aided Design & Computer Graphics, 2009,21(12):1774-1784.(in Chinese)

史泽林,刘云鹏,李广伟. 基于李代数的变形目标跟踪[J]. 自动化学报, 2012, 38(3):420-429. SHI Z L, LIU Y P, LI G W. Deformable object tracking based on Lie algebra[J]. Acta Automatica Sinica, 2012, 38(3):420-429.

KWON J H,PARKFC.Visual tracking via particle filtering on the affine group[C].International Conference on Information and Automation,Seoul,2008:198-216.

KWONJH, LEEKM, PAR KFC.Visual tracking via geometric particle filtering on the affine group with optimal importance functions[C].IEEE Conference on Computer Vision and Pattern Recognition,Seoul,2009:991-998.

SALMOND D J, BIRCH H. A particle filter for track-before-detect[C]. Proceedings of the American Control Conference, New York:IEEE, 2001:3755-3760.

肖延国,魏建明,邢涛,等. 分布式Unscented粒子滤波跟踪[J]. 光学精密工程, 2009, 17(7):1708-1713. XIAO Y G, WEI J M, XING T, et al.. Target tracking using distributed Unscented particle filter in sensor network[J]. Opt. Precision Eng., 2009, 17(7):1708-1713.(in Chinese)

Views

503

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Moving object tracking with multi-degree-of-freedom based on particle filters

A Transformer-based visual tracker via knowledge distillation

Special attribute-based cross-modal interactive fusion network for RGBT tracking

Salient region weighted correlation filter for object tracking

Correlation filter tracking algorithm based on double model

Related Author

WANG Guo-liang

LIU Jin-guo

LI Na

LIU Mengqiao

PAN Jinting

HUANG Kai

JIA Xingxuan

SHAO Xiaoqiang

Related Institution

Changchun Institute of Optics,Fine Mechanics and Physics, Chinese Academy of Sciences

School of Communication and Information Engineering， Xi’an University of Posts and Telecommunications

College of Electrical and Control Engineering， Xi’an University of Science and Technology

University of Chinese Academy of Sciences

Changchun Institute of Optics， Fine Mechanics and Physics Chinese Academy of Sciences

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰