Real-time compressive tracking based on online feature selection

MAO Zheng; YUAN Jian-jian; WU Zhen-rong; QU Jin-song; LI Hong-yan

doi:null

您当前的位置：

首页 >

文章列表页 >

Real-time compressive tracking based on online feature selection

Information Sciences | 更新时间：2020-08-13

- Real-time compressive tracking based on online feature selection
- Optics and Precision Engineering Vol. 22, Issue 3, Pages: 730-736(2014)
- 作者机构：
  
  北京工业大学电子信息与控制工程学院北京,100022
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP391
- Published：25 March 2014
- 稿件说明：
移动端阅览
毛征,袁建建,吴珍荣等. 基于在线特征选择的实时压缩跟踪[J]. 光学精密工程, 2014,22(3): 730-736

MAO Zheng, YUAN Jian-jian, WU Zhen-rong etc. Real-time compressive tracking based on online feature selection[J]. Editorial Office of Optics and Precision Engineering, 2014,22(3): 730-736
毛征,袁建建,吴珍荣等. 基于在线特征选择的实时压缩跟踪[J]. 光学精密工程, 2014,22(3): 730-736 DOI：

MAO Zheng, YUAN Jian-jian, WU Zhen-rong etc. Real-time compressive tracking based on online feature selection[J]. Editorial Office of Optics and Precision Engineering, 2014,22(3): 730-736 DOI：

摘要

针对原始压缩跟踪算法无法自适应选择特征易导致目标丢失或者漂移这一现象

提出一种基于在线选择特征的实时压缩跟踪算法。首先

在初始化阶段生成两个互补的投影矩阵

利用该投影矩阵提取特征构造候选特征池。然后

通过特征置信度度量策略实时从候选特征池中选择置信度较高的特征

并融合所选特征对应的置信度构造分类器。最后

利用该分类器对候选样本做二元分类处理

获得最高分类器响应值的样本作为最后跟踪结果;而上一帧跟踪结果用来在线更新特征池和分类器为后续跟踪做准备。本算法在多个公共测试视频序列与原始压缩跟踪算法进行了对比

结果表明其跟踪精度和鲁棒性方面得到了改善

对于320 pixel×240 pixel大小的视频平均处理帧速为25 frame/s

满足实时跟踪要求。

Abstract

关键词

Keywords

references

COLLINS R T, LIU Y X, LEORDEANU M. Online selection of discriminative tracking features [J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005,27(10):1631-1643.

GRABNER H, LEISTNER C, BISCHOF H.Semi-supervised on-line booting for robust tracking[J].Lecture Notes in Computer Science, 2008,5302:234-247.

BABENKO B, YANG M H, BELONGIE S. Robust object tracking with online multiple instance learning[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011,33(8):1619-1632.

BALAN A O, BLACK M J.An adaptive appearance model approach for model-based articulated object tracking[C].2006 IEEE Computer Society Conterence on Computer Vision and Pattern Recognition, 2006, (1):758-765.

ROSS D A, LIM J W, LIN R S, et al..Incremental learning for robust visual tracking [J].International Journal of Computer Vision, 2008, 77(1-3):125-141.

LIN R S, ROSS D, LIM J, et al..Adaptive discriminative generative model and its application [C].NIPS, 2004:801-808.

FRIEDMAN J, HASTIE T, TIBSHIRANI R.Adaptive logistic regression:a statistical view of boosting [J].The Annals of Statistics, 2000, 28(2):337-407.

DONOHO D L.Compressed sensing[J].Information Theory, 2006, 52(4):1289-1306.

LI H X, SHEN CH H, SHI Q F.Real-time visual tracking using compressive sensing[C].2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011:1305-1312.

ZHANG K H, ZHANG L, YANG M H. Real-time compressive tracking [C].Computer Vision-ECCV 2012,2012,7574:864-877.

朱秋平, 颜佳, 张虎, 等.基于压缩感知的多特征实时跟踪[J].光学精密工程, 2013, 21(2):437-444.

ZHU Q P, YAN J, ZHANG H, et al..Real-time tracking using multiple features based on compressive sensing [J].Opt. Precision Eng., 2013, 21 (2):437-444.(in Chinese).

ACHLIOPTAS D.Database-friendly random projections:Johnson-Lindenstrauss with binary coins[J].Comput.Syst.Sci 66, 2003:671-687.

颜佳, 吴敏渊.遮挡环境下采用在线Boosting的目标跟踪[J].光学精密工程, 2012, 20(2):439-446.

YAN J, WU M Y.On line boosting based target tracking under occlusion [J].Opt. Precision Eng., 2012, 20(2):439-446.(in Chinese).导师简介:

毛征(1959-), 男, 工学博士, 主要从事光电图像信息处理、系统仿真、数据融合等方面的研究。E-mail:maozhen@bjut.edu.cn

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

No data

Related Author

No data

Related Institution

No data

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