基于压缩感知的多特征实时跟踪

朱秋平; 颜佳; 张虎; 范赐恩; 邓德祥

doi:10.3788/OPE.20132102.0437

您当前的位置：

首页 >

文章列表页 >

基于压缩感知的多特征实时跟踪

信息科学 | 更新时间：2020-08-12

- 基于压缩感知的多特征实时跟踪
- Real-time tracking using multiple features based on compressive sensing
- 光学精密工程 2013年21卷第2期页码：437-444
- 作者机构：
  
  武汉大学电子信息学院,湖北武汉,中国,430072
- 作者简介：
- 基金信息：
  
  国家自然科学基金面上项目(51275504)
- DOI：10.3788/OPE.20132102.0437
  中图分类号： TP391
- 收稿日期：2012-08-09，
  
  修回日期：2012-10-12，
  
  网络出版日期：2013-02-23，
  
  纸质出版日期：2013-02-15
- 稿件说明：
移动端阅览
朱秋平颜佳张虎范赐恩邓德祥. 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 Qiu-ping YAN Jia ZHANG Hu FAN Ci-en DENG De-xiang. Real-time tracking using multiple features based on compressive sensing [J]. Editorial Office of Optics and Precision Engineering, 2013,21(2): 437-444
朱秋平颜佳张虎范赐恩邓德祥. 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 DOI： 10.3788/OPE.20132102.0437.

ZHU Qiu-ping YAN Jia ZHANG Hu FAN Ci-en DENG De-xiang. Real-time tracking using multiple features based on compressive sensing [J]. Editorial Office of Optics and Precision Engineering, 2013,21(2): 437-444 DOI： 10.3788/OPE.20132102.0437.

摘要

针对基于压缩感知的目标跟踪算法中存在的特征单一，在目标纹理变化、光照变化较大时跟踪不稳定、易丢失目标的问题，提出了多特征联合的实时跟踪算法。该算法以多个矩阵作为压缩感知中的投影矩阵，将压缩后的数据作为特征来提取出跟踪所需的多种特征。在更新过程中，针对不同特征在跟踪过程中的稳定性不同，采取不同速度的更新方法，使得在目标环境变化时跟踪的鲁棒性仍然很高。对不同视频的测试结果表明，提出的方法在目标运动、旋转、纹理变化和光照变化的情况下跟踪准确，在目标大小为70 pixel×100 pixel时平均帧速为23 frame/s，满足实时跟踪的要求。与单一特征的压缩感知算法相比，本算法在目标纹理和光照变化很大的情况下仍能完成稳定的实时跟踪。

Abstract

As traditional tracking algorithm based on compressive sensing can extrack few features and fails to track targets stably in textures and lightings changed

a real-time tracking algorithm using multi-features based on compressive sensing is proposed.The algorithm uses multiple matrixes as the projection matrix of the compressive sensing

and the compressed data as the multiple features to extract the multiple features needed by track. Because the feature stability is different in tracky processing

different update levels are taken to maintain the tracking robustness in varied target conditions. The proposed algorithm is tested with variant video sequences and the results show that the algorithm achieves stable tracking for the target moved or the light changed

and average computing frame rate is 23 frame/s when the target scale is 70 pixel×100 pixel.Obtained results satisfy the requirements of real-time tracking. As compared with the compressive tracking with single kind of feature

the algorithm can track stably under big changed lightings and target textures.

关键词

Keywords

references

WANG S, LU H CH, YANG F, et al.. Superpixel tracking [C]. Compute Vision (ICCV), 2011: 1323-1330.[2]ORON S, AHARON B H, LEVI D, et al.. Locally orderless tracking [C]. Computer Vision and Pattern Recognition, IEEE Computer Society Conference, 2012.[3]KWON J, LEE K M. Tracking of a non-rigid object via patch-based dynamic appearance modeling and adaptive basin hopping Monte Carlo sampling [C]. Computer Vision and Pattern Recognition, IEEE Computer Society Conference, 2009,1208-1215.[4]KALAL Z, MATAS J, MIKOLAJCZYK K. Online learning of robust object detectors during unstable tracking [C]. Computer Vision Workshops (ICCV Workshops), 2009: 1417-1424.[5]GRABNER H, GRABNER M, BISCHOF H. Real time tracking via on-line boosting [C]. Proceedings of British Machine Vision Conference, 2006, 1:47-56.[6]程有龙，李斌，张文聪，等，融合先验知识的自适应行人跟踪算法 [J]. 模式识别与人工智能，2009，22（5）：704-708.CHENG Y L,LI B, ZHANG W C,et al.. An adaptive pedestrian tracking algorithm with prior knowledge [J]. Pattern Recognition and Artificial Intelligence, 2009, 22(5): 704-708.(in Chinese)[7]ADAM A, RIVLIN E, SHIMSHON L. Robust fragments -based tracking using the integral histogram [C]. Computer Vision and Pattern Recognition, IEEE Computer Society Conference, 2006:798-805.[8]NEJHUM S M S, HO J, YANG M H. Visual tracking with histograms and articulating blocks [C]. Computer Vision and Pattern Recognition, IEEE Computer Society Conference, 2008:1-8.[9]YANG J CH, YU K, HUANG T. Supervised Translation-Invariant sparse coding [C]. Computer Vision and Pattern Recognition (CVPR), 2010:3517-3524.[10]LI H X, SHEN CH H. Real-time visual tracking using compressive sensing [C]. Computer Vision and Pattern Recognition (CVPR), 2011:1305-1312.[11]ZHANG K H, ZHANG L, YANG M H. Real-time compressive tracking [C]. European Conference on Computer Vision, 2012.[12]DONOHO D L. Compressed sensing [J]. Information Theory, 2006, 52(4): 1289-1306.[13]VIOLA P, JONES M. Rapid object detection using a boosted cascade of simple features [C]. Computer Vision and Pattern Recognition (CVPR), 2001,1: 511-518.[14]COLLINSR, YANX L, LEORDEANU M. Online selection of discriminative tracking features [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(10):1631-1643.[15]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)

浏览量

219

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

数据驱动的多模复合制导信息融合及其试验验证

联合图像层级特征的压缩感知迭代重构

基于非机动单站的目标运动状态无偏估计

联合全局与局部特征的深度压缩感知图像重构

面向航天光学遥感场景压缩感知测量值的舰船检测