###目标跟踪

点击查看Evernot原文。

#@author:       gr
#@date:         2014-07-21
#@email:        [email protected]

Guide

进行多目标跟踪的学习。

Contents

1. 这是别人整理的一些跟踪方面的资料，方便以后学习使用。

2. CVPR 2014上关于 tracking 的文章还是比较多的。

3. UIUC的Jia-Bin Huang同学收集的关于tracking的代码。

   • Particle filter object tracking [1] [Project](http://blogs.oregonstate.edu/hess/code/particles/)
     
   • KLT Tracker [2-3] [Project](http://www.ces.clemson.edu/~stb/klt/)
     
   • MILTrack [4] [Code](http://vision.ucsd.edu/~bbabenko/data/MilTracker-V1.0.zip)
     
   • Incremental Learning for Robust Visual Tracking [5] [Project](http://www.cs.toronto.edu/~dross/ivt/)
     
   • Online Boosting Trackers [6-7] [Project](http://www.vision.ee.ethz.ch/boostingTrackers/index.htm)
     
   • L1 Tracking [8] [Matlab code](http://www.dabi.temple.edu/~hbling/code/L1_Tracking_v4_release.zip)

   代码相关论文

   1. P. Perez, C. Hue, J. Vermaak, and M. Gangnet. Color-Based Probabilistic Tracking ECCV, 2002. [PDF]
      
   2. B.D. Lucas and T. Kanade, An Iterative Image Registration Technique with an Application to Stereo Vision, IJCAI 1981. [PDF]
      
   3. J. Shi, C. Tomasi, Good Feature to Track, CVPR 1994. [PDF]
      
   4. B. Babenko, M. H. Yang, S. Belongie, Robust Object Tracking with Online Multiple Instance Learning, PAMI 2011 [PDF]
      
   5. D. Ross, J. Lim, R.-S. Lin, M.-H. Yang, Incremental Learning for Robust Visual Tracking, IJCV 2007 [PDF]
      
   6. H. Grabner, and H. Bischof, On-line Boosting and Vision, CVPR 2006 [PDF]
      
   7. H. Grabner, C. Leistner, and H. Bischof, Semi-supervised On-line Boosting for Robust Tracking, ECCV 2008 [PDF]
      
   8. X. Mei and H. Ling, Robust Visual Tracking using L1 Minimization, ICCV, 2009. [PDF]
4. UCF的GMCP-Tracker方法，可以进行多个行人跟踪，相关论文是Global Multi-object Tracking Using Generalized Minimum Clique Graphs。效果不错，但貌似不是实时的，论文中说在Matlab中实现，一帧要4s左右，不过可以进行优化。
   

5. CVPR2014:Occlusion Geodesics for Online Multi-Object Tracking和CVPR2013:Robust Real-Time Tracking of Multiple Objects by Volumetric Mass Densities两篇文章，第一篇的代码可以直接运行，效果看起来也不错。

Reference

1. http://www.yale.edu/perception/Brian/refGuides/MOT.html
   
2. CVPR 2014