matlab版源程序：http://download.csdn.net/detail/cv_richie/4982673
C程序：http://download.csdn.net/detail/cv_richie/4982678
晚点我会把我注释的版本发上来。
看了Zdenek的Tracking-Learning-Detection.决定从程序入手，学习这个算法。
算法的源程序代码可以从作者的个人网站上下载http://info.ee.surrey.ac.uk/Personal/Z.Kalal/
这是一个MATLAB调用C++程序的结构，按照网上其他人的过来路，安装好VS2008,MATLB2010B与OPENCV2.2
""""""""""""""""""""""""""""""""""""""下面这段发现不是最好的方法""""""""""""""""""""""""""""""
在MATLAB中需要通过MEX编译C++文件实现调用
输入mex -setup选择VS2008的编译器
输入mex -v会显示错误，不用管它，直接在其中找到
Options file=C:\Users\Administrator\AppData\Roaming\MathWorks\MATLAB\R2010b\mexopts.bat
用编辑器打开这个bat文件，在PATH，INCLUDE，LIB相应的赋值后面添加OPENCV2.2的路径，如图
接下来，在下面的set LINKFLAGS=/dll下添加，opencv的库文件，如这里添加修改为
set LINKFLAGS=/dll /export:%ENTRYPOINT% /LIBPATH:"%LIBLOC%" opencv_calib3d220d.lib opencv_contrib220d.lib opencv_features2d220d.lib opencv_ffmpeg220d.lib opencv_flann220d.lib opencv_gpu220d.lib
opencv_core220d.lib opencv_highgui220d.lib opencv_imgproc220d.lib opencv_legacy220d.lib opencv_ml220d.lib opencv_objdetect220d.lib opencv_ts220.lib opencv_video220d.lib libmx.lib libmex.lib libmat.lib /MACHINE:X86 kernel32.lib user32.lib gdi32.lib winspool.lib
comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /incremental:NO /implib:"%LIB_NAME%.x" /MAP:"%OUTDIR%%MEX_NAME%%MEX_EXT%.map"
opencv_core220d.lib opencv_highgui220d.lib opencv_imgproc220d.lib opencv_legacy220d.lib opencv_ml220d.lib opencv_objdetect220d.lib opencv_ts220.lib opencv_video220d.lib libmx.lib libmex.lib libmat.lib /MACHINE:X86 kernel32.lib user32.lib gdi32.lib winspool.lib
comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /incremental:NO /implib:"%LIB_NAME%.x" /MAP:"%OUTDIR%%MEX_NAME%%MEX_EXT%.map"
""""""""""""""""""""""""""""""""""""""上面这段发现不是最好的方法""""""""""""""""""""""""""""""
其实只需打开compile.m文件，
include = ' -Id:\software\OpenCV2.2\include\opencv -Id:\software\OpenCV2.2\include\';
libpath = 'D:\software\OpenCV2.2\lib\';
把这两行修改为相应的你的电脑上的OPENCV目录即可！！
现在再运行TLD程序目录下的compile.m文件即可编译通过。
这里参考了博文：http://blog.csdn.net/climbingc/article/details/6762424
另有此方法未验证：http://blog.csdn.net/xiankaichen/article/details/7403670
附关于TLD的几篇文章
[1]. Kalal, Z.,K. Mikolajczyk,J. Matas. Tracking-Learning-Detection. Pattern Analysis and Machine Intelligence, IEEE , 2012. 34(7): 1409-1422.
[1]. Kalal, Z.,K. Mikolajczyk,J. Matas. Forward-Backward Error: Automatic Detection of Tracking Failures. in Pattern Recognition (ICPR), 2010 20th International Conference on. 2010.
[1]. Kalal, Z.,K. Mikolajczyk,J. Matas. Face-TLD: Tracking-Learning-Detection applied to faces. in Image Processing (ICIP), 2010 17th IEEE International Conference on. 2010.
[1]. Kalal, Z.,J. Matas,K. Mikolajczyk. Online learning of robust object detectors during unstable tracking. in Computer Vision Workshops (ICCV Workshops), 2009 IEEE 12th International Conference on. 2009.
[1]. Kalal, Z.,J. Matas,K. Mikolajczyk. P-N learning: Bootstrapping binary classifiers by structural constraints. in Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on. 2010.