TLuthra-OpenTLD-81e521f
所属分类：图形图像处理
开发工具：Visual C++
文件大小：2633KB
下载次数：230
上传日期：2012-09-01 21:34:19
上 传 者：
247991
说明： 经典的目标跟踪算法，基于TLD的C代码。可以移植到VC或者QT上。算法速度还可以，就是精度不如matlab的，可以参考。
(Classical target tracking algorithm, based on the C code TLD. Can be ported to the VC or QT. The algorithm speed accuracy better than matlab can refer.)
文件列表:
TLuthra-OpenTLD-81e521f (0, 2012-04-25)
TLuthra-OpenTLD-81e521f\CMakeLists.txt (2478, 2012-04-25)
TLuthra-OpenTLD-81e521f\LICENSE (35146, 2012-04-25)
TLuthra-OpenTLD-81e521f\OpenTLDConfig.cmake.in (554, 2012-04-25)
TLuthra-OpenTLD-81e521f\build (0, 2012-04-25)
TLuthra-OpenTLD-81e521f\build\click (9080, 2012-04-25)
TLuthra-OpenTLD-81e521f\build\click.m (1285, 2012-04-25)
TLuthra-OpenTLD-81e521f\build\finger (5067344, 2012-04-25)
TLuthra-OpenTLD-81e521f\build\finger2 (2713380, 2012-04-25)
TLuthra-OpenTLD-81e521f\build\load_finger.cfg (2376, 2012-04-25)
TLuthra-OpenTLD-81e521f\build\load_pen.cfg (2369, 2012-04-25)
TLuthra-OpenTLD-81e521f\build\pen (6114546, 2012-04-25)
TLuthra-OpenTLD-81e521f\build\tld (329428, 2012-04-25)
TLuthra-OpenTLD-81e521f\conf (0, 2012-04-25)
TLuthra-OpenTLD-81e521f\conf\config-sample.cfg (2428, 2012-04-25)
TLuthra-OpenTLD-81e521f\res (0, 2012-04-25)
TLuthra-OpenTLD-81e521f\res\tld.png (15867, 2012-04-25)
TLuthra-OpenTLD-81e521f\src (0, 2012-04-25)
TLuthra-OpenTLD-81e521f\src\CMakeLists.txt (314, 2012-04-25)
TLuthra-OpenTLD-81e521f\src\OpenTLD.cpp (491, 2012-04-25)
TLuthra-OpenTLD-81e521f\src\config (0, 2012-04-25)
TLuthra-OpenTLD-81e521f\src\config\CMakeLists.txt (342, 2012-04-25)
TLuthra-OpenTLD-81e521f\src\config\grammar.c (54422, 2012-04-25)
TLuthra-OpenTLD-81e521f\src\config\grammar.h (3144, 2012-04-25)
TLuthra-OpenTLD-81e521f\src\config\libconfig.c (40254, 2012-04-25)
TLuthra-OpenTLD-81e521f\src\config\libconfig.h (12342, 2012-04-25)
TLuthra-OpenTLD-81e521f\src\config\libconfig.h++ (13509, 2012-04-25)
TLuthra-OpenTLD-81e521f\src\config\libconfig.hh (1076, 2012-04-25)
TLuthra-OpenTLD-81e521f\src\config\libconfigcpp.c++ (29530, 2012-04-25)
TLuthra-OpenTLD-81e521f\src\config\libconfigcpp.cc (1079, 2012-04-25)
TLuthra-OpenTLD-81e521f\src\config\parsectx.h (1639, 2012-04-25)
TLuthra-OpenTLD-81e521f\src\config\scanctx.c (4675, 2012-04-25)
TLuthra-OpenTLD-81e521f\src\config\scanctx.h (2093, 2012-04-25)
TLuthra-OpenTLD-81e521f\src\config\scanner.c (68124, 2012-04-25)
TLuthra-OpenTLD-81e521f\src\config\scanner.h (8256, 2012-04-25)
TLuthra-OpenTLD-81e521f\src\config\strbuf.c (1874, 2012-04-25)
TLuthra-OpenTLD-81e521f\src\config\strbuf.h (1294, 2012-04-25)
TLuthra-OpenTLD-81e521f\src\config\wincompat.h (2374, 2012-04-25)
... ...
Introduction
==============
This is a C++ implementation of OpenTLD that was originally published in MATLAB by Zdenek Kalal. OpenTLD is used for tracking objects in video streams. What makes this algorithm outstanding is that it does not make use of any training data. This implementation is based solely on open source libraries, meaning that you do not need any commercial products to compile or run it.
The easiest way to get started is to download the precompiled binaries that are available for Windows and Ubuntu 10.04. You can get a .deb package here:
http://dl.dropbox.com/u/8715460/tld.deb
and a windows installer file here:
http://dl.dropbox.com/u/8715460/tld.zip
If you have a webcam attached to your PC, you can simply execute tld (on Ubuntu) or tld.exe (on Windows) in order to
try it out. For other configuration options, please see below.
Usage
=======
Keyboard shortcuts
-------------------
q...quit
b...remember current frame as background model / clear background
c...clear model and stop tracking
l...toggle learning
a...toggle alternating mode (if true, detector is switched off when tracker is available)
e...export model to file specified in configuration parameter "modelExportFile"
i...import model from file specified in configuration parameter "modelPath"
r...clear model, let user reinit tracking
command line options
--------------------
__usage__
`tld [option arguments] [arguments]`
__option arguments__
`[-a
]` video starts at the frameNumber _startFrameNumber_
`[-b ]` Initial bounding box
`[-d ]` select input device: _device_=(IMGS|CAM|VID)
IMGS: capture from images
CAM: capture from connected camera
VID: capture from a video
`[-e ]` export model after run to _path_
`[-f]` shows foreground
`[-i ]` _path_ to the images or to the video.
`[-h]` shows help
`[-m ]` if specified load a model from _path_. An initialBoundingBox must be specified or selectManually must be true.
`[-n ]` Specifies the video device to use (defaults to 0). Useful to select a different camera when multiple cameras are connected.
`[-p path]` prints results into the file _path_
`[-s]` if set, user can select initial bounding box
`[-t ]` threshold for determining positive results
`[-z ]` video ends at the frameNumber _lastFrameNumber_.
If _lastFrameNumber_ is 0 or the option argument isn't specified means
all frames are taken.
__arguments__
`[CONFIG_FILE]` path to config file
Building
=========
Dependencies
------------
* OpenCV & OpenCV highgui >= 2.0
* CMake >= 2.6
Compiling
---------
Use CMake to build the project. You can use "cmake-gui", if you need a graphical user interface.
* CMake
* Specify the source path (root path of the dictionary) and the binary path (where to build the program, out
of source build recommended)
* Configure
* Select compiler
* Define the install path and other options
* Generate
* Windows: go to the binary directory and build the solutions you want (You have to compile in RELEASE mode):
* tld: build the project
* INSTALL: install the project
* Linux: go with the terminal to the build directory
* make: build the project
* Mac
* brew install python
* brew install gfortran
* easy_install numpy
* brew install cmake
* brew install opencv
* mkdir build
* cd build
* cmake ..
* cd ..
* make
* ./tld
近期下载者：
相关文件：
收藏者：