OpenTLD
所属分类：图形图像处理
开发工具：C++
文件大小：30940KB
下载次数：68
上传日期：2012-06-11 18:49:08
上 传 者：
luanlai
说明： OpenTLD,捕食者物体跟踪算法。使用C++实现，不需要Matlab。这个系统能够通过分析物体的运动来完善跟踪算法。你能在很短的时间里教会它跟踪你的手指、面孔或在高速公路上狂颠的轿车。
(OpenTLD predator object tracking algorithm. Use C++ to achieve, does not require of Matlab. This system is able to analyze the motion of the object to improve the tracking algorithm. In a very short time you can teach it to keep track of your fingers, face, or mad Britain' s car on the highway.)
文件列表:
datasets\01_david\david.mpg (962560, 2012-04-28)
datasets\01_david\gt.txt (21684, 2012-04-28)
datasets\01_david\init.txt (14, 2012-04-28)
datasets\01_david\pn_tracker.txt (18856, 2012-04-28)
datasets\02_jumping\gt.txt (8908, 2012-04-28)
datasets\02_jumping\init.txt (15, 2012-04-28)
datasets\02_jumping\jumping.mpg (704512, 2012-04-28)
datasets\02_jumping\pn_tracker.txt (7613, 2012-04-28)
datasets\03_pedestrian1\gt.txt (3979, 2012-04-28)
datasets\03_pedestrian1\init.txt (11, 2012-04-28)
datasets\03_pedestrian1\pedestrian1.mpg (313344, 2012-04-28)
datasets\03_pedestrian1\pn_tracker.txt (3130, 2012-04-28)
datasets\03_pedestrian1\TLD1.0.txt (3976, 2012-04-28)
datasets\04_pedestrian2\BeyondSemiBoost.txt (2329, 2012-04-28)
datasets\04_pedestrian2\coGD.original.txt (13942, 2012-04-28)
datasets\04_pedestrian2\coGD.txt (9580, 2012-04-28)
datasets\04_pedestrian2\CVPR.txt (8639, 2012-04-28)
datasets\04_pedestrian2\final_detector.txt (7397, 2012-04-28)
datasets\04_pedestrian2\gt.txt (8787, 2012-04-28)
datasets\04_pedestrian2\init.txt (15, 2012-04-28)
datasets\04_pedestrian2\initial_detector.txt (7257, 2012-04-28)
datasets\04_pedestrian2\MIL.original.txt (4942, 2012-04-28)
datasets\04_pedestrian2\MIL.txt (5616, 2012-04-28)
datasets\04_pedestrian2\OnlineBoost.txt (731, 2012-04-28)
datasets\04_pedestrian2\pedestrian2.mpg (452608, 2012-04-28)
datasets\04_pedestrian2\pn_tracker.txt (8253, 2012-04-28)
datasets\04_pedestrian2\SemiBoost.txt (5690, 2012-04-28)
datasets\04_pedestrian2\TLD1.0.txt (8845, 2012-04-28)
datasets\05_pedestrian3\BeyondSemiBoost.txt (2975, 2012-04-28)
datasets\05_pedestrian3\coGD.original.txt (7417, 2012-04-28)
datasets\05_pedestrian3\coGD.txt (5196, 2012-04-28)
datasets\05_pedestrian3\CVPR.txt (4803, 2012-04-28)
datasets\05_pedestrian3\final_detector.txt (4244, 2012-04-28)
datasets\05_pedestrian3\gt.txt (4931, 2012-04-28)
datasets\05_pedestrian3\init.txt (15, 2012-04-28)
datasets\05_pedestrian3\initial_detector.txt (4213, 2012-04-28)
datasets\05_pedestrian3\MIL.original.txt (2478, 2012-04-28)
datasets\05_pedestrian3\MIL.txt (2645, 2012-04-28)
datasets\05_pedestrian3\OnlineBoost.txt (819, 2012-04-28)
datasets\05_pedestrian3\pedestrian3.mpg (268288, 2012-04-28)
... ...
This will be a C++ implementations of the OpenTLD (aka Predator)
----------------------------------------------------------------------------
This is a work in progress, as of right now the code is functional but pretty slow.
----------------------------------------------------------------------------
Installation Notes
=====================================
git clone git@github.com:alantrrs/OpenTLD.git
cd OpenTLD
mkdir build
cd build
cmake ../src/
make
cd ../bin/
%To run from camera
./run_tld -p ../parameters.yml -tl
%To run from file
./run_tld -p ../parameters.yml -s ../datasets/06_car/car.mpg -tl
%To init bounding box from file
./run_tld -p ../parameters.yml -s ../datasets/06_car/car.mpg -b ../datasets/06_car/init.txt -tl
%To train only in the firs frame (no tracking, no learning)
./run_tld -p ../parameters.yml -s ../datasets/06_car/car.mpg -b ../datasets/06_car/init.txt
%To test the final detector (Repeat the video, first time learns, second time detects)
./run_tld -p ../parameters.yml -s ../datasets/06_car/car.mpg -b ../datasets/06_car/init.txt -tl -r
=====================================
Evaluation
=====================================
The output of the program is a file called bounding_boxes.txt which contains all the detections made through the video. This file should be compared with the ground truth file to evaluate the performance of the algorithm. This is done using a python script:
python ../datasets/evaluate_vis.py ../datasets/06_car/car.mpg bounding_boxes.txt ../datasets/06_car/gt.txt
====================================
Thanks
====================================
To Zdenek Kalal for realeasing his awesome algorithm
近期下载者：
相关文件：
收藏者：