We developed a system for the tracking of players and ball in a soccer video. Work done at the Advanced Digital Sciences Center under Stefan Winkler. Details can be found in the attached report.
What we used to develop the system
- OpenCV 3.3
- Microsoft Visual Studio Community 2015
- Windows 10
├── Soccer Tracker : Directory containing the source and header files of the project
├── dataset : Directory containing the dataset and the results folder
├── others : Directory containing images for instructions
├── Soccer Tracker.sln : MSVC Project Solution
|── Report.pdf : Report
-
Install OpenCV
-
Download the dataset at http://www.issia.cnr.it/wp/dataset-cnr-fig/ and place them in the dataset directory
-
Launch
Soccer Tracker.sln
. -
Set solution configuration and platform to
Release
andx64
.
- Set project properties (see images below) if using a different version of OpenCV.
- Enable OpenMP support
- Build the solution
- Ensure that the files
opencv_ffmpeg330_64.dll
andopencv_world330.dll
are in the release directory (created only after building the solution). Both files can be found at<your_opencv_folder>\build\bin
.
- Run the program via the
Start Without Debugging
option (Ctrl + F5) - The video will be saved in
dataset/results