Video labeling tool based on OpenCV. Easily customizable.
The idea behind the project is to create a labeling to for videos, which is fully based on Python + OpenCV and thus very easy to customize. The whole labelling pipeline can easily be changed or parts can be replaced or added.
With VirtualEnv:
virtualenv --python=/usr/bin/python3.6 venv
source venv/bin/activate
pip install -r requirements.txt
Run with video and config as mandatory input:
python main.py data/example_video.avi data/example_config.json
Optional add output path with -o/--output:
python main.py data/example_video.avi data/example_config.json -o results/output.json
If classifier is added (in label_tool/classifier.py), activate "pre-classification" with -c/--classify:
python main.py data/example_video.avi data/example_config.json --classify
- 1.0.0
- First public version.
- Fork it (https://github.com/yourname/yourproject/fork)
- Create your feature branch (
git checkout -b feature/fooBar
) - Commit your changes (
git commit -am 'Add some fooBar'
) - Push to the branch (
git push origin feature/fooBar
) - Create a new Pull Request
- fix tracker bug
- add example classifier
- different colors for different types of rois
Distributed under the MIT license. See LICENSE
for more information.