Crowd-sourced Annotation of Human Motion.
0

Configure Feed

Select the types of activity you want to include in your feed.

5 1 0

Clone this repository

https://tangled.org/matthiasplappert.tngl.sh/motion-annotation-tool https://tangled.org/did:plc:tfusos7fl3vuk3zevc7flkno
git@tangled.org:matthiasplappert.tngl.sh/motion-annotation-tool git@tangled.org:did:plc:tfusos7fl3vuk3zevc7flkno

For self-hosted knots, clone URLs may differ based on your setup.



README.md

Motion Annotation Tool#

Installation#

Start by installing all Python dependencies:

pip install -r requirements.txt

Next, install SRILM. You'll have to adapt the path to SRILM in src/proj/settings.py. You might also have to adapt other parts of the configuration depending on your needs. You should also make sure that your configuration is secure. Please consult the Django documentation for this!

Finally, you can set up the database:

cd src/
python manage.py migrate
python manage.py createsuperuser

At this point everything is ready. However, you'll probably need some motion data:

python manage.py importmotions

This step requires a free account for the KIT Whole-Body Human Motion Database. You can select different filters. At this point, only a single subject can be visualized so you should at least set the maximum number of subjects to 1. This step is going to take a while. After all motions have been imported, you might have to collect the static files and switch them to visible:

python manage.py collectstatic
python manage.py dbshell
UPDATE dataset_motionfile SET is_hidden=0;

Lastly, you can try if everything works by running a local server:

python manage.py runserver

Just visit http://localhost:8000. If everything worked, you should be able to log in using your previously created account.