This is an Android application that uses TensorFlow MoveNet to perform real-time pose estimation on a live camera feed or on a video file. The app displays the video feed and overlays the detected poses on top of it. The app analyzes the gymnastic exercises Squat and L-Sit and provides feedback to the user. The app can run on any device with a camera and Android 6.0 (API level 23) or higher.
-
If you don't have it already, install Android Studio Iguana, following the instructions on the website.
-
Android device and Android development environment with minimum API 23.
-
Open Android Studio, and from the
Welcome
screen, selectOpen an existing Android Studio project
. -
From the
Open File or Project
window that appears, navigate to and select theandroid
directory from wherever you cloned theStudienarbeit
GitHub repo. ClickOK
. -
If it asks you to do a
Gradle Sync
, clickOK
. -
You may also need to install various platforms and tools, if you get errors like
Failed to find target with hash string 'android-21'
and similar. Click theRun
button (the green arrow) or selectRun
>Run 'android'
from the top menu. You may need to rebuild the project usingBuild
>Rebuild Project
. -
If it asks you to use
Instant Run
, clickProceed Without Instant Run
. -
If there are build errors in the
OpenCV
module, you may reinstall the OpenCV SDK by following the instructions ininstall_openCV.md
. -
If you want to run the app on a smartphone, you need to have an Android device plugged in with developer options enabled at this point. See here for more details on setting up developer devices.
Please do not delete the assets folder content. If you explicitly deleted the
files, then please choose Build
> Rebuild
from menu to re-download the
deleted model files into assets folder.