Skip to content

Range of Motion motion capture and data acquisition

Notifications You must be signed in to change notification settings

JonoSax/KneeTAPE

Repository files navigation

Purpose

To observe a user performing knee flexion exercises and track their motion and calculate their range of motion across the entirety of the video

Getting Started

  1. Install requirements in virtual environment
python -m venv venvSBP
. venvSBP/bin/activate
pip install -r requirements.txt
  1. Download desired tfjs models for bodypix.
# For example, download a ResNet50-based model to ./bodypix_resnet50_float_model-stride16
# bodypix/mobilenet/float/050/model-stride8.json
$ ./get-model.sh bodypix/resnet50/float/model-stride16
  1. Set path to models and image for inference in .py files
videoPath = './awesome_vid.mov'
modelPath = './bodypix_resnet50_float_model-stride16/'
  1. Run the script
python evalbody_singleposemodelVIDEO.py

Acknowledgement

  1. https://github.com/ajaichemmanam/simple_bodypix_python for model loading function
  2. https://github.com/patlevin for support functions
  3. https://github.com/likeablob for download script

About

Range of Motion motion capture and data acquisition

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published