move fall detection library out of ambianic-edge into independent pypi package

[ivelin]

Pull fall detection code out of ambianic-edge into this standalone repo as an independent python library.
The goal is to allow data scientists to use, collaborate and improve people the fall detection ML model independently of ambianic deployments.

[ivelin]

The repo should follow best practices for standalone ML repos and include:

• Python source code and wheel package published on PyPi
• Jupyter notebook for live demo and interaction with the model.
• Usage documentation for data scientists and app developers
• CI & test suite
• Training and testing data sets
• Third party ML models used as building blocks

Several references for ML github repos:

• https://github.com/tensorflow/tfjs-models/tree/master/posenet
• https://github.com/xingyizhou/CenterNet

A best practice blog post:

• How to Create a Professional Github Data Science Repository

Related work - fall detection using pose estimates:

• https://github.com/cwlroda/falldetection_openpifpaf
• https://towardsdatascience.com/fall-detection-using-pose-estimation-a8f7fd77081d

[bhavikapanara]

Yes...sure @ivelin, will do this.