Physiotherapy Aid

Inspiration

During Covid or in general working class specially IT professionals cant get time for exercise, sitting for long hours therefore they might get issues in body. So if we get them a virtual physiotherapist, so that sitting at home they can work out with proper guidance and do exercises will be beneficial.

What it does

Our application uses a tensorflow.js (browser-based) model to make predictions on the state of the current user's pose. It has been trained on a dataset of images created by us (~300 images per pose) to predict whether the position is correct, or incorrect - and what makes it so. I have used GCP Machine Learning Studio, a GCP Machine Learning tool, to train our models in the various physiotherapy poses. GCP Services Speech-to-Text API was also used to enable the application to be accessible by the visually impaired. The user can start their exercises via speech in various languages using GCPTranslator Speech API remotely and this is more convenient and easier to use for our target audience. The application utilizes GCP Services for text-to-speech. This is useful for the visually impaired as they can hear if they are in the right position as the application will tell them to adjust their posture if incorrect. We also use the webcam to track the user's movement which is fed as input to the posenet machine learning model and outputs posture image on the user's body.