Skip to content

Latest commit

 

History

History
54 lines (36 loc) · 2.52 KB

File metadata and controls

54 lines (36 loc) · 2.52 KB

SlouchyJS

What do using computer and body building have in common ? Your posture matters

How to use

  • You will need Docker to run SlouchyJS

  • Build the docker image

$ docker build -t local/slouchyjs .
  • And run it !
$ docker run -p 1410:1410 -e PORT=1410 -td --name slouchy local/slouchyjs
  • SlouchyJS should be running at http://localhost:1410 ( You will have to configure a https server to fully use SlouchyJS )

Background

Like many of us, I have spent more and more time in front of a computer in the last decade.
I’ve always tried to be healthy and listen to my body, therefore I’ve been quite surprised when my trapezius muscles started feeling tight and sometimes even painful.

At first, I thought that maybe I didn’t stretch enough after exercising myself. But the discomfort occurred even when I didn’t do sport for several days. After mentioning it to a doctor, he immediately ask me if I often worked on a computer.
It was right on the mark !

Poor posture when sitting in front of a computer lead sooner or later to muscular tension if not pain.
This is how I realised that the importance of a good sitting posture is rarely mentioned in our digital world.

Idea

So when I stumbled upon a GitHub project that aims at notifying slouchy people, it immediately kept my attention. Unfortunately, the source code (in Python) wasn’t up to date and I didn’t manage to run it on my MacBook.

10 python versions and libraries installed later, I said to myself :

Why not doing it using the brand new TensorFlow JS so that anybody could use this app without having to struggle installing dependencies.

Project

As you’ve (hopefully) understood SlouchyJS promises to notify the user when he is slouching using only his webcam and a convolutional neural network (or other image recognition techniques).

The clear benefit of using front end Javascript to process images lays in keeping webcam pictures on the user’s computer.

How to contribute