In this post we’ll share how we used TensorFlow’s object detection API to build a custom image annotation service for eyeson. Below you can seen an example where Philipp is making the “thinking” 🤔 pose during a meeting which automatically triggers a GIF reaction. Background and Overview The idea for this project came up in one of our stand-up meetings. After we introduced GIF reactions to eyeson we thought about marrying that feature with some machine learning.
This tutorial provides a practical example of how to setup a video platform using the eyeson API service. The application uses the eyeson ruby gem, the web application framework Sinatra and hosting platform Heroku. By following the steps in the how-to you will have a website up and running, providing an entry point for a shared video meeting room. The participants can join the meeting without any registration or sign up, and will return to the application website after exiting the meeting.
In this post I’ll try to explain how you can build a screen sharing extension. I’ll cover the architecture of the extension and the way the individual parts communicate with each other. Our goal is to capture the entire desktop or an application window via Chrome and display it in an HTML video element. Below is a preview of the finished extension. In order to accomplish that, we need to invoke navigator.