Our first step is to make a proof of concept by using a Desktop PC, webcam, & pre-trained neural network to show tracking of hand signals and/or gestures as a way of controlling a device such as a TV.
After proving that the concept is possible and that we can do it with pre-trained networks we will focus on training our own network with our own input. This will allow us to refine the network and keep its functions to only those which we need as compared to a pre-trained network which is not custom-fit to our needs.