The most significant risks right now is if the facial detection algorithm is too laggy. It’s mentioned more in Iris’s status report, but we were planning on taking advantage of pre trained models that boast high accuracy numbers, but we found out that its very computation heavy and makes the Jetson Nano run very slowly. We are pivoting towards a more Haar classifier approach, but we are getting pretty low accuracy numbers so we will need to work on that more.
No changes have been made to the existing design from last week. We have updated our Gantt chart according to our progress made so far, to better reflect our goals for the demo on 11/9. All the slack time we added was really helpful because we are still fairly on track with our final goals.
