I have continued working on the head pose algorithm. I was able to get 4 directions to be identified, left, right, forward and down. As our professor suggested the hardest part was differentiating between forward and down. I did several iterations for the ratio calculated for the SVM classifier. The method that finally worked was to add another triangle to the equation. For the interim demo I had two triangles, one for each side of the face over the cheek area and I would subtract the area of each and divide by 2. This gave a good distinction for forward and right poses. Then when I added left this method still seemed to work. But to include the down direction, I added a third triangle that looked at the area between the nose, left jaw and right jaw. This new method takes the left cheek area subtracts the right cheek and divides by 2 just like before but then also subtracts the new triangle area. This ratio gives an even better distinction between the poses than before. I first got this version working on my laptop and then tested on the jetson and experienced similar results. I tested this on myself and a friend.
My progress is still on schedule, although now we are towards the end and have to pick up the pace. I will be pushing to get more data for the head pose to be as robust as possible for the final demo.
This next week, I will be collecting more head pose data to add to our pretrained model. Will also be working with the rest of my groupmates to collect our metrics for the presentation coming up.
