I have been hard at work getting the face tracking system ported over to the Raspberry Pi 2 in an organized fashion, and I am definitely just about there.
Here is a teaser video showing off the simplest working version.
I even put forth the initial efforts towards a full fledged C++ API! I now have PWM and Servo control very well supported for the PiSoC so that it can be very easily embedded into your C++ programs.
Anyway, the tracking system shown in the video is pretty good, but I’m still working on it. I am getting about 10fps capturing at 960×720 in full color for face detection. But you might notice I am only getting about 25% usage out of the cpu! That’s where the four cores of the new Raspberry Pi2 come in- I am only pushing one core to its limits, I need more!
So with a little extra work this morning dedicated to multithreading the detection and capture processes, I have already nearly doubled the performance.
Stay tuned!
Brian
Brian Newman
May 11, 2015 at 7:23 pm
Hi guys!
Very pleased to hear that you are on the brink of another Kickstarter.
After a few months with no blog posting I was starting to wonder if you had ‘pulled the plug’ on the PiSoc. So much so, that in desperation I just ordered and recently received a couple of the Cypress development kits. I looked briefly at a prototyping board I received as part of the order and was totally intimidated by the amount and depth of the C++ programming required to do anything really meaningful.
So I have just taken another look at your Python API library. It looks SOOO much tamer and more approachable. Can’t wait to get my hands on a PiSoc!!!
All the best with your upcoming KickStarter!!!
admin
May 11, 2015 at 7:56 pm
Thanks!
You’ll probably be pleased to find out I also got the face tracker working through Python! (kind of… ) I will have more details on that soon.
And thanks for the support!
Brian
Greg S
July 9, 2015 at 8:01 pm
Would love to hear how you got python face tracker to work
Can you give any steps or suggestions ?
Thank yoU!
Greg.
Robert Barron
June 22, 2016 at 8:24 pm
We put up a tutorial and a link to the github code on our learning page: https://www.embeditelectronics.com/blog/project/face-tracker/
We also have a python version of the Face Tracker as well now. While it is much slower, it is usable on the Pi 3 and can be easily integrated into more involved PiSoC projects.