Here’s an interesting Pi + PIC project by MrValkeerie that is using a Raspberry Pi to run face detection analysis via an inexpensive webcam and then in turn trigger position adjustments for a series of hobby servos hooked up to his PIC breakout board. His intended application? A costume where many eyes track the human faces that it detects! From the video description:
This is a stock Model B Rev 1.0 256Mbyte, 700Hz Raspberry Pi running Raspbian. It is interfaced to a PIC 16F690 through a homebrew 3.3V-5.2V level convertor based on a couple of 2N7000 Mosfets (circuits online). The protocol is I2C, with the Pi acting as master and the PIC as slave.
The Pi uses I2C to update 8 registers in the PIC holding angles in the range 0-255, which in turn converts the angles into pulses of 1-2 milliseconds every 20 milliseconds (this is normal for servos). The servos are low-cost generics ordered off Ebay direct from China.
The Webcam came from a thrift store and is reported as “Pixart Imaging Inc”. The face detection uses the Python bindings to OpenCV and is based on Haar Cascades. The eyes were found in a graveyard.
The face detection is slow … but I only integrated everything this morning, and I am sure I can speed it up a little.
Have an amazing project to share? Join the SHOW-AND-TELL every Wednesday night at 7:30pm ET on Google+ Hangouts.
Join us every Wednesday night at 8pm ET for Ask an Engineer!
Learn resistor values with Mho’s Resistance or get the best electronics calculator for engineers “Circuit Playground” – Adafruit’s Apps!
No comments yet.
Sorry, the comment form is closed at this time.