AI on Raspberry Pi with the Intel Neural Compute Stick

I’ve always been fascinated by AI and machine learning. Google TensorFlow offers tutorials and has been on my ‘to-learn’ list since it was first released, although I always seem to neglect it in favor of the shiniest new embedded platform.

Last July, I took note when Intel released the Neural Compute Stick. It looked like an oversized USB stick, and acted as an accelerator for local AI applications, especially machine vision. I thought it was a pretty neat idea: it allowed me to test out AI applications on embedded systems at a power cost of about 1W. It requires pre-trained models, but there are enough of them available now to do some interesting things.

You can add a few of them in a hub for parallel tasks. Image credit Intel Corporation.

I wasn’t convinced I would get great performance out of it, and forgot about it until last November when they released an improved version. Unambiguously named the ‘Neural Compute Stick 2’ (NCS2), it was reasonably priced and promised a 6-8x performance increase over the last model, so I decided to give it a try to see how well it worked.


I took a few days off work around Christmas to set up Intel’s OpenVino Toolkit on my laptop. The installation script provided by Intel wasn’t particularly user-friendly, but it worked well enough and included several example applications I could use to test performance. I found that face detection was possible with my webcam in near real-time (something like 19 FPS), and pose detection at about 3 FPS. So in accordance with the holiday spirit, it knows when I am sleeping, and knows when I’m awake.

That was promising, but the NCS2 was marketed as allowing AI processing on edge computing devices. I set about installing it on the Raspberry Pi 3 Model B+ and compiling the application samples to see if it worked better than previous methods. This turned out to be more difficult than I expected, and the main goal of this article is to share the process I followed and save some of you a little frustration.

Continue reading “AI on Raspberry Pi with the Intel Neural Compute Stick”

Robot Can’t Take Its Eyes Off The Bottle

Robots, as we currently understand them, tend to run on electricity. Only in the fantastical world of Futurama do robots seek out alcohol as both a source of fuel and recreation. That is, until [Les Wright] and his beer seeking robot came along. (YouTube, video after the break.)

A Raspberry Pi 3 provides the brains, with an Intel Neural Compute stick plugged in as an accelerator for neural network tasks. This hardware, combined with the OpenCV image detection software, enable the tracked robot to identify objects and track their position accordingly.

That a beer bottle was chosen is merely an amusing aside – the software can readily identify many different object categories. [Les] has also implemented a search feature, in which the robot will scan the room until a target bottle is identified. The required software and scripts are available on GitHub for your perusal.

Over the past few years, we’ve seen an explosion in accelerator hardware for deep learning and neural network computation. This is, of course, particularly useful for robotics applications where a link to cloud services isn’t practical. We look forward to seeing further development in this field – particularly once the robots are able to open the fridge, identify the beer, and deliver it to the couch in one fell swoop. The future will be glorious!


Continue reading “Robot Can’t Take Its Eyes Off The Bottle”