Monthly Archives: November 2017

Build your own AI-powered camera for $45 (!) from Google

Days of miracles & wonder, part 6,392

Today, we’re excited to announce our latest AIY Project, the Vision Kit. It’s our first project that features on-device neural network acceleration, providing powerful computer vision without a cloud connection. […]

The provided software includes three TensorFlow-based neural network models for different vision applications. One based on MobileNets can recognize a thousand common objects, a second can recognize faces and their expressions and the third is a person, cat and dog detector. We’ve also included a tool to compile models for Vision Kit, so you can train and retrain models with TensorFlow on your workstation or any cloud service.

You can pre-order it here


Explore Maya culture through Google & the British Museum

I’m eager to show the Micronaxx, who are studying Native American cultures in school:

Dr Jago Cooper, Curator, Head of the Americas at the British Museum, introduces Google Arts & Culture’s new collection on the preservation of the Maya Heritage.

The video showcases pioneering and cutting edge technologies that enable to preserve some unique traces of this Guatemalan civilization, inherited by British explorer Alfred Maudslay.



A cool demo of Google’s pose estimation tech

“Teaching Google Photoshop” has been my working mantra here—i.e. getting computers to see like artists & wield their tools. A lot of that hinges upon understanding the shape & movements of the human body. Along those lines, my Google Research teammates Tyler Zhu, George Papandreou, and co. are doing cool work to estimate human poses in video. Check out the demo below, and see their poster and paper for more details.



Photography: A ridiculously cool “layer lapse” of NYC

Julian Tryba scripts After Effects to produce carefully segmented, meticulously choreographed “layer lapses” that produce a “visual time dilation” that juxtaposes the same scene shot at different times of day. Here, just check it out:

You can read more about the project on PetaPixel:

Tryba visited NYC 22 times, drove 9988 miles, spent 352 hours shooting 232,000 photos with 6 cameras (5 Canon DSLRs and a Sony a7R II) and 11 different lenses, and paid $1,430 in parking fees.