AI technology is a new frontier, with limitless potential for the improvement of human lives. The OpenCV Artificial Intelligence Kit (OAK) project began life as part of CommuteGuardian, a technological solution to the causes of many bicycle – automobile accidents, by alerting distracted drivers and warning cyclists just in time.
Cycling is an enduring human pastime beyond its simple utility, but it is not without risk: In 2018, 857 people in America alone were killed after being struck by automobiles.
Even when these “minor” (to the car) accidents don’t result in death, they often do result in broken bones, lifetime disability, and protracted legal battles designed to wear out the victim. The OAK team formed around the idea of using spatial AI and computer vision to augment human perception, stopping these horrible collisions before they occur.
Building A Platform For Safety
Working with the Movidius Myriad X chip on a prototype, the team learned that it had several important hardware capabilities that were simply not unlocked in the software made available to developers. We knew these capabilities would unlock hundreds, even thousands of new use cases and could help us user in a new era of further democratized computer vision and spatial AI.
So, we decided to build it. Without further ado, we proudly present… The Open CV AI Kit(s):
The OpenCV AI Kit(s)
In broad strokes, The OpenCV AI Kit is made up of several parts:
- A single-camera 4k @ 60fps hardware module which includes a Myriad X and is a tiny 45 mm x 30 mm.
- A module with a 4k @ 60fps camera and stereo depth cameras which provide spatial 3D tracking capability. It is about the size of a Raspberry Pi.
- A new software library coming to OpenCV for advanced on-device real-time neural network processing for the OAK boards.
- Both boards can run Deep Learning models for image classification, object detection, segmentation, human pose estimation, and many more in real time even on low-power hosts like the Raspberry Pi.
These modules aren’t available to buy just yet- but we can’t wait to see what the global OpenCV community does with these new capabilities. Let’s solve some problems together.
You will be seeing and hearing much more about these modules and the OAK in the coming weeks. Sign up for the mailing list and be among the first to know when we release more information.