|OpenCV Spatial AI Contest Winners Announced|
|Written by Kay Ewbank|
|Friday, 17 June 2022|
The OpenCV Spatial AI contest has ended with the announcement of the winners of the popular vote. OpenCV partnered with Intel and Microsoft Azure to bring an AI, computer vision, and manufacturing competition to life.
This contest set team the challenge of creating a replica of a real-world manufacturing solution using Lego blocks and OpenCV AI Kit, a tiny yet powerful edge AI camera engineered by Luxonis and capable of neural network processing. 50 teams were provided with the resources to help bring their ideas to life over the 3-month build phase, and the Phase 1 winners were announced in December.
The winners of the Popular Vote and $1,000 cash prize have now been announced. The winners are Team B-Arol-o with Project ARNEIS. ARNEIS is short for Automated Recognizer, Network-Enabled, Item Sorter, and is a scale reproduction of a packaging machine.
The OAK-D-Lite captures photos of bottles flowing past on a conveyor and runs a neural network trained on a custom dataset to be able to classify and recognize the type (Part Number) of the bottle. This information is fed in real-time to the Raspberry Pi which - based on the job order - decides whether to eject the bottle to the final packaging unit, or to put it back to the parts warehouse.
Earlier in the competition, the top three prizes were awarded by the judges. The first prizewinner was EyeCan Reborn, a scanning station to “teleport” a real object to the metaverse by framing it with the OAKDLite from different view angles and using neural rendering technologies.
Second place went to UCA Robotics for their vision-based human robot interaction, and third place was awarded to the Potato Lovers Colorado Beetle Buster.
or email your comment to: firstname.lastname@example.org