Spatial AI Competition A Winner
Written by Sue Gee   
Friday, 20 November 2020

When OpenCV launched a Computer Vision contest earlier this year, it expected to award three prizes, totalling $6,000. The competition was so popular that it has now announced six winners who share $12,000. It also plans further contests with "10X times rewards".

OpenCV celebrated in 20th Anniversary in July and ran a highly successful kickstarter campaign for its OpenCV AI Kit, OAK for short, described as a tiny, powerful, open source Spatial AI system. 

OAK

When OpenCV embarked its Spatial AI Competition contest the idea was to select the 15 best submissions from among the participants and give them a prototype OAK-D (the OAK-1 augmented by a pair of  stereo cameras for depth perception) to realize their proposals. However, instead of receiving around 50 entries, there were 235 of them and 32 of them were chosen to receive not only the OAK-2 smart camera but also a GoPro-compatible mount, expanding the potential for positioning, wearing, or affixing the OAK-D module.

The list of 32 Phase 1 winners, and a further 22 strong entries, was posted by OpenCV in July and now the prize winners have been revealed, with OpenCV commenting:

We believe the people who won the competition are not just some talented Al engineers but also trailblazers who are leading the way in making the world a better place. Congrats to all of them!

opencvcomp

There were two winners at each of the Gold, Silver and Bronze levels: 

1st Prize - $3,000:
Vision System For Visually Impaired

  • Jagadish Mahendran
  • A project to build a reliable smart perception system to assist blind and visually impaired people to safely ambulate in a variety of indoor and outdoor environments.

Universal Hand Control

  • Pierre Mangeot
  • Use a hand to control connected devices (includes smart speaker, smart plugs, TV, … ) or to interact with applications running on computers without touching a keyboard or a mouse.

2nd Prize - $2,000:
Parcel Classification & Dimensioning 

  • Abhijeet Bhatikar, Daphne Tsatsoulis, Nils Heyman-Dewitte, Hasan Syed 
  • Addresses the problem faced by the global cargo industry,  due to the inability to determine the shape of packages and measure their dimensions accurately.

Real Time Perception for Autonomous Forklifts

Kunal Tyagi, Kota Mogami, Abhishek Sharma, Bhuvanchandra DV

  • Enhance the functionality of advanced sensors, as well as vision and geo guidance technology.

3rd Prize - $1,000:

At Home Workout Assistant

  • Daniel Rodriguez Perazzo, Gustavo Camargo Rocha Lima, Natalia Souza Soares, Victory Gouveia De Menezes Lyra
  • This project aims to help folks working out at home with posture and pose correction technology.

Automatic Lawn Mower Navigation

  • Jan Lukas Augustin and Silas Raschka
  • An RGB-D law mowing bot utilizes the object detection, positional tracking, and semantic segmentation features of OAK-D

On the OpenCV site, you can see videos of each of the winning projects and read more about what they set out to achieve and how they implemented their solutions. Comparing the winning entries with their original outline proposals indicates that hands-on experience with the OAK-D enabled teams to be more ambitious. OpenCV has announced that it will be offering Black Friday discounts on purchasing the OpenCV Kit which has been used by participants on the submitted projects. It has also announced more upcoming contests, the next being in January 2021, with 10X times rewards. 

 

More Information

OpenCV Spatial AI Kit Competition Winners Announced

Related Articles

OpenCV AI Kit On Kickstarter

Kickstarter Campaign For AI Computer Vision Courses 

OpenCV Hackathon 

OpenCV 4.0 Says Goodbye To C  

OpenCV 3.0 Released - Computer Vision For The Rest Of Us 

To be informed about new articles on I Programmer, sign up for our weekly newsletter, subscribe to the RSS feed and follow us on Twitter, Facebook or Linkedin.

 

Banner


The Dynamic DevOps Roadmap
05/02/2025

Αre you taking your first steps in the Devops world? Have you gone beyond the basics and trying to find your bearings figuring out what to focus on next? No worries, the Dynamic DevOps Road [ ... ]



Google Explains Add Me
31/01/2025

Add Me is an AI-based feature for Google's Pixel 9 phones that lets you add missing individuals into group photos. Google has now explained how this "magic" feature was developed.


More News

espbook

 

Comments




or email your comment to: comments@i-programmer.info

 

Last Updated ( Friday, 20 November 2020 )