Open Computer Vision Library
Congratulations to the very deserving Global Grand Prize Winners!
NeoCam: Real-time telemonitoring of preterm neonates
Democratizing A.I. using the OAK-D
Next-Generation Electric Wheelchair
Different parts of the world have different local problems that AI can help solve. Part of the OpenCV mission is to spread AI knowledge and usage globally. We have therefore identified 6 competition regions in the world and are thrilled to announce the regional prize and the popular vote winners.
Welcome to the OpenCV AI Competition 2021, sponsored by Microsoft Azure and Intel. This year’s competition will be focused on solutions solving real world problems using spatial AI. Teams will use the new OpenCV AI Kit D (OAK-D) to solve their challenge areas. The OAK-D is a smart camera with neural inference and depth processing capability on board.
Due to our sponsor’s generosity, we are giving away 1200 (WOW!) OAK-D devices to Phase 1 winners to help them build solutions during Phase 2.
Thank you so much for being part of our community and we look forward to seeing your submissions.
1200 OAK-D devices will be given to phase one winners to help them complete their phase two projects. The OAK-D is a variant of the OpenCV AI Kit (OAK) capable of Spatial AI.
What is Spatial AI? It’s the capability to for AI to be applied to the physical world – to tell you what an object is and where it is in 3D space – in real time.
It does this by running object detection off of its integrated 12MP RGB camera and combining hte results with its integrated stereo-depth engine. You can run a variety of deep learning models support by OpenVINO and OAK-D automatically augments them with spatial data from the integrated stereo depth engine.
It does this by running object detection off of its integrated 12MP RGB camera and combining the results with its integrated stereo-depth engine. You can run a variety of deep learning models support by OpenVINO and OAK-D automatically augments them with spatial data from the integrated stereo depth engine.
The competition will consist of two phases; selection and finals. Starting 12 Jan 2021, teams may apply for the competition with a project proposal in one of the above categories The selection period will last for 19 days, ending on 31 Jan 2021. Proposals must include the following important sections:
Team applications will be evaluated in one of two groups. 150 general teams (25 per region) + 60 University teams (10 per region) will be selected for the finals. The teams will receive:
The 210 teams selected for the finals have 3 months to complete their project. Finalist teams will be announced on 3 Mar 2021. Finalists will be awarded OAK-D devices to accomplish their projects, which will be mailed before the end of February. Finalists will have until 9 August 2021 to complete their projects. Regional and Grand Prize Winners will be announced 6 September 2021.
Regional PrizesWe will choose 3 winners from each region based on the quality of submitted projects. In addition, we will have a Popular Prize awarded to the most popular project based on a public vote. The winners will receive the following monetary prizes:
Global Grand PrizesIn addtion, we will have three Global Grand Prizes for best projects across all regions. The winners will receive the following prizes:
The organizers of the competition believe AI is like electricity with the potential to disrupt and transform many areas of our lives. It will have a positive impact on a wide variety of industries like autonomous driving, healthcare, agriculture, manufacturing, assistive technologies, entertainment, safety and security to name a few. We encourage submissions in all these areas. However, AI can also be used in ways that are unethical and/or discriminatory.
Participants should review the TensorFlow Responsible AI page as well as the Microsoft Responsible AI Resources page before submitting a proposal.
University teams are allowed up to 10 members. Standard teams are allowed 1-4 members.
Choose the region that most team members are located in, and that your solution focuses on. Use your best judgement.
Yes. See the documentation for examples showing how to run OpenVINO models.
Yes! Send an email to [email protected] with your submission formatted as a PDF.
OAK-D’s provided software is officially available for Python and C++, with a community-support Java version.
We prefer a PDF. You can see an example of what we will expect here: Download Sample Application PDF
Due to demand the deadline has been pushed back to 31 January 2021 at 11:59pm PST.
Yes! You can resubmit your project any time up to the deadline which is 31 January 2021 at 11:59pm PST.
Yes, teams can be just one person, but it’s much more fun to collaborate!
We will contact the winners via email, on or before 11 February 2021.
Yes! We love videos. Please send any video links inside your proposal.
Your project can use any license you choose. Closed-source projects will be required to provide extensive live demonstrations to judges.
Stay up to date on OpenCV and Computer Vision news