Grand Prize, Regional Prize & Popular Vote Winners Announced

OpenCV AI Competition 2021

An international AI competition celebrating OpenCV's 20th anniversary.

Sponsored by:
The Intel logo, and other Intel marks are trademarks of Intel Corporation or its subsidiaries.

Grand Prize Winners

Congratulations to the very deserving Global Grand Prize Winners! 

Play Video

#2 CALETA

NeoCam: Real-time telemonitoring of preterm neonates

Play Video

#1 CORTIC TIGERS

Democratizing A.I. using the OAK-D

Play Video

#3 CEREBROS

Next-Generation
Electric Wheelchair

Regional Prize and Popular Vote Winners

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.

North America

Play Video
1st

American Stereo Types

VR Laser Tag at Home

Play Video
2nd

Cortic Tigers

Democratizing A.I. using the OAK-D

Play Video
3rd

The Bench Botics

The BenchBot

SOUTH & CENTRAL AMERICA + CARIBBEANS

Play Video
1st

Quetzal C++

Warehouse Inspection with Autonomous Drones and Spatial IA

Play Video
2nd

SHL Robotics

SEDRAD – The Self-Driving Ads Robot Powered

Play Video
3rd

Smart Sierras Solution

Proboscis Project

EUROPE + RUSSIA + AUSTRALASIA

Play Video
1st

Caleta

NeoCam: Real-time telemonitoring of preterm neonates

Play Video
2nd

Eyecan Unicorns

Automated dataset annotation and detector training using OAK

Play Video
3rd

Aachen Armchair Engineers

Armchir Robot Arm for grasping / opening doors

Play Video
3rd

CVAR-U.P.Madrid

Vision based Search & Rescue Micro Aerial Vehicles (MAVs) for catastrophic situations

Middle East + Africa

Play Video
1st

CEREBROS TEAM

Next-Generation Electric Wheelchair

Play Video
2nd

PaLotus

Smart Assistant System for Visual Impairment

Play Video
3rd

Africa Business Integration

OpenGesture

Central Asia + Southern Asia

Play Video
1st

Topspin Trackers

Table Tennis Sport Analytics Using A System of OAK-Ds

Play Video
2nd

Calcutta Devs

Sofia - AI-powered personal yoga instructor

Play Video
3rd

Deepflow Tesseract

Agri Robot

Eastern Asia + South Eastern Asia

Play Video
1st

Rapyuta Robotics

Lifting Pallets using Edge AI

Play Video
2nd

NaRiPa VisionAIrs

6D-Pose Estimation for Precise Grasping in Retail Robotics

Play Video
3rd

Train & Track

Inspection of Current Collector Devices for Trains

Introduction

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.

The OAK-D Device

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.

Play Video

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.

The OAK-D Device

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 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.

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.

Prizes

$400,000 in prizes, sponsored by Microsoft Azure and Intel

Phase 1 Prizes will be given to the top 210 teams.

Additional Prizes will be awarded to top completed projects.

Global Prizes will be awarded to the top projects across all regions:
Regional Prizes will be awarded to the top 3 teams within each geographical region. In addition, a popular vote will determine an additional prize for each region:

Categories

Our 2021 competition offers new opportunities and challenge categories in addition to long-standing challenge areas.

Phases

Phase 1 : Selection

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 Name : We encourage people to use creative team names that include their University, Company, or City name + some creative phrase. E.g. San Diego Dolphins, or the Cambridge Turings.
  • Problem Statement : A description of a real-world AI problem and proposed solution using OAK-D within 3 months of effort.
  • Category: One of the seven categories. Note that evaluation is not dependent on category, so submit whatever application best fits your team.
  • Region: Where the team is located.
  • Team Capability : The qualification of the team.
  • Team Type :
    • General Team : Up to 4 members. Only 1 final submission allowed per team.
    • University Team : We want to encourage AI labs from universities to participate. If selected the university lab will receive 10 OAK-Ds. Universities may submit up to 2 submissions.

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:

  •  A free OAK-D for every team member (i.e. 4 for general team and 10 for university team) This is important for collaboration during COVID times.
  • Access to 100 hours of free processing time on Azure.
  • Access to Intel’s Dev Cloud.
  • Support on our Slack channel for successful completion of the project.

Phase 2 : finals

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 Prizes
We 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:

  • First Prize : $5k
  • Second Prize : $3k
  • Third Prize : $2k
  • Popular Prize (by public vote) : $2k

Global Grand Prizes
In addtion, we will have three Global Grand Prizes for best projects across all regions. The winners will receive the following prizes:

  • First Prize : $20k
  • Second Prize : $10k
  • Third Prize : $5k

Finalists

  • Be Right There, Boston
  • University of Colorado Denver LynxVision
  • Okanagan Smart Composite Manufacturers
  • The BenchBotics.
  • University of Hawaii PL4STIC
  • Little Rock-ies
  • Flaming AI
  • Ragin’ Cajuns
  • Cornell Tech Abeona
  • Cheyney AREL
  • The Plant Doctors
  • USC SAILers
  • American STEREOtypes
  • Archangel
  • Calgary Storm
  • Crystal Ball Solutions
  • CVPA
  • Golden Pheonix
  • intARact
  • Maryland Monks
  • MotionSmart
  • Move Squad
  • Peoria Pangolins
  • Saran Bros
  • ShareStreets CartOAKgraphers
  • The Coding Cousins
  • The Oly Shuckers
  • Transient Vision Infinity
  • Washington Monuments
  • Waterloo Autono-Goose
  • White Peacocks
  • Auttowa Crusaders
  • Falling Edge
  • LightBuzz
  • Social Distancers
  • SP4RX
  • DCToddlerBot
  • Submatter
  • The PingPongInators
  • Lumber Labor Union
  • Team GrandPlay
  • The Meadows Architects
  • Active Play Revolution
  • The Tenacious Tennis Tater Tots (TTTTT)
  • Inspiration-M
  • Cortic Tigers
  • See Clearly
  • I, For One, Welcome Our New Dolphin Overlords
  • Invasive Python Eradication & Survey Team (iPest)
  • Kids Guardian Angel
  • Orlando Frankensteins
  • NORDIC AI
  • Grand Tetonics
  • Rise Line Engineering
  • Bee Nusantara
  • Dong Lao Rangers
  • Honor of Kings is not fun
  • National Cheng Kung University’s Parkinson’s Disease Quantifiers
  • Train & Track
  • UTAR4Vision
  • UTokyo Farmers
  • Budacare 471
  • Cheongju Eagles
  • Taiwan Tech Tiger Team
  • Active Zone SG
  • Baywatch
  • Bit Bangkok
  • Changchun DXG-s
  • Chaseroos
  • chengdu panda
  • Computational ​​Koi Nerds
  • Fearless Sunny Islanders
  • Foresight for better ocean
  • Inferq Beeblebrox
  • MachineLearningTokyo – FishEye
  • Mileshift Pokayoke
  • NaRiPa VisionAIrs
  • Rapyuta Robotics
  • Sheares ChouChou
  • Singapore Smart Farmers
  • Team Oldie Goldies
  • falcons
  • Sing Sling
  • Takao-GFalls
  • Thanks for all the fish
  • Tinkerers
  • WBA-FL
  • BIT Catching Fish
  • Herb Hunter
  • Mamaking
  • Notty Boys (University of Nottingham Malaysia)
  • Team WAKUWAKU
  • Shanghai Frog
  • Snow Riders
  • Team SOAR (Smart Operations And Rescue)
  • Re-Drawing Campinas
  • UCB-Beavers
  • UFAM Alligators
  • VisiAr Austral (from Universidad Austral, Argentina)
  • U-LAkesCV
  • BogotaChildren-Signs&Expressions
  • Copacabana Deep Farm
  • UCB Squirrels
  • Clara
  • Eyes of Cassava
  • Los guerreros Jaguar
  • Multivac-GT
  • QuetzalC++
  • ROCFORT
  • SHL Robotics
  • Smart Sierras Solutions
  • Temuco’s Volcanoes
  • Vigilare
  • Chelkatun Nauka
  • Guará Wolves FTW (For the Win)
  • Hats’i
  • Ice Vulpix
  • Mendoza Cracken13
  • Quickium
  • RoadEngin
  • Robótica de la Mixteca
  • Team WindNet
  • Vecno Team Argentina
  • Andean Horizon
  • Green Dream at Ecatepunk
  • MindLab – NutrAI
  • VP ClimbingTeam
  • Paisa-tech
  • HITEC Mirchi
  • Vishnu Wizards
  • Swarm Prodigies
  • Romi Deltas
  • Phoenix
  • The NUST Griffin Case
  • Alphabot
  • Vishnu Techies
  • Kool Kids from Kathmandu
  • Kurukshetra Warlords
  • BITS Goa Grounders
  • Bombay Vadapav
  • Coimbatore Chanakyas
  • Forus – Disha
  • Kolkata Geek
  • Team ZFighters
  • Bangalore Vision
  • clOAKs_n_Daggers
  • EthicalSign
  • India Visioners
  • Tarsyer Watchers
  • Tink Dynamics
  • Adlytic: Lahore Retail AI
  • Applied Vision Navigators
  • Astana Steppewolves
  • CODE Auth
  • Deep Visionary
  • Deepflow tesseract
  • Future of Design
  • Nep-Vision Rhinos
  • NUST-Alpha
  • Topspin Trackers
  • Y Not We?
  • Belligerent Bangaloreans
  • Calcutta Devs
  • Chennai_pipers
  • FireAndIce
  • Four Kaareegar
  • Mumbai Coder
  • Pandoras Box
  • Pune AI Couple
  • Chennai Pullingos
  • PEC Parindas
  • Tata Titans
  • Vascu du Bengaluru
  • Vision Bots Analytics, Islamabad, Pakistan.
  • PaLotus
  • CEREBROS TEAM
  • PalPose
  • AU Perceptrons United
  • Africa Business Integration (Pty) Ltd.
  • AIC Hawks
  • Cameroon School of AI
  • DEV-X PATRIOT’S
  • Egypt Iris
  • FADE Israel
  • Green Pi-Kahi
  • MyCrops
  • RAISE – Robotics and Artificial Intelligence Solution Enterprise
  • SenseExpanse: Real Time, More See!
  • Team Copula AI
  • TexkLab Network
  • The African Eagles
  • The Gait Musketeers
  • Unilever AI Enthusiasts
  • VIDGE
  • WeedFighters
  • Zreeba Dynamics
  • Brighter Eyes Lynxes
  • Brussels Engineers Enhancing Respiratory Sensing (BEERS)
  • Cranfield Bristol Investigation Express
  • CVAR-U.P.Madrid
  • Cyber Monks of TU Munich
  • Sk_[PLACEHOLDER]
  • Turku Walruses
  • Sant’Anna’s TUTTOMONDO
  • Aachen Armchair Engineers
  • Caleta
  • HiPeRT Lab
  • TUM Yellow Bots
  • QUT Space White Belly Sea Eagles
  • BioSense BInToF
  • Ulyanovsk Pioneers
  • Active Wheats
  • Adorable Penguins
  • BikeWorkz
  • Cyber-Physical Cyclists (CHILL)
  • Czech Curious Fishermen (CCF)
  • DotConnect
  • Essort
  • Exobotic Technologies
  • eyecan unicorns
  • Fast Sense
  • Getafe Musarañas
  • Grumpy Norwegians
  • LCT ROBOCARE
  • Orion Robotics
  • Snowball Dynamics
  • Subsea Binoculars
  • TangibleLight
  • Zurich Treemers
  • AIHunters
  • AIoli Brunswick
  • Cocreated
  • Halfspace.AI
  • Kauda
  • LET’S MAKE OAK-D SMARTER
  • Madrid Arbutus Bears
  • Panopty the Robot
  • Synapse
  • The Guard​AI​ans
  • CNR AI-sphalters
  • Depth Burners
  • Flying Swans
  • HackDance
  • IDLE (Image Deep Learning Enthusiasts)
  • Moscow Drone Shuffle
  • OrchardEyes
  • ProRail Railway Level Crossing Monitor
  • Tahiti ARtists
  • The German Mite Busters
  • Visio-cyclist
  • Delft Ultra
  • [email protected]
  • British AI Bicycle Boys
  • Duck Vision
  • DutchDike
  • Insightful yogi
  • Team Sentinels
  • Spectacular AI
  • Mircotopia

Submission Guidelines : Do's and Don’t

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.

Frequently Asked Questions

Check this section often- we will be adding new FAQs over the next several days.

  • Integrated 4K 12 MP Color Camera
  • JPEG, H.264 & H.265/HEVC Encoding
  • Integrated 1 MP Global Shutter Synchronized Stereo Pair
  • USB 3.0 Type-C Interface
  • Use with any host OS that OpenVINO supports
  • Disparity-Depth Min Distance: 69cm
  • Stereo AI (Stereo Inference Min Distance): 19.6cm
  • Stereo Camera Hyperfocal Distance: 19.6cm
  • Stereo Camera Baseline: 7.5cm
  • Stereo Horizontal Field of View (HFOV): 71 degrees
  • Stereo Camera Resolution: 1280×800
  • RGB Camera resolution: 4056×3040
  • RGB (AutoFocus) Min Distance: 8cm

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.

Technical Specification

OpenCV AI Kit – Lite: Now on Kickstarter

Join the waitlist to receive a 10% discount

Courses are (a little) oversubscribed and we apologize for your enrollment delay. As an apology, you will receive a 10% discount on all waitlist course purchases. Current wait time will be sent to you in the confirmation email. Thank you!