You are here

Mechanical Engineering Team Selected as Finalist in Phase I OpenCV AI Competition

Top Stories

Mechanical Engineering Department to help manufacturers be more productive

The University of Louisiana at Lafayette is partnering with Louisiana Tech University and Grambling State University

Read More ➝

The UL Lafayette College of Engineering is proud to congratulate a team of four Mechanical Engineering students selected as finalists in Phase 1 of the OpenCV AI Competition. The team named Ragin’ Cajuns, directed by Dr. Joshua Vaughan, consists of leader Brennan Moeller along with Nathan Madsen, Joseph Stevens, and Benjamin Willis. The team also received special help from Mechanical Engineering instructor, Yasmeen Qudsi.

The OpenCV AI competition is the world’s largest Artificial, AI, Intelligence competition. As finalists, the Ragin’ Cajuns Team is now working on Phase 2 of the competition where $20,000 will be awarded to the national winners and $5,000 to the regional winners.

The Ragin’ Cajuns’ proposal was based on previous autonomous maritime systems work on the UL Lafayette 2016 Maritime RobotX, pictured below. They will leverage Oak-D devices to enhance object detection and identification, using it for obstacle avoidance, path planning, and mission awareness.

Photo Credit: Dr. Joshua Vaughan, lead research facilitator in the C.R.A.W.LAB (Controls, Robotics, and Automation, With respect for human interaction)

As North America – University Team Phase 1 finalists, they were awarded 10 Oak-D devices for team members to use for remote collaboration during COVID-19 social distancing. The competition’s website explains the importance of these special cameras:

“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.” -Image and text taken from the OpenCV AI Competition Website

As listed on the OpenCV AI Competition Website, Phase 2 is the final round where the students have 3 months, until July 11, 2021, to complete their projects that meet the goal of the competition, to solve real world problems.