Ghassan AlRegib and his research team in the Multimedia and Sensors Laboratory have been chosen to host and run the 2017 IEEE Video and Image Processing (VIP) Cup.
A professor in the Georgia Tech School of Electrical and Computer Engineering (ECE), AlRegib is joined in this effort by ECE postdoctoral fellow Dogancan Temel and ECE Ph.D. students Tariq Alshawi, and Min-Hung (Steve) Chen.
The VIP Cup theme is traffic sign detection under challenging conditions, and the event is open to teams of three to 10 undergraduate students, with one graduate student acting as a tutor/mentor and one faculty member serving as the team supervisor. At the intersection of autonomous vehicles and machine learning, this topic is attractive not only to students, but also to the industry and research communities.
One of the side products developed by AlRegib and his team is an open source dataset that will also give ECE and Georgia Tech visibility in the autonomous vehicles and machine learning arenas. They are also creating a dataset that has labeled ground truth data to test the vision algorithms under practical and real weather conditions, which have been missing in the publicly existing algorithms built for autonomous vehicles.
Any eligible team can participate in the competition. The detailed guidelines and dataset are planned for release on March 15, and participating teams should complete their submission by July 1, 2017. The three best teams will be selected and announced by August 1, 2017, and the three finalist teams will be judged at the IEEE International Conference on Image Processing (ICIP), which will be held September 17-20, 2017 in Beijing, China.
The top three performing teams will receive travel grants to attend and present at ICIP. The total cash prize for the three winning teams is $9,000. For more information about this event and to register, please visit the VIP Cup Competition overview and the full description of the competition.