Hyderabad: Professor Vineet Gandhi from the Centre for Visual Information Technology (CVIT) at IIIT-Hyderabad has won patent for split screens research.
In collaboration with the French Institute for Research in Computer Science and Automation (INRIA) and University of Wisconsin-Madison and along with his student Moneish Kumar, he has been able to simulate a professional cameraman’s behaviour through mathematical models.
Spilt screens research automatically creates a split screen video from non-static recordings that can display both the context of the scene as well as close-up details of the performers. This approach is especially attractive for digital heritage projects of the performing arts and social and sports events. Context is provided by a wide-angle shot in the top part of the screen.
Mr Gandhi has worked on this research like producing theatre or dance performances for the small screen which not only a huge physical effort but also an expensive proposition. Such productions, can’t focus on the actors’ or dancers’ faces in close up because of their movement on stage. The wide angle shots of the stage further make it difficult to understand the emotions and facial expressions.
Mr Gandhi presented his groundbreaking research at the prestigious Euro-graphics at Lyon, France. He was awarded a patent in the United States for his research “System and Method for Automatically Generating Split Screen for a Video of a Dynamic Scene”.
The 31-year-old Gandhi from IIIT-H said, “From one fixed camera, using AI techniques we automatically generate multiple cameras doing the work of multiple cameramen. It should look like there are cameramen behind the cameras following the movements of each performer.
“Algorithms in computer vision take care of issues typically faced by professional cameramen while recording dynamic scenes by mathematically ensuring smooth camera movement, as well as preserving order in which the group of characters are split up and their consequent interactions,” he said.
