Product Labs of International Institute of Information Technology, Hyderabad (IIIT-H), has successfully tested a viable market prototype of badminton analytics developed at its Centre for Visual Information Technology (CVIT).
A pilot study conducted in collaboration with Star Sports saw the data going live during the telecast of the Premier Badminton League (PBL) in January. The productisation of badminton analytics was based on a research paper authored by Anurag Ghosh and Suriya Singh, the students of CVIT, under the guidance of professor C.V. Jawahar.
Titled ‘Towards Structured Analysis of Broadcast Badminton Videos’, the paper proposed a method to analyse a large corpus of badminton broadcast videos by segmenting the points played, tracking and recognising the players in each point and annotating their respective badminton strokes.
Algorithms can identify when a rally starts, or ends, and who wins the rally (player identification). It provides segmentation of the shots played – backhand, forehand, smash – thereby revealing the style of the player. By generating heat maps based on how fast the players move on court, one can also deduce the dominant player, said Prakash Yella, head of Product Labs, in a press release.
In the lab context, students’ algorithms churned out data on canned video footage, which was available for scrutiny an hour or two later. However, this was not practical in real-time high-quality streaming videos. “Other challenge is that the broadcaster wanted rally-wise analytics. A rally typically lasts for 3-4 seconds and our technology was running sequentially for an hour. So we had to bring an hour-long runtime down to 3-4 seconds,” he said.
The team showcased successful display on screens the distance travelled by the players on court during the telecast of the semi-final match of PBL. “It absolves the need for complicated multi-camera set-ups and relies on a single camera feed. The system should enable automatic low-cost analysis of players,” explained Mr. Ghosh.
Star Sports is now said to be keen on exploring the possibilities of expanding the pilot study to a larger scenario and also look beyond badminton to other sports.
“We zeroed in on badminton because a fairly deep amount of work was done and there is an excellent badminton eco-system here,” added Mr. Prakash.