SmartTennisTV: Automatic indexing of tennis videos

TL;DR

This paper presents an automated system for indexing tennis videos by recognizing scores and rally segments, enabling efficient navigation and retrieval of match highlights from broadcast footage.

Contribution

It introduces a novel score-based indexing method that segments rallies, recognizes scores, and tags key events, improving video searchability in tennis broadcasts.

Findings

Effective rally segmentation and score recognition demonstrated on real broadcast videos.

Automatic tagging of key tennis events like faults and deuce.

System enables quick retrieval of relevant match segments.

Abstract

In this paper, we demonstrate a score based indexing approach for tennis videos. Given a broadcast tennis video (BTV), we index all the video segments with their scores to create a navigable and searchable match. Our approach temporally segments the rallies in the video and then recognizes the scores from each of the segments, before refining the scores using the knowledge of the tennis scoring system. We finally build an interface to effortlessly retrieve and view the relevant video segments by also automatically tagging the segmented rallies with human accessible tags such as 'fault' and 'deuce'. The efficiency of our approach is demonstrated on BTV's from two major tennis tournaments.