Automatic annotation of events and highlights generation of cricket match videos

Abstract

In this paper, we propose a novel method for automatic annotation of events and highlights generation for cricket match videos. The videos are divided into time intervals representing one ball clip using a Convolutional Neural Network (CNN) and Optical Character Recognition (OCR). CNN detects the start frame of a ball. OCR is used to detect the end of the ball and to annotate it by recognizing the change in runs/wickets. The proposed framework is able to annotate events and generate sufficiently good highlights for four full length cricket matches.