Classification Of Batting Shots In Cricket Video : A Review

Abstract

Cricket is one of the most watching and loved sports in current world. With the increasing craze for cricket, different countries are participating at various tournaments, leagues conducting all over the world. Since each player has a responsibility to perform at the best, it is important to understand the game very well. Recognizing and classifying different batting shots played in cricket are remarkable part in generation of context based advertisement. It has application in automatic textual commentary generation. Detecting cricket shots based on its characteristics will help sport analysts and coaches to understand the game very well . This review paper analyzed various technique that can be used for shot classification such as motion vectors and neural networks. Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) together can extract the spatial and temporal features of the videos. Examined the performance of various methodologies with transfer learning technique.

Keywords: Batting Shots, Motion Vector, Support Vector Machine (SVM), Neural Networks, CNN, RNN, Transfer Learning