Strokes Classification in Cricket Batting Videos

In this paper, we present a novel approach to classify strokes in cricket batting. To classify front foot and back foot strokes, we created a feature space consisting of spatiotemporal time series obtained from generated stick Figure video overlays. Classification was performed using Long Short Term memory (LSTM) and Bidirectional LSTM networks. Both LSTM models accurately classified (100%) of all the videos from the testing split for a dataset created using publicly available videos (63 strokes). The presented approach has the potential to contribute to sport analytics and advance augment coaching systems and cricket viewing experience (including automated body segments annotations). Future work will include application in other sport disciplines and advancing prototype implementations on various platforms.