CricShotClassify: An Approach to Classifying Batting Shots from Cricket Videos Using a Convolutional Neural Network and Gated Recurrent Unit

Abstract

Recognizing the sport of cricket on the basis of different batting shots can be a significant part of context-based advertisement to users watching cricket, generating sensor-based commentary systems and coaching assistants. Due to the similarity between different batting shots, manual feature extraction from video frames is tedious. This paper proposes a hybrid deep-neural-network architecture for classifying 10 different cricket batting shots from offline videos. We composed a novel dataset, CricShot10, comprising uneven lengths of batting shots and unpredictable illumination conditions. Impelled by the enormous success of deep-learning models, we utilized a convolutional neural network (CNN) for automatic feature extraction, and a gated recurrent unit (GRU) to deal with long temporal dependency. Initially, conventional CNN and dilated CNN-based architectures were developed. Following that, different transfer-learning models were investigated—namely, VGG16, InceptionV3, Xception, and DenseNet169—which freeze all the layers. Experiment results demonstrated that the VGG16–GRU model outperformed the other models by attaining 86% accuracy. We further explored VGG16 and two models were developed, one by freezing all but the final 4 VGG16 layers, and another by freezing all but the final 8 VGG16 layers. On our CricShot10 dataset, these two models were 93% accurate. These results verify the effectiveness of our proposed architecture compared with other methods in terms of accuracy.

Deep Transfer Learning‐Based Foot No‐Ball Detection in Live Cricket Match

“…The proposed model can recognize a shot with 0.90 accuracy. Sen et al [ 16 ] initiated a hybrid deep neural network architecture for the classification of 10 distinct cricket batting strokes from offline footage with 0.93 height accuracy. Tong et al [ 17 ] demonstrated the framework (unified) for the types of field sports played with ball for the purpose of shot of semantic in category, which leads to separation of video frames based on three main important factors such as diameter of camera snap, technology used for video creation, and main topic in a scene.…”

Innovating a Centuries-Old Sport: How Emerging Data Analytics Tools Are Redefining Cricket

“…Some early approaches used motion estimation or wearable technology for different shots (Khan et al, 2017). Like bowling, however, these approaches have mostly been made obsolete with CNNs, particularly in broadcasted cricket matches (Foysal et al, 2019;Harun-ur-Rashid et al, 2018;Khan et al, 2018;Semwal et al, 2018;Sen et al, 2021). The most recent work at the time of publication, CricShotClassify, attains a 93% out-of-sample classification accuracy of batter outcomes.…”

Information communication and technology in sports: a meticulous review

“…The accuracy of the predicted model is found to be good as compared to other algorithms. To categorize batting shots of 10 types from offline footage the research by Anik Sen et al ( 27 ) 2021 suggests a mixed deep-neural network design. Various transfer-learning models that freeze all the layers—namely, VGG16, InceptionV3, Xception, and DenseNet169—were examined.…”