Cargando…

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

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 extra...

Descripción completa

Detalles Bibliográficos
Autores principales: Sen, Anik, Deb, Kaushik, Dhar, Pranab Kumar, Koshiba, Takeshi
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8072636/
https://www.ncbi.nlm.nih.gov/pubmed/33919484
http://dx.doi.org/10.3390/s21082846
_version_ 1783683952635019264
author Sen, Anik
Deb, Kaushik
Dhar, Pranab Kumar
Koshiba, Takeshi
author_facet Sen, Anik
Deb, Kaushik
Dhar, Pranab Kumar
Koshiba, Takeshi
author_sort Sen, Anik
collection PubMed
description 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.
format Online
Article
Text
id pubmed-8072636
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-80726362021-04-27 CricShotClassify: An Approach to Classifying Batting Shots from Cricket Videos Using a Convolutional Neural Network and Gated Recurrent Unit Sen, Anik Deb, Kaushik Dhar, Pranab Kumar Koshiba, Takeshi Sensors (Basel) Article 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. MDPI 2021-04-18 /pmc/articles/PMC8072636/ /pubmed/33919484 http://dx.doi.org/10.3390/s21082846 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Sen, Anik
Deb, Kaushik
Dhar, Pranab Kumar
Koshiba, Takeshi
CricShotClassify: An Approach to Classifying Batting Shots from Cricket Videos Using a Convolutional Neural Network and Gated Recurrent Unit
title CricShotClassify: An Approach to Classifying Batting Shots from Cricket Videos Using a Convolutional Neural Network and Gated Recurrent Unit
title_full CricShotClassify: An Approach to Classifying Batting Shots from Cricket Videos Using a Convolutional Neural Network and Gated Recurrent Unit
title_fullStr CricShotClassify: An Approach to Classifying Batting Shots from Cricket Videos Using a Convolutional Neural Network and Gated Recurrent Unit
title_full_unstemmed CricShotClassify: An Approach to Classifying Batting Shots from Cricket Videos Using a Convolutional Neural Network and Gated Recurrent Unit
title_short CricShotClassify: An Approach to Classifying Batting Shots from Cricket Videos Using a Convolutional Neural Network and Gated Recurrent Unit
title_sort cricshotclassify: an approach to classifying batting shots from cricket videos using a convolutional neural network and gated recurrent unit
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8072636/
https://www.ncbi.nlm.nih.gov/pubmed/33919484
http://dx.doi.org/10.3390/s21082846
work_keys_str_mv AT senanik cricshotclassifyanapproachtoclassifyingbattingshotsfromcricketvideosusingaconvolutionalneuralnetworkandgatedrecurrentunit
AT debkaushik cricshotclassifyanapproachtoclassifyingbattingshotsfromcricketvideosusingaconvolutionalneuralnetworkandgatedrecurrentunit
AT dharpranabkumar cricshotclassifyanapproachtoclassifyingbattingshotsfromcricketvideosusingaconvolutionalneuralnetworkandgatedrecurrentunit
AT koshibatakeshi cricshotclassifyanapproachtoclassifyingbattingshotsfromcricketvideosusingaconvolutionalneuralnetworkandgatedrecurrentunit