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...
Autores principales: | , , , |
---|---|
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 |