File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Artificial Intelligence for Sport Actions and Performance Analysis using Recurrent Neural Network (RNN) with Long Short-Term Memory (LSTM)

TitleArtificial Intelligence for Sport Actions and Performance Analysis using Recurrent Neural Network (RNN) with Long Short-Term Memory (LSTM)
Authors
Fok, WWTChan, LCWChen, C
KeywordsArtificial Intelligence
Deep Learning
Human Activity Recognition
LSTM
RNN
Sport Performance Analysis
Issue Date2018
PublisherAssociation for Computing Machinery.
Citation
Proceedings of 2018 4th International Conference on Robotics and Artificial Intelligence (ICRAI 2018), Guangzhou, China, 17-19 November 2018, p. 40-44 How to Cite?
DOI: http://dx.doi.org/10.1145/3297097.3297115
AbstractThe development of Human Action Recognition (HAR) system is getting popular. This project developed a HAR system for the application in the surveillance system to minimize the man-power for providing security to the citizens such as public safety and crime prevention. In this research, deep learning network using Recurrent Neural Network (RNN) with Long Short-Term Memory (LSTM) are used to analyze dynamic video motion of sport actions and classify different types of actions and their performance. It could classify different types of human motion with a small number of video frame for efficiency and memory saving. The current accuracy achieved is up to 92.9% but with high potential of further improvement.
Persistent Identifierhttp://hdl.handle.net/10722/278339
ISBN
978-1-4503-6584-0
ISI Accession Number ID
WOS:000470228200008

 

DC FieldValueLanguage
dc.contributor.authorFok, WWT-
dc.contributor.authorChan, LCW-
dc.contributor.authorChen, C-
dc.date.accessioned2019-10-04T08:12:05Z-
dc.date.available2019-10-04T08:12:05Z-
dc.date.issued2018-
dc.identifier.citationProceedings of 2018 4th International Conference on Robotics and Artificial Intelligence (ICRAI 2018), Guangzhou, China, 17-19 November 2018, p. 40-44-
dc.identifier.isbn978-1-4503-6584-0-
dc.identifier.urihttp://hdl.handle.net/10722/278339-
dc.description.abstractThe development of Human Action Recognition (HAR) system is getting popular. This project developed a HAR system for the application in the surveillance system to minimize the man-power for providing security to the citizens such as public safety and crime prevention. In this research, deep learning network using Recurrent Neural Network (RNN) with Long Short-Term Memory (LSTM) are used to analyze dynamic video motion of sport actions and classify different types of actions and their performance. It could classify different types of human motion with a small number of video frame for efficiency and memory saving. The current accuracy achieved is up to 92.9% but with high potential of further improvement.-
dc.languageeng-
dc.publisherAssociation for Computing Machinery.-
dc.relation.ispartof4th International Conference on Robotics and Artificial Intelligence (ICRAI 2018)-
dc.rights4th International Conference on Robotics and Artificial Intelligence (ICRAI 2018). Copyright © Association for Computing Machinery.-
dc.subjectArtificial Intelligence-
dc.subjectDeep Learning-
dc.subjectHuman Activity Recognition-
dc.subjectLSTM-
dc.subjectRNN-
dc.subjectSport Performance Analysis-
dc.titleArtificial Intelligence for Sport Actions and Performance Analysis using Recurrent Neural Network (RNN) with Long Short-Term Memory (LSTM)-
dc.typeConference_Paper-
dc.identifier.emailFok, WWT: wilton@hkucc.hku.hk-
dc.identifier.authorityFok, WWT=rp00116-
dc.identifier.doi10.1145/3297097.3297115-
dc.identifier.scopuseid_2-s2.0-85061528559-
dc.identifier.hkuros306898-
dc.identifier.spage40-
dc.identifier.epage44-
dc.identifier.isiWOS:000470228200008-
dc.publisher.placeNew York, NY-

Export via OAI-PMH Interface in XML Formats

OR

Export to Other Non-XML Formats