OrsNet: A hybrid neural network for official sports referee signal recognition

Tse Yu Pan, Chen Yuan Chang, Wan Lun Tsai, Min Chun Hu

研究成果: Conference contribution

5 引文 斯高帕斯(Scopus)

摘要

In this work, we propose a novel sports referee training system based on wearable sensors and a real-time Official Referee Signal (ORS) segmentation/recognition method which can recognize 65 kinds basketball ORSs with the accuracy of 95.3%. A hybrid neural network named ORSNet is designed for recognizing gestures based on IMU signals. The proposed ORSNet involves convolution layers and recurrent layers to learn more representative features and correlations in temporal domain, respectively. A novel loss function and a weight sharing strategy are proposed to learn a more robust ORS recognition model. Moreover, we investigate the influence of applying a semi-supervised network in the proposed ORSNet.

原文English
主出版物標題MMSports 2018 - Proceedings of the 1st International Workshop on Multimedia Content Analysis in Sports, Co-located with MM 2018
發行者Association for Computing Machinery, Inc
頁面51-58
頁數8
ISBN(電子)9781450359818
DOIs
出版狀態Published - 2018 十月 19
事件1st ACM International Workshop on Multimedia Content Analysis in Sports, ACM 2018, co-located with ACM Multimedia 2018 - Seoul, Korea, Republic of
持續時間: 2018 十月 26 → …

出版系列

名字MMSports 2018 - Proceedings of the 1st International Workshop on Multimedia Content Analysis in Sports, Co-located with MM 2018

Conference

Conference1st ACM International Workshop on Multimedia Content Analysis in Sports, ACM 2018, co-located with ACM Multimedia 2018
國家/地區Korea, Republic of
城市Seoul
期間18-10-26 → …

All Science Journal Classification (ASJC) codes

  • 媒體技術
  • 電腦繪圖與電腦輔助設計
  • 電腦視覺和模式識別
  • 軟體

指紋

深入研究「OrsNet: A hybrid neural network for official sports referee signal recognition」主題。共同形成了獨特的指紋。

引用此