PointCNN-Hand: 3D hand joints estimate by PointCNN from hand point cloud

Jia Hong Chen, Chen Chien Hsu*

*此作品的通信作者

研究成果: 書貢獻/報告類型會議論文篇章

摘要

This paper provides a novel method called "PointCNN-Hand"for 3D hand joints estimation based on PointCNN. To use the depth image effectively, we transfer the hand depth image into the 3D hand cloud point and implement end-to-end training by PointCNN-Hand for hand joint estimation. We then perform error analysis on MSRA, NYU, and ICVL datasets to compare with the state-of-the-art methods. The experiments show that the proposed method has desired results, and the model parameters are relatively smaller than those of other methods. To be specific, the parameters of the proposed PointCNN-Hand network are reduced to only 3 Mega Byte (MB) with Floating Point Operations (FLOPs) less than 232.05M.

原文英語
主出版物標題Proceedings of 2021 International Conference on System Science and Engineering, ICSSE 2021
發行者Institute of Electrical and Electronics Engineers Inc.
頁面458-463
頁數6
ISBN(電子)9781665448482
DOIs
出版狀態已發佈 - 2021 8月 26
事件2021 International Conference on System Science and Engineering, ICSSE 2021 - Virtual, Ho Chi Minh City, 越南
持續時間: 2021 8月 262021 8月 28

出版系列

名字Proceedings of 2021 International Conference on System Science and Engineering, ICSSE 2021

會議

會議2021 International Conference on System Science and Engineering, ICSSE 2021
國家/地區越南
城市Virtual, Ho Chi Minh City
期間2021/08/262021/08/28

ASJC Scopus subject areas

  • 人工智慧
  • 電腦視覺和模式識別
  • 訊號處理
  • 能源工程與電力技術
  • 控制與系統工程
  • 電氣與電子工程
  • 控制和優化

指紋

深入研究「PointCNN-Hand: 3D hand joints estimate by PointCNN from hand point cloud」主題。共同形成了獨特的指紋。

引用此