Accurate and efficient 3D hand pose regression for robot hand teleoperation using a monocular RGB camera

作者：

Highlights：

• A large-scale multi-view dataset that provides accurate annotations for hand poses.

• A pipeline that improves the state-of-the-art results for 3D hand pose estimation.

• We successfully applied our approach to robot hand teleoperation.

摘要

•A large-scale multi-view dataset that provides accurate annotations for hand poses.•A pipeline that improves the state-of-the-art results for 3D hand pose estimation.•We successfully applied our approach to robot hand teleoperation.

论文关键词：Hand pose estimation,Deep learning,Robot teleoperation,Monocular

论文评审过程：Received 12 November 2018, Revised 25 April 2019, Accepted 24 June 2019, Available online 25 June 2019, Version of Record 29 June 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.06.055