A survey on 3D hand pose estimation: Cameras, methods, and datasets

作者：

Highlights：

• A markerless approach is proposed to evaluate the tracking accuracy of a depth camera with a numerical control linear motion guide.

• State-of-the-art hand pose estimation methods are intuitively summarized with tables, and their research lines are detailly analyzed.

• Public datasets and evaluation criteria are identified to provide further insight into the field of hand pose estimation.

• Realistic challenges, recent trends, dataset creation and annotation, and open problems for future research directions are outlined.

摘要

•A markerless approach is proposed to evaluate the tracking accuracy of a depth camera with a numerical control linear motion guide.•State-of-the-art hand pose estimation methods are intuitively summarized with tables, and their research lines are detailly analyzed.•Public datasets and evaluation criteria are identified to provide further insight into the field of hand pose estimation.•Realistic challenges, recent trends, dataset creation and annotation, and open problems for future research directions are outlined.

论文关键词：Hand pose estimation,Hand tracking,Depth camera,Human-computer interaction

论文评审过程：Received 16 May 2018, Revised 23 March 2019, Accepted 24 April 2019, Available online 25 April 2019, Version of Record 2 May 2019.

论文官网地址：https://doi.org/10.1016/j.patcog.2019.04.026