A hybrid framework for automatic joint detection of human poses in depth frames

作者：

Highlights：

• A hybrid framework to detect joints from depth videos of human body.

• Geometric features based on the geodesic distance are used to construct a skeleton with joints and extreme points.

• A data-driven method is developed to identify joint candidates with weak constraints.

• Improved performance in terms of accuracy in comparison with the state of the art methods.

摘要

•A hybrid framework to detect joints from depth videos of human body.•Geometric features based on the geodesic distance are used to construct a skeleton with joints and extreme points.•A data-driven method is developed to identify joint candidates with weak constraints.•Improved performance in terms of accuracy in comparison with the state of the art methods.

论文关键词：Human pose detection,Joint detection,Human body model,Geodesic features

论文评审过程：Received 16 December 2016, Revised 13 December 2017, Accepted 30 December 2017, Available online 3 January 2018, Version of Record 8 January 2018.

论文官网地址：https://doi.org/10.1016/j.patcog.2017.12.020