Non-parametric hand pose estimation with object context

作者：

Highlights：

• We developed a system that estimates in real-time the articulated pose of the hand.

• Our approach is discriminative, with low computational load and fast error recovery.

• Our system is robust to occlusions, implicitly extracting information from them.

• The system is thoroughly evaluated with quantitative and qualitative experiments.

摘要

•We developed a system that estimates in real-time the articulated pose of the hand.•Our approach is discriminative, with low computational load and fast error recovery.•Our system is robust to occlusions, implicitly extracting information from them.•The system is thoroughly evaluated with quantitative and qualitative experiments.

论文关键词：Articulated hand pose,Approximate nearest neighbor,Context

论文评审过程：Received 5 January 2012, Revised 26 January 2013, Accepted 11 April 2013, Available online 30 April 2013.

论文官网地址：https://doi.org/10.1016/j.imavis.2013.04.002