Motion segment decomposition of RGB-D sequences for human behavior understanding

作者：

Highlights：

• We propose to decompose a human behavior sequence into relevant motion segments.

• Each motion segment is described by both human motion and depth appearance around hands.

• We model the sequence dynamics using a Dynamic Naive Bayesian classifier.

• We evaluate the method for various types of behavior: gesture, action and activity.

• The challenge of online detection of successive behaviors is also investigated.

摘要

Highlights•We propose to decompose a human behavior sequence into relevant motion segments.•Each motion segment is described by both human motion and depth appearance around hands.•We model the sequence dynamics using a Dynamic Naive Bayesian classifier.•We evaluate the method for various types of behavior: gesture, action and activity.•The challenge of online detection of successive behaviors is also investigated.

论文关键词：3D human behavior understanding,Temporal modeling,Shape space analysis,Online activity detection

论文评审过程：Received 12 February 2016, Revised 23 June 2016, Accepted 27 July 2016, Available online 28 July 2016, Version of Record 10 August 2016.

论文官网地址：https://doi.org/10.1016/j.patcog.2016.07.041