Articulated Non-Rigid Point Set Registration for Human Pose Estimation from 3D Sensors
Open Access
- 29 June 2015
- Vol. 15 (7) , 15218-15245
Abstract
We propose a generative framework for 3D human pose estimation that is able to operate on both individual point sets and sequential depth data. We formulate human pose estimation as a point set registration problem, where we propose three new approaches to address several major technical challenges in this research. First, we integrate two registration techniques that have a complementary nature to cope with non-rigid and articulated deformations of the human body under a variety of poses. This unique combination allows us to handle point sets of complex body motion and large pose variation without any initial conditions, as required by most existing approaches. Second, we introduce an efficient pose tracking strategy to deal with sequential depth data, where the major challenge is the incomplete data due to self-occlusions and view changes. We introduce a visible point extraction method to initialize a new template for the current frame from the previous frame, which effectively reduces the ambiguity and uncertainty during registration. Third, to support robust and stable pose tracking, we develop a segment volume validation technique to detect tracking failures and to re-initialize pose registration if needed. The experimental results on both benchmark 3D laser scan and depth datasets demonstrate the effectiveness of the proposed framework when compared with state-of-the-art algorithms.Keywords
Funding Information
- US National Science Foundation (NRI-1427345)
- Oklahoma Center for the Advancement of Science and Technology (HR12-30)
This publication has 45 references indexed in Scilit:
- Model-Based Reinforcement of Kinect Depth Data for Human Motion Capture ApplicationsSensors, 2013
- Fast oriented bounding box optimization on the rotation group SO (3,ℝ)ACM Transactions on Graphics, 2011
- A robust hybrid method for nonrigid image registrationPattern Recognition, 2011
- A Bayesian Framework for Human Body Pose Tracking from Depth Image SequencesSensors, 2010
- Direct visibility of point setsACM Transactions on Graphics, 2007
- A survey of advances in vision-based human motion capture and analysisComputer Vision and Image Understanding, 2006
- SCAPEACM Transactions on Graphics, 2005
- A new point matching algorithm for non-rigid registrationComputer Vision and Image Understanding, 2003
- Nonlinear Dimensionality Reduction by Locally Linear EmbeddingScience, 2000
- A method for registration of 3-D shapesIEEE Transactions on Pattern Analysis and Machine Intelligence, 1992