Title :
Markerless Motion Capture of Human Body Using PSO with Single Depth Camera
Author :
Xing, Tianwei ; Yu, Yao ; Zhou, Yu ; Du, Sidan
Author_Institution :
Sch. of Electron. Sci. & Eng., Nanjing Univ., Nanjing, China
Abstract :
This paper presents a novel approach to model human body, recover and track its 3D position, orientation and articulated-skeleton pose parameters from a single depth camera video sequence observed by Kinect sensor. In our work, human body is modeled as assembled 3D geometric primitives whose dimensions are estimated automatically. Motion parameters are recovered by projecting hypothesized body model pose to camera imaging space and seeking for optimal solution that best matches camera observation as well as physical constraints. An objective function is designed to quantify the discrepancy between the predicted and the actual, observed features and penalize implausible or unnatural pose. We exploit body skeleton´s tree structure and propose a self-adaptive version of Particle Swarm Optimization (PSO) to solve the optimization problem. In order to avoid swarm collapse and accelerate convergence, motion temporal continuity over frame sequence is exploited as initial pose using from-coarse-to-fine strategy. The overall system does not require any markers, special capture environment or complex image acquisition setup, and is ready-to-use for users.
Keywords :
cameras; convergence; feature extraction; image matching; image sequences; image thinning; motion estimation; object tracking; particle swarm optimisation; pose estimation; solid modelling; video signal processing; 3D geometric primitives; 3D position recovery; 3D position tracking; Kinect sensor; PSO; articulated-skeleton pose parameter; body model pose; body skeleton tree structure; camera imaging space; camera observation matching; convergence acceleration; dimension estimation; frame sequence; from-coarse-to-fine strategy; human body markerless motion capture; human body modeling; implausible pose; motion temporal continuity; objective function; observed features; optimal solution seeking; optimization problem; orientation tracking; physical constraint; self-adaptive particle swarm optimization; single depth camera video sequence; swarm collapse; unnatural pose; Biological system modeling; Cameras; Humans; Joints; Optimization; Solid modeling; human body motion capture; marker-less; self-adaptive PSO; single Kinect;
Conference_Titel :
3D Imaging, Modeling, Processing, Visualization and Transmission (3DIMPVT), 2012 Second International Conference on
Conference_Location :
Zurich
Print_ISBN :
978-1-4673-4470-8
DOI :
10.1109/3DIMPVT.2012.21