Human Motion Tracking by Registering an Articulated Surface to 3-D Points and Normals

TL;DR

This paper presents a novel method for human motion tracking by registering a surface to 3-D points and normals, using an iterative approach that estimates kinematic parameters and data assignment probabilities, suitable for visual-shape observations.

Contribution

It introduces a new metric for surface-to-data registration and an iterative algorithm that jointly estimates motion parameters and data associations, handling outliers effectively.

Findings

Successfully tracks human motion from sparse 3-D shape data.

Handles outliers and imperfect silhouettes effectively.

Demonstrates applicability to visual-hull and visual-shape observations.

Abstract

We address the problem of human motion tracking by registering a surface to 3-D data. We propose a method that iteratively computes two things: Maximum likelihood estimates for both the kinematic and free-motion parameters of a kinematic human-body representation, as well as probabilities that the data are assigned either to a body part, or to an outlier cluster. We introduce a new metric between observed points and normals on one side, and a parameterized surface on the other side, the latter being defined as a blending over a set of ellipsoids. We claim that this metric is well suited when one deals with either visual-hull or visual-shape observations. We illustrate the method by tracking human motions using sparse visual-shape data (3-D surface points and normals) gathered from imperfect silhouettes.