Three-Dimensional Object Modelling Fitting & Tracking

摘要

Described herein is a method and system for marker-less three-dimensional modelling, fitting and tracking of a skeletal representation of an object in a three-dimensional point cloud. In particular, it concerns the tracking of a human user skeletal representation with respect to time. The method comprises inputting a three-dimensional point cloud derived from a depth map; predetermining a set of control points representing the skeleton of the user, determining a start-up skeleton pose, obtaining an orthographic representation of the user 3D point cloud projected onto a grid by sampling the 3D point cloud with a predetermined static size, determining a set of curvature centres points approximating central axes of main parts of the user, determining the torso plane, and refining and/or defining the principal direction of the body. The method comprises then the step of performing iterative local and global fittings of the set of control points onto the user 3D point cloud and the associated data such as the curvature centre points, using topological and geometric constraints so that to track skeleton posture along the time. Stabilising the skeleton pose; resolving ambiguities; and providing a suitable output are then the last steps of a preferred embodiment of the invention.

主权项

1. A method of fitting and tracking a skeletal representation of an object within a three-dimensional scene represented by a three-dimensional point cloud, the skeletal representation comprising an arrangement of a plurality of control points, the method comprising the steps of:
a) using the three-dimensional point cloud of the scene to determine input information relating to the object to be fitted and tracked within the scene; b) converting the determined three-dimensional point cloud of the object to be fitted and tracked into an orthographic representation; c) determining curvature centre points to estimate a central axis position of at least one part the object to be fitted and tracked using the orthographic representation; d) determining the position of the plurality of control points representing the object to be fitted and tracked within the three-dimensional scene using the orthographic representation; and e) fitting and tracking the plurality of control points within the three-dimensional scene using the orthographic representation to refine the position of the skeletal representation of the object with respect to time.