Single-View RGBD-Based Reconstruction of Dynamic Human Geometry

• Published in: 2013 IEEE International Conference on Computer Vision Workshops pp. 307 - 314
• Main Authors: Malleson, Charles, Klaudiny, Martin, Hilton, Adrian, Guillemaut, Jean-Yves
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.12.2013
• Subjects: 3D reconstruction; articulated; Cameras; depth; Geometry; Iterative closest point algorithm; Joints; Optical imaging; piece-wise rigid; rgbd; rgbz; Sensors; Surface reconstruction
• DOI: 10.1109/ICCVW.2013.48

We present a method for reconstructing the geometry and appearance of indoor scenes containing dynamic human subjects using a single (optionally moving) RGBD sensor. We introduce a framework for building a representation of the articulated scene geometry as a set of piecewise rigid parts which are tracked and accumulated over time using moving voxel grids containing a signed distance representation. Data association of noisy depth measurements with body parts is achieved by online training of a prior shape model for the specific subject. A novel frame-to-frame model registration is introduced which combines iterative closest-point with additional correspondences from optical flow and prior pose constraints from noisy skeletal tracking data. We quantitatively evaluate the reconstruction and tracking performance of the approach using a synthetic animated scene. We demonstrate that the approach is capable of reconstructing mid-resolution surface models of people from low-resolution noisy data acquired from a consumer RGBD camera.