Dynamic Surface Reconstruction by Recursive Fusion of Depth and Position Measurements

Surface estimation can be performed based on
position or depth measurements. We propose a method to fuse
both types of measurements. Position measurements are obtained
from landmarks on the surface, i.e., they are fixed to a certain
point on the surface. In contrast, depth measurements reflect the
depth measured along a line emanating from a depth camera
and are not fixed to a position on the surface. The proposed
approach uses a mixture of Cartesian and polar or spherical
coordinate to treat both measurement types accordingly. By doing
so, the uncertainties associated with the different measurement
types are explicitly considered. The presented method represents
the surface by a spline and is applicable to both 2D and 3D
applications. Surface estimation is considered as a recursive
filtering problem and standard nonlinear filtering methods such
as the unscented Kalman filter can be used to obtain surface
estimates. We show a thorough evaluation of the proposed
approach in simulations.