Continuous Surface-Point Distributions for 3D Object Pose Estimation and Recognition

We present a 3D, probabilistic object-surface model, along with mechanisms for probabilistically integrating unregistered 2.5D views into the model, and for segmenting model instances in cluttered scenes. The object representation is a probabilistic expression of object parts through smooth surface-point distributions obtained by kernel density estimation on 3D point clouds. A multi-part, viewpoint-invariant model is learned incrementally from a set of roughly segmented, unregistered views, by sequentially registering and fusing the views with the incremental model. Registration is conducted by nonparametric inference of maximum-likelihood model parameters, using Metropolis

• Type: Journal
• Year: 2010
• Where: ACCV
• Authors: Renaud Detry, Justus H. Piater
• Keywords: ACCV 2010, Computer Vision, Model, Probabilistic Object-surface Model, Viewpoint-invariant Models