Unsupervised learning of 3D object models from partial views

• Published in: 2009 IEEE International Conference on Robotics and Automation pp. 801 - 806
• Main Authors: Ruhnke, M., Steder, B., Grisetti, G., Burgard, W.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.05.2009
• Subjects: Clouds; Iterative algorithms; Laser modes; Layout; Merging; model learning; Object detection; range images; Robotics and automation; Robots; Robustness; Unsupervised learning
• ISBN: 1424427886; 9781424427888
• ISSN: 1050-4729
• DOI: 10.1109/ROBOT.2009.5152524

We present an algorithm for learning 3D object models from partial object observations. The input to our algorithm is a sequence of 3D laser range scans. Models learned from the objects are represented as point clouds. Our approach can deal with partial views and it can robustly learn accurate models from complex scenes. It is based on an iterative matching procedure which attempts to recursively merge similar models. The alignment between models is determined using a novel scan registration procedure based on range images. The decision about which models to merge is performed by spectral clustering of a similarity matrix whose entries represent the consistency between different models.