General 3D modelling of novel objects from a single view
Authors:
- 1 October 2010
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21530858,p. 3700-3705
Abstract
In this paper we present a method for building models for grasping from a single 3D snapshot of a scene composed of objects of daily use in human living environments. We employ fast shape estimation, probabilistic model fitting and verification methods capable of dealing with different kinds of symmetries, and combine these with a triangular mesh of the parts that have no other representation to model previously unseen objects of arbitrary shape. Our approach is enhanced by the information given by the geometric clues about different parts of objects which serve as prior information for the selection of the appropriate reconstruction method. While we designed our system for grasping based on single view 3D data, its generality allows us to also use the combination of multiple views. We present two application scenarios that require complete geometric models: grasp planning and locating objects in camera images.Keywords
This publication has 13 references indexed in Scilit:
- Scalable learning for object detection with GPU hardware2009
- Fast Point Feature Histograms (FPFH) for 3D registration2009
- Object recognition and full pose registration from a single image for robotic manipulation2009
- CAD-based recognition of 3D objects in monocular images2009
- Learning informative point classes for the acquisition of object model maps2008
- Efficient RANSAC for Point‐Cloud Shape DetectionComputer Graphics Forum, 2007
- Shape from symmetry2005
- GraspIt!IEEE Robotics & Automation Magazine, 2004
- Superquadric representation of automotive parts applying part decompositionJournal of Electronic Imaging, 2004
- Random sample consensusCommunications of the ACM, 1981