3D object reconstruction processing chain for extensible virtual spaces

Authors:
Miika Santala;Juha Hyvärinen;Seamus Hickey;Jarkko Vatjus-Anttila
Affiliations:
University of Oulu, Finland;University of Oulu, Finland;University of Oulu, Finland;University of Oulu, Finland
Venue:
Proceeding of the 16th International Academic MindTrek Conference
Year:
2012

Citing 2
Cited 0

A Method for Registration of 3-D Shapes

IEEE Transactions on Pattern Analysis and Machine Intelligence - Special issue on interpretation of 3-D scenes—part II
Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography

Communications of the ACM

Quantified Score

Hi-index	0.00

Visualization

Abstract

3D reconstruction of real world objects is an important content creation tool for the 3D internet. This poster shows how cheap commercial sensors can be used to reconstruct real 3D objects and import those objects within a 3D virtual world. This poster describes the implementation of a 3D content capturing processing chain using Microsoft Kinect. The capturing process includes a method for filtering and segmenting an object from the unwanted background data, a method for registering multiple scans together and a method for creating a solid surface presentation for the captured point cloud. The resulting 3D asset is imported and rendered in RealXtend Tundra 2.