PUMA
Istituto di Scienza e Tecnologie dell'Informazione     
Mellado N., Dellepiane M., Scopigno R. Relative scale estimation and 3D registration of multi-modal geometry using growing least squares. In: IEEE Transactions on Visualization and Computer Graphics, vol. 22 (9) pp. 2160 - 2173. IEEE, 2016.
 
 
Abstract
(English)
The advent of low cost scanning devices and the improvement of multi-view stereo techniques have made the acquisition of 3D geometry ubiquitous. Data gathered from different devices, however, result in large variations in detail, scale, and coverage. Registration of such data is essential before visualizing, comparing and archiving them. However, state-of-the-art methods for geometry registration cannot be directly applied due to intrinsic differences between the models, e.g., sampling, scale, noise. In this paper we present a method for the automatic registration of multi-modal geometric data, i.e., acquired by devices with different properties (e.g., resolution, noise, data scaling). The method uses a descriptor based on Growing Least Squares, and is robust to noise, variation in sampling density, details, and enables scale-invariant matching. It allows not only the measurement of the similarity between the geometry surrounding two points, but also the estimation of their relative scale. As it is computed locally, it can be used to analyze large point clouds composed of millions of points. We implemented our approach in two registration procedures (assisted and automatic) and applied them successfully on a number of synthetic and real cases. We show that using our method, multi-modal models can be automatically registered, regardless of their differences in noise, detail, scale, and unknown relative coverage.
URL: http://ieeexplore.ieee.org/document/7349220/
DOI: 10.1109/TVCG.2015.2505287
Subject Multi-modal data
3D registration
Multi-scale descriptors
I.3.5 Computational Geometry and Object Modeling


Icona documento 1) Download Document PDF


Icona documento Open access Icona documento Restricted Icona documento Private

 


Per ulteriori informazioni, contattare: Librarian http://puma.isti.cnr.it

Valid HTML 4.0 Transitional