3D shape estimation from silhouettes using mean-shift

Author

Kim, Donghoon ; Ruttle, Jonathan ; Dahyot, Rozenn

Author_Institution

Sch. of Comput. Sci. & Stat., Trinity Coll. Dublin, Dublin, Ireland

fYear

2010

fDate

14-19 March 2010

Firstpage

1430

Lastpage

1433

Abstract

In this article, a novel method to accurately estimate 3D surface of objects of interest is proposed. Each ray projected from 2D image plane to 3D space is modelled with the Gaussian kernel function. Then a mean shift algorithm with an annealing scheme is used to find maximums of the probability density function and recovers the 3D surface. Experimental results show that our method is more accurate to estimate 3D surface than the Radon transform-based approach.

Keywords

Gaussian processes; Radon transforms; object detection; probability; shape recognition; 2D image plane; 3D shape estimation; 3D surface estimation; Gaussian kernel function; Radon transform; mean shift algorithm; probability density function; silhouettes; Biomedical image processing; Cameras; Computed tomography; Histograms; Image reconstruction; Kernel; Magnetic resonance imaging; Probability density function; Shape; Surface reconstruction; 3D shape estimation; 3D shape reconstruction; 3D shape recovery; mean shift; shape from silhouettes;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics Speech and Signal Processing (ICASSP), 2010 IEEE International Conference on

Conference_Location

Dallas, TX

ISSN

1520-6149

Print_ISBN

978-1-4244-4295-9

Electronic_ISBN

1520-6149

Type

conf

DOI

10.1109/ICASSP.2010.5495474

Filename

5495474