Shape recovery from an unorganized image sequence

Authors:
Kazuhiko Kawamoto;Atsushi Imiya;Kaoru Hirota
Affiliations:
Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan;Institute of Media and Information Technology, Chiba University, Chiba, Japan and Software Research Division, National Institute of Informatics, Tokyo, Japan;Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan
Venue:
MLDM'03 Proceedings of the 3rd international conference on Machine learning and data mining in pattern recognition
Year:
2003

Citing 11
Cited 0

A survey of the Hough transform

Computer Vision, Graphics, and Image Processing
Shape and motion from image streams under orthography: a factorization method

International Journal of Computer Vision
Which Hough transform?

CVGIP: Image Understanding
Geometric computation for machine vision

Geometric computation for machine vision
Three-dimensional computer vision: a geometric viewpoint

Three-dimensional computer vision: a geometric viewpoint
Randomized Hough transform (RHT): basic mechanisms, algorithms, and computational complexities

CVGIP: Image Understanding
SUSAN—A New Approach to Low Level Image Processing

International Journal of Computer Vision
Computing and simplifying 2D and 3D continuous skeletons

Computer Vision and Image Understanding
Implicit and nonparametric shape reconstruction from unorganized data using a variational level set method

Computer Vision and Image Understanding
Multiple view geometry in computer visiond

Multiple view geometry in computer visiond
Shape Reconstruction with Delaunay Complex

LATIN '98 Proceedings of the Third Latin American Symposium on Theoretical Informatics

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose a method for recovering a 3D object from an unorganized image sequence, in which the order of the images and the corresponding points among the images are unknown, using a random sampling and voting process. Least squares methods such that the factorization method and the 8-point algorithm are not directly applicable to an unorganized image sequence, because the corresponding points are a priori unknown. The proposed method repeatedly generates relevant shape parameters from randomly sampled data as a series of hypotheses, and finally produces the solutions supported by a large number of the hypotheses. The method is demonstrated on synthetic and real data.