Block world reconstruction from spherical stereo image pairs
Block world reconstruction from spherical stereo image pairs
We propose a block-based scene reconstruction method using multiple stereo pairs of spherical images. We assume that the urban scene consists of axis-aligned planar structures (Manhattan world). Captured spherical stereo images are converted into six central-point perspective images by cubic projection and façade alignment. Depth information is recovered by stereo matching between images. Semantic regions are segmented based on colour, edge and normal information. Independent 3D rectangular planes are constructed by fitting planes aligned with the principal axes of the segmented 3D points. Finally cuboid-based scene structure is recovered from multiple viewpoints by merging and refining planes based on connectivity and visibility. The reconstructed model efficiently shows the structure of the scene with a small amount of data.
Image processing, Image reconstruction, Semantics, Spheres, Three dimensional computer graphics, 3D reconstruction, Block world interpretation, Depth information, Multiple viewpoints, Perspective image, Planar structure, Scene reconstruction, Spherical imaging, Stereo image processing
104-121
Kim, H.
2c7c135c-f00b-4409-acb2-85b3a9e8225f
Hilton, Adrian
12782a55-4c4d-4dfb-a690-62505f6665db
Kim, H.
2c7c135c-f00b-4409-acb2-85b3a9e8225f
Hilton, Adrian
12782a55-4c4d-4dfb-a690-62505f6665db
Kim, H. and Hilton, Adrian
(2015)
Block world reconstruction from spherical stereo image pairs.
Computer Vision and Image Understanding, 139, .
(doi:10.1016/j.cviu.2015.04.001).
Abstract
We propose a block-based scene reconstruction method using multiple stereo pairs of spherical images. We assume that the urban scene consists of axis-aligned planar structures (Manhattan world). Captured spherical stereo images are converted into six central-point perspective images by cubic projection and façade alignment. Depth information is recovered by stereo matching between images. Semantic regions are segmented based on colour, edge and normal information. Independent 3D rectangular planes are constructed by fitting planes aligned with the principal axes of the segmented 3D points. Finally cuboid-based scene structure is recovered from multiple viewpoints by merging and refining planes based on connectivity and visibility. The reconstructed model efficiently shows the structure of the scene with a small amount of data.
This record has no associated files available for download.
More information
Accepted/In Press date: 6 April 2015
e-pub ahead of print date: 21 August 2015
Keywords:
Image processing, Image reconstruction, Semantics, Spheres, Three dimensional computer graphics, 3D reconstruction, Block world interpretation, Depth information, Multiple viewpoints, Perspective image, Planar structure, Scene reconstruction, Spherical imaging, Stereo image processing
Identifiers
Local EPrints ID: 440585
URI: http://eprints.soton.ac.uk/id/eprint/440585
PURE UUID: 021f673f-00a8-4d85-9128-5f253d9067e4
Catalogue record
Date deposited: 07 May 2020 16:38
Last modified: 17 Mar 2024 04:01
Export record
Altmetrics
Contributors
Author:
H. Kim
Author:
Adrian Hilton
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics