Conditions for segmentation of 2D translations of 3D objects

Link to publisher's homepage at http://link.springer.com/

Saved in:
Bibliographic Details
Main Authors: Shafriza Nisha, Basah, Dr., Bab-Hadiashar, Alireza, Hoseinnezhad, Reza
Other Authors: rezah@unimelb.edu.au
Format: Article
Language:English
Published: Springer Berlin Heidelberg 2014
Subjects:
Online Access:http://dspace.unimap.edu.my:80/dspace/handle/123456789/33927
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.unimap-33927
record_format dspace
spelling my.unimap-339272014-04-23T01:34:37Z Conditions for segmentation of 2D translations of 3D objects Shafriza Nisha, Basah, Dr. Bab-Hadiashar, Alireza Hoseinnezhad, Reza rezah@unimelb.edu.au abab-hadiashar@swin.edu.au sbasah@swin.edu.au Motion segmentation Multibody structure-and-motion Fundamental matrix Robust estimation Link to publisher's homepage at http://link.springer.com/ Various computer vision applications involve recovery and estimation of multiple motions from images of dynamic scenes. The exact nature of objects’ motions and the camera parameters are often not known a priori and therefore, the most general motion model (the fundamental matrix) is applied. Although the estimation of a fundamental matrix and its use for motion segmentation are well understood, the conditions governing the feasibility of segmentation for different types of motions are yet to be discovered. In this paper, we study the feasibility of separating 2D translations of 3D objects in a dynamic scene. We show that successful segmentation of 2D translations depends on the magnitude of the translations, average distance between the camera and objects, focal length of the camera and level of noise. Extensive set of controlled experiments using both synthetic and real images were conducted to show the validity of the proposed constraints. In addition, we quantified the conditions for successful segmentation of 2D translations in terms of the magnitude of those translations, the average distance between the camera and objects in motions for a given camera. These results are of particular importance for practitioners designing solutions for computer vision problems. 2014-04-23T01:34:37Z 2014-04-23T01:34:37Z 2009 Article Image Analysis and Processing, vol. 5716, 2009, pages 82-91 3642041450;978-364204145-7 03029743 http://dspace.unimap.edu.my:80/dspace/handle/123456789/33927 10.1007/978-3-642-04146-4_11 http://link.springer.com/chapter/10.1007%2F978-3-642-04146-4_11 en Springer Berlin Heidelberg
institution Universiti Malaysia Perlis
building UniMAP Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Malaysia Perlis
content_source UniMAP Library Digital Repository
url_provider http://dspace.unimap.edu.my/
language English
topic Motion segmentation
Multibody structure-and-motion
Fundamental matrix
Robust estimation
spellingShingle Motion segmentation
Multibody structure-and-motion
Fundamental matrix
Robust estimation
Shafriza Nisha, Basah, Dr.
Bab-Hadiashar, Alireza
Hoseinnezhad, Reza
Conditions for segmentation of 2D translations of 3D objects
description Link to publisher's homepage at http://link.springer.com/
author2 rezah@unimelb.edu.au
author_facet rezah@unimelb.edu.au
Shafriza Nisha, Basah, Dr.
Bab-Hadiashar, Alireza
Hoseinnezhad, Reza
format Article
author Shafriza Nisha, Basah, Dr.
Bab-Hadiashar, Alireza
Hoseinnezhad, Reza
author_sort Shafriza Nisha, Basah, Dr.
title Conditions for segmentation of 2D translations of 3D objects
title_short Conditions for segmentation of 2D translations of 3D objects
title_full Conditions for segmentation of 2D translations of 3D objects
title_fullStr Conditions for segmentation of 2D translations of 3D objects
title_full_unstemmed Conditions for segmentation of 2D translations of 3D objects
title_sort conditions for segmentation of 2d translations of 3d objects
publisher Springer Berlin Heidelberg
publishDate 2014
url http://dspace.unimap.edu.my:80/dspace/handle/123456789/33927
_version_ 1643797349447761920
score 13.222552