Weak-perspective structure from motion for strongly contaminated data

Levente Hajder, D. Chetverikov

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

It is widely known that, for the affine camera model, both shape and motion data can be factorised directly from the measurement matrix containing the image coordinates of the tracked feature points. However, classical algorithms for structure from motion (SfM) are not robust: measurement outliers, that is, incorrectly detected or matched feature points can destroy the result. A few methods to robustify SfM have already been proposed. Different outlier detection schemes have been used. We examine an efficient algorithm by Trajković and Hedley [Trajković, M., Hedley, M., 1997. Robust recursive structure and motion recovery under affine projection. In: Proc. British Machine Vision Conference. Available from: ] who use the affine camera model and the least median of squares (LMedS) method to separate inliers from outliers. LMedS is only applicable when the ratio of inliers exceeds 50%. We show that the least trimmed squares (LTS) method is more efficient in robust SfM than LMedS. In particular, we demonstrate that LTS can handle inlier ratios below 50%. We also show that using the real (Euclidean) motion data results in more precise SfM than using the affine motion data. Based on these observations, we propose a novel robust SfM algorithm and discuss its advantages and limits. Furthermore, we introduce a RANSAC based outlier detector that also provides robust results. The proposed methods and the Trajković procedure are quantitatively compared on synthetic data in different simulated situations. The methods are also tested on synthesised and real video sequences.

Original languageEnglish
Pages (from-to)1581-1589
Number of pages9
JournalPattern Recognition Letters
Volume27
Issue number14
DOIs
Publication statusPublished - Oct 15 2006

Fingerprint

Cameras
Computer vision
Detectors
Recovery

Keywords

  • Factorisation
  • Robustness
  • Structure from motion
  • Weak perspective

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Weak-perspective structure from motion for strongly contaminated data. / Hajder, Levente; Chetverikov, D.

In: Pattern Recognition Letters, Vol. 27, No. 14, 15.10.2006, p. 1581-1589.

Research output: Contribution to journalArticle

@article{4f0786330cef424499cd87bd0ef88534,
title = "Weak-perspective structure from motion for strongly contaminated data",
abstract = "It is widely known that, for the affine camera model, both shape and motion data can be factorised directly from the measurement matrix containing the image coordinates of the tracked feature points. However, classical algorithms for structure from motion (SfM) are not robust: measurement outliers, that is, incorrectly detected or matched feature points can destroy the result. A few methods to robustify SfM have already been proposed. Different outlier detection schemes have been used. We examine an efficient algorithm by Trajković and Hedley [Trajković, M., Hedley, M., 1997. Robust recursive structure and motion recovery under affine projection. In: Proc. British Machine Vision Conference. Available from: ] who use the affine camera model and the least median of squares (LMedS) method to separate inliers from outliers. LMedS is only applicable when the ratio of inliers exceeds 50{\%}. We show that the least trimmed squares (LTS) method is more efficient in robust SfM than LMedS. In particular, we demonstrate that LTS can handle inlier ratios below 50{\%}. We also show that using the real (Euclidean) motion data results in more precise SfM than using the affine motion data. Based on these observations, we propose a novel robust SfM algorithm and discuss its advantages and limits. Furthermore, we introduce a RANSAC based outlier detector that also provides robust results. The proposed methods and the Trajković procedure are quantitatively compared on synthetic data in different simulated situations. The methods are also tested on synthesised and real video sequences.",
keywords = "Factorisation, Robustness, Structure from motion, Weak perspective",
author = "Levente Hajder and D. Chetverikov",
year = "2006",
month = "10",
day = "15",
doi = "10.1016/j.patrec.2006.03.007",
language = "English",
volume = "27",
pages = "1581--1589",
journal = "Pattern Recognition Letters",
issn = "0167-8655",
publisher = "Elsevier",
number = "14",

}

TY - JOUR

T1 - Weak-perspective structure from motion for strongly contaminated data

AU - Hajder, Levente

AU - Chetverikov, D.

PY - 2006/10/15

Y1 - 2006/10/15

N2 - It is widely known that, for the affine camera model, both shape and motion data can be factorised directly from the measurement matrix containing the image coordinates of the tracked feature points. However, classical algorithms for structure from motion (SfM) are not robust: measurement outliers, that is, incorrectly detected or matched feature points can destroy the result. A few methods to robustify SfM have already been proposed. Different outlier detection schemes have been used. We examine an efficient algorithm by Trajković and Hedley [Trajković, M., Hedley, M., 1997. Robust recursive structure and motion recovery under affine projection. In: Proc. British Machine Vision Conference. Available from: ] who use the affine camera model and the least median of squares (LMedS) method to separate inliers from outliers. LMedS is only applicable when the ratio of inliers exceeds 50%. We show that the least trimmed squares (LTS) method is more efficient in robust SfM than LMedS. In particular, we demonstrate that LTS can handle inlier ratios below 50%. We also show that using the real (Euclidean) motion data results in more precise SfM than using the affine motion data. Based on these observations, we propose a novel robust SfM algorithm and discuss its advantages and limits. Furthermore, we introduce a RANSAC based outlier detector that also provides robust results. The proposed methods and the Trajković procedure are quantitatively compared on synthetic data in different simulated situations. The methods are also tested on synthesised and real video sequences.

AB - It is widely known that, for the affine camera model, both shape and motion data can be factorised directly from the measurement matrix containing the image coordinates of the tracked feature points. However, classical algorithms for structure from motion (SfM) are not robust: measurement outliers, that is, incorrectly detected or matched feature points can destroy the result. A few methods to robustify SfM have already been proposed. Different outlier detection schemes have been used. We examine an efficient algorithm by Trajković and Hedley [Trajković, M., Hedley, M., 1997. Robust recursive structure and motion recovery under affine projection. In: Proc. British Machine Vision Conference. Available from: ] who use the affine camera model and the least median of squares (LMedS) method to separate inliers from outliers. LMedS is only applicable when the ratio of inliers exceeds 50%. We show that the least trimmed squares (LTS) method is more efficient in robust SfM than LMedS. In particular, we demonstrate that LTS can handle inlier ratios below 50%. We also show that using the real (Euclidean) motion data results in more precise SfM than using the affine motion data. Based on these observations, we propose a novel robust SfM algorithm and discuss its advantages and limits. Furthermore, we introduce a RANSAC based outlier detector that also provides robust results. The proposed methods and the Trajković procedure are quantitatively compared on synthetic data in different simulated situations. The methods are also tested on synthesised and real video sequences.

KW - Factorisation

KW - Robustness

KW - Structure from motion

KW - Weak perspective

UR - http://www.scopus.com/inward/record.url?scp=33747872419&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33747872419&partnerID=8YFLogxK

U2 - 10.1016/j.patrec.2006.03.007

DO - 10.1016/j.patrec.2006.03.007

M3 - Article

AN - SCOPUS:33747872419

VL - 27

SP - 1581

EP - 1589

JO - Pattern Recognition Letters

JF - Pattern Recognition Letters

SN - 0167-8655

IS - 14

ER -