Vision and Lie's approach to invariance
Image and Vision ComputingPublished 1 May 1995
Luc Van Gool, Theo Moons, Els Pauwels, A. Oosterlinck
Citations81
SJR quartileQ1
SJR score0.79
SNIP1.33
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
The theory of Lie groups is described, a systematic approach to the problem of extracting invariants from Lie groups that helps in tackling problems such as calibration-less vision, efficient matching, shape-from-motion, grouping, and several other problems considered crucial to intelligent vision.
Abstract
The application of invariance theory has gained a renewed interest in the computer vision community. Recent results show that it offers a strong, unifying framework that helps in tackling problems such as calibration-less vision, efficient matching, shape-from-motion, grouping, and several other problems considered crucial to intelligent vision. Nonetheless, a systematic approach to the problem of extracting invariants is far from trivial. This paper describes one such approach, the theory of Lie groups. After a concise and non-rigorous account on the method itself, typical problems that arise in vision are discussed. For each of these problems, one or more relevant examples are given.
Keywords
Computer ScienceEngineering
Acta Applicandae MathematicaeApplications of lie groups to differential equations
6,006 Citations1990
MIT Press eBooksGeometric invariance in computer vision
1,022 Citations1992Joseph L. Mundy, Andrew Zisserman
Part 1 foundations: algebraic invariants - invariant theory and enumerative combinatorics of young tableaux, and applications: transformation invariant indexing and invariant linear methods in photogrammetry and model-matching.
Journal of the Optical Society of America AAffine structure from motion
875 Citations1991Jan J. Koenderink, Andrea J. van Doorn
It is indicated how solutions of the structure-from-motion problem can be stratified in such a way that one explicitly knows at which stages various a priori assumptions enter and specific geometrical expertise is required.
Lecture notes in computer scienceWhat can be seen in three dimensions with an uncalibrated stereo rig?
833 Citations1992Olivier Faugeras
This paper addresses the problem of determining the kind of three- dimensional reconstructions that can be obtained from a binocular stereo rig for which no three-dimensional metric calibration data is available, and shows that even in this case some very rich non-metric reconstructions of the environment can nonetheless be obtained.
Lecture notes in computer scienceEuclidean reconstruction from uncalibrated views
346 Citations1994Richard Hartley
A practical algorithm for Euclidean reconstruction from several views with the same camera is given and is shown to behave very robustly in the presence of noise giving excellent calibration and reconstruction results.
Projective invariants of shapes
157 Citations2003Ittay Weiss
The author starts from classical theories for differential and algebraic invariants not previously used in image understanding, and studies general projective transformations, which include both perspective and orthographic projections as special cases.
Relative 3-D reconstruction using multiple uncalibrated images
123 Citations2002Roger Mohr, F. Veillon +1 more
International Journal of Computer VisionFoundations of semi-differential invariants
79 Citations1995Theo Moons, Els Pauwels +2 more
This paper elaborates the theoretical foundations of a semi-differential framework for invariance and shows that invariance under reparametrisation can be cast in the same framework.
Recognition and semi-differential invariants
65 Citations2002Luc Van Gool, P. Kempenaers +1 more
The method for the derivation of such invariants, based on Lie group theory and applicable to a wide spectrum of transformation groups, is described and invariant curve parameterizations are developed for affine and projective transformations.
MIT Press eBooksRecognizing general curved objects efficiently
48 Citations1992Andrew Zisserman, David Forsyth +2 more
Couples were matched in a “computer dating” study to examine the efficaciousness of the similarity hypothesis in fostering interpersonal attraction and some support for the Similarity Hypothesis was demonstrated.
Lecture notes in computer scienceAffine reconstruction from perspective image pairs obtained by a translating camera
40 Citations1994Theo Moons, Luc Van Gool +2 more
PerceptionInvariance from the Euclidean Geometer's Perspective
40 Citations1994Luc J. Van Gool, Theo Moons +2 more
A nonmathematical account explains the basic philosophy and trade-offs underlying invariance-based research and the principles are explained for the relatively simple case of planar-object recognition under arbitrary viewpoints.
Using Projective Invariants for Constant Time Library Indexing in Model Based Vision
29 Citations1991C. Rothwell, A. Zisserman +2 more
Similarity extraction and modeling
26 Citations2002Luc Van Gool, Johan Wagemans +2 more
A computer vision algorithm is presented that emulates such behavior in that it similarly makes use of shape redundancies for the concise description and meaningful segmentation of planar object contours.
Lecture notes in computer scienceOn geometric and algebraic aspects of 3D affine and projective structures from perspective 2D views
24 Citations1994Amnon Shashua
This paper proposes an affine framework for perspective views, captured by a single remarkably simple equation, based on a viewer-centered invariant the authors call relative affine structure, and shows that Euclidean, affine and projective structure representations can be obtained by simple specializations and generalizations of the main results.
IEEE Transactions on Pattern Analysis and Machine IntelligenceFundamental limitations on projective invariants of planar curves
22 Citations1995Kalle Åström
It is shown that all curves within a large class can be mapped arbitrarily close to a circle by projective transformations, which limits the possibility of finding so called projective normalisation schemes for closed planar curves.
Differential Invariants of Planar Curves and Recognizing Partially Occluded Shapes
18 Citations1992Alfred M. Bruckstein⋆, Arun N. Netravali
The derivation of signature functions, generalizing the intrinsic curvature versus arclength representation in case of rigid motions in the plane, is based on differential invariants associated to viewing transformations.
Lecture notes in computer scienceClassification based on the cross ratio
18 Citations1994Stephen J. Maybank
The performance of the cross ratio in model based vision is quantified for a decision rule which is computationally expensive, but which makes good use of the available information.
Lecture notes in computer scienceProjective invariants for planar contour recognition
8 Citations1994M Van Diest, Luc Van Gool +2 more
Methods for the generation of projectively invariant representations of curve segments between bitangent points as well as — and this for the first time — segments between inflections are outlined.
Lecture notes in computer scienceFundamental difficulties with projective normalization of planar curves
8 Citations1994Kalle Åström
There can not exist continuous projective invariants, and a projective normalisation scheme can not have both the properties of continuity and uniqueness, because uniqueness might be preferred but it is not essential for recognition.
Eliciting qualitative structure from image curve deformations
7 Citations2002Andrew Zisserman, Andrew Blake +3 more
A family of qualitative methods is described that determines structure of curves in a scene from their image projections in two or more views, unaffected by camera intrinsic parameters, so calibration is not required and viewer motion need not be known.
Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIESemidifferential invariants: algebraic-differential hybrids
5 Citations1992P. Kempenaers, Luc J. Van Gool +1 more
An algorithm for the recognition of plane shapes under pseudo- perspective projection is presented based on the comparison of features that remain invariant under 2-D affine transformations as part of the wider framework of semi-differential invariants.