A unified factorization algorithm for points, line segments and planes with uncertainty models
Published 27 November 2002
Daniel Morris, Takeo Kanade
Citations116
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
This formulation leads to a weighted least squares motion and shape recovery problem which is solved by an efficient quasi-linear algorithm and the statistical uncertainty model enables us to recover uncertainty estimates for the reconstructed three dimensional feature locations.
Abstract
In this paper we present a unified factorization algorithm for recovering structure and motion from image sequences by using point features, line segments and planes. This new formulation is based on directional uncertainty model for features. Points and line segments are both described by the same probabilistic models and so can be recovered in the same way. Prior information on the coplanarity of features is shown to fit naturally into the new factorization formulation and provides additional constraints for the shape recovery. This formulation leads to a weighted least squares motion and shape recovery problem which is solved by an efficient quasi-linear algorithm. The statistical uncertainty model also enables us to recover uncertainty estimates for the reconstructed three dimensional feature locations.
Keywords
Computer ScienceEngineering
HAL (Le Centre pour la Communication Scientifique Directe)An Iterative Image Registration Technique with an Application to Stereo Vision
11,614 Citations1981Bruce D. Lucas, Takeo Kanade
This work presents a new image registration technique that makes use of the spatial intensity gradient of the images to find a good match using a type of Newton-Raphson iteration, and can be generalized to handle rotation, scaling and shearing.
Good features to track
6,858 Citations1994Jianbo Shi, Tomasi
A feature selection criterion that is optimal by construction because it is based on how the tracker works, and a feature monitoring method that can detect occlusions, disocclusions, and features that do not correspond to points in the world are proposed.
International Journal of Computer VisionShape and motion from image streams under orthography: a factorization method
2,884 Citations1992Carlo Tomasi, Takeo Kanade
A factorization method is developed that can overcome the difficulty by recovering shape and motion under orthography without computing depth as an intermediate step, and gives accurate results.
NatureA computer algorithm for reconstructing a scene from two projections
2,364 Citations1981H. C. Longuet–Higgins
A simple algorithm for computing the three-dimensional structure of a scene from a correlated pair of perspective projections is described here, when the spatial relationship between the two projections is unknown.
Discrete Random Signals and Statistical Signal Processing
870 Citations1992C.W. Therrien
Random vectors random processes moment analysis linear transformations estimation optimal filtering linear prediction linear models spectrum estimation.
IEEE Transactions on Pattern Analysis and Machine IntelligenceUniqueness and Estimation of Three-Dimensional Motion Parameters of Rigid Objects with Curved Surfaces
827 Citations1984R. Tsai, Thomas S. Huang
It is shown that seven point correspondences are sufficient to uniquely determine from two perspective views the three-dimensional motion parameters (within a scale factor for the translations) of a rigid object with curved surfaces.
AutomaticaDiscrete random signals and statistical signal processing
808 Citations1993Miloslav Vošvrda
This survey of the field is well done: it is efficient, lucid and engaging, and for teaching purposes the book can be faulted little.
Proceedings of the IEEETracking a few extreme singular values and vectors in signal processing
489 Citations1990Pierre Comon, Gene H. Golub
In various applications it is necessary to keep track of a low-rank approximation of a covariance matrix, R(t), slowly varying with time, and it is shown why this heavy computational burden is questionable in numerous situations and should be revised.
IEEE Transactions on Pattern Analysis and Machine IntelligenceA paraperspective factorization method for shape and motion recovery
467 Citations1997Conrad J. Poelman, Takeo Kanade
This work has shown that the paraperspective factorization method can be applied to a much wider range of motion scenarios, including image sequences containing motion toward the camera and aerial image sequences of terrain taken from a low-altitude airplane.
Journal of Visual Communication and Image RepresentationRecovering 3D Shape and Motion from Image Streams Using Nonlinear Least Squares
327 Citations1994Richard Szeliski, Sing Bing Kang
A shape and motion estimation algorithm based on nonlinear least squares applied to the tracks of features through time is presented, using an object-centered representation for faster and more accurate structure and motion recovery.
IEEE Transactions on Pattern Analysis and Machine IntelligenceStructure and motion from line segments in multiple images
246 Citations1995C. James Taylor, David Kriegman
Factorization methods for projective structure and motion
242 Citations1996Bill Triggs
This paper describes a family of factorization-based algorithms that recover 3D projective structure and motion from multiple uncalibrated perspective images of 3D points and lines that can be viewed as generalizations of the Tomasi-Kanade algorithm from affine to fully perspective cameras, and from points to lines.
International Journal of Computer VisionA multi-frame approach to visual motion perception
139 Citations1991Minas E. Spetsakis, John Aloimonos
This paper presents an algorithm based on multiple frames that employs only the rigidity assumption, is simple and mathematically elegant and, experimentally, proves to be a major improvement over the two-frame algorithms.
A unified factorization algorithm for points, line segments and planes with uncertainty models
116 Citations2002Daniel Morris, Takeo Kanade
This formulation leads to a weighted least squares motion and shape recovery problem which is solved by an efficient quasi-linear algorithm and the statistical uncertainty model enables us to recover uncertainty estimates for the reconstructed three dimensional feature locations.
Recursive estimation of structure and motion using relative orientation constraints
73 Citations2002A. Azarbayejani, B. Horowitz +1 more
A recursive estimation technique for recovering the 3-D motion and pointwise structure of an object is presented which is remarkably accurate, stable, and fast-conveying.
A factorization method for affine structure from line correspondences
39 Citations1996Long Quan, Takeo Kanade
It is established that affine shape and motion with uncalibrated affine cameras can be achieved with at least seven lines over three views, which extends the previous results of Koenderink and Van Doorn (1989) for points to lines.
Extended structure and motion analysis from monocular image sequences
34 Citations2002Ning Cui, John Weng +1 more
The simulations and experiments with long image sequences of real world scenes indicate that the optimization method developed greatly reduces the computational complexity and substantially improves the motion and structure estimation over that produced by linear algorithms.
Research Showcase @ Carnegie Mellon University (Carnegie Mellon University)Error modelling in stereo navigation
20 Citations2018Larry Matthies, Steven A. Shafer
Simulations show that compared to scalar error models the 3-D gaussian reduces the variance in robot position estimates and better distinguishes rotational from translational motion in stereo vision.