Markerless tracking using planar structures in the scene
Published 7 November 2002
Gilles Simon, Andrew Fitzgibbon, Andrew Zisserman
Citations267
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
A markerless camera tracking system for augmented reality that operates in environments which contain one or more planes, which is a common special case, which it is shown significantly simplifies tracking.
Abstract
We describe a markerless camera tracking system for augmented reality that operates in environments which contain one or more planes. This is a common special case, which we show significantly simplifies tracking. The result is a practical, reliable, vision-based tracker. Furthermore, the tracked plane imposes a natural reference frame, so that the alignment of the real and virtual coordinate systems is rather simpler than would be the case with a general structure-and-motion system. Multiple planes can be tracked, and additional data such as 2D point tracks are easily incorporated.
Keywords
Computer ScienceEarth and Planetary SciencesEngineering
Communications of the ACMRandom sample consensus
25,463 Citations1981Martin A. Fischler, Robert C. Bolles
New results are derived on the minimum number of landmarks needed to obtain a solution, and algorithms are presented for computing these minimum-landmark solutions in closed form that provide the basis for an automatic system that can solve the Location Determination Problem under difficult viewing.
Cambridge University Press eBooksMultiple View Geometry in Computer Vision
20,788 Citations2004Richard Hartley, Andrew Zisserman
A Combined Corner and Edge Detector
12,478 Citations1988Chris Harris, Matthew J. Stephens
The problem the authors are addressing in Alvey Project MMI149 is that of using computer vision to understand the unconstrained 3D world, in which the viewed scenes will in general contain too wide a diversity of objects for topdown recognition techniques to work.
International Journal of Computer VisionModel-based object pose in 25 lines of code
996 Citations1995Daniel DeMenthon, Larry S. Davis
Compared to classic approaches making use of Newton's method, POSIT does not require starting from an initial guess, and computes the pose using an order of magnitude fewer floating point operations; it may therefore be a useful alternative for real-time operation.
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.
International Joint Conference on Artificial IntelligenceTowards automatic visual obstacle avoidance
755 Citations1977Hans P. Morevec
This report describes ongoing research on a working system which drives a vehicle through cluttered environments under computer control, guided by images perceived through an onboard television camera.
International Journal of Computer VisionUsing vanishing points for camera calibration
709 Citations1990Bruno Caprile, Vincent Torre
Extensive experimentation shows that the precision that can be achieved with the proposed method is sufficient to efficiently perform machine vision tasks that require camera calibration, like depth from stereo and motion from image sequence.
Lecture notes in computer scienceAutomatic camera recovery for closed or open image sequences
397 Citations1998Andrew Fitzgibbon, Andrew Zisserman
Progress in completely automatically recovering 3D scene structure together with 3D camera positions from a sequence of images acquired by an unknown camera undergoing unknown movement is described.
Lecture notes in computer science3D model acquisition from extended image sequences
382 Citations1996Paul Beardsley, P. Torr +1 more
A method for matching image primitives through a sequence is described, for the purpose of acquiring 3D geometric models, which includes a novel robust estimator of the trifocal tensor, based on a minimum number of token correspondences across an image triplet.
SCAAT
270 Citations1997Greg Welch, Gary Bishop
The introduction and exploration of the SCAAT approach to 3D tracking for virtual environments is introduced, which facilitates user motion prediction, multisensor data fusion, and in systems where the observations are only available sequentially it provides estimates at a higher rate and with lower latency than a multiple-constraint approach.
Lecture notes in computer scienceAutomatic 3D Model Construction for Turn-Table Sequences
214 Citations1998Andrew Fitzgibbon, G. Cross +1 more
A system which, given a sequence of images of an object rotating about a single axis, generates a textured 3D model fully automatically, and requires no prior information about the cameras or scene, and does not require that the turntable angles be known.
IEEE Transactions on MultimediaNatural feature tracking for augmented reality
159 Citations1999Ulrich Neumann, Sisi You
This work develops robust computer vision methods to detect and track natural features in video images that represent a step toward integrating vision with graphics to produce robust wide-area augmented realities.
Computers in Biology and MedicineVision-based object registration for real-time image overlay
145 Citations1995Michihiro Uenohara, Takeo Kanade
IEEE Transactions on Visualization and Computer GraphicsCalibration-free augmented reality
140 Citations1998Kiriakos N. Kutulakos, J. Vallino
A new approach to video-based augmented reality that avoids both camera calibration and Euclidean 3D measurements is described, which is readily implementable, imposes minimal computational and hardware requirements, and generates real-time and accurate video overlays even when the camera parameters vary dynamically.
Combining scene and auto-calibration constraints
137 Citations1999David Liebowitz, Andrew Zisserman
A simple approach to combining scene and auto-calibration constraints for the calibration of cameras from single views and stereo pairs and examples of various cases of constraint combination and degeneracy as well as computational techniques are presented.
Real-time vision-based camera tracking for augmented reality applications
137 Citations1997Dieter Koller, Gudrun Klinker +4 more
This work addresses the problem of accurately tracking the 3D motion of a monocular camera in a known 3D environment and dynamically estimating the3D camera location by utilizing fully automated landmark-based camera calibration and extended Kalman filter techniques to track landmarks and to estimate the camera location.
Image and Vision Computing3D positional integration from image sequences
130 Citations1988C.G. Harris, J.M. Pike
An explicit three-dimensional representation is constructed from feature points extracted from a sequence of images taken by a moving camera, and their 3D locations are accurately determined by use of Kalman filters.
Lecture notes in computer scienceModel-based object tracking in traffic scenes
76 Citations1992Daniela Koller, Kostas Daniilidis +2 more
This contribution addresses the problem of detection and tracking of moving vehicles in image sequences from traffic scenes recorded by a stationary camera by using a parameterized vehicle model and a recursive estimator based on a motion model for motion estimation.
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.
Computers & GraphicsTracking in unprepared environments for augmented reality systems
71 Citations1999Ronald Azuma, Jong Weon Lee +4 more
Two 3DOF results are summarized: a real-time system with a compass — inertial hybrid, and a non-real- time system fusing optical and inertial inputs.
A two-stage robust statistical method for temporal registration from features of various type
44 Citations2002Gilles Simon, Marie‐Odile Berger
A model registration system capable of tracking an object, the model of which is known, in an image sequence is presented and is able to give a correct estimate of the pose even when tracking errors occur.
Parallax geometry of smooth surfaces in multiple views
35 Citations1999G. Cross, Andrew Fitzgibbon +1 more
This paper investigates the multiple view geometry of smooth surfaces and a plane, where the plane provides a planar homography mapping between the views, and new solutions are given for the computation of epipolar and trifocal geometry for this type of scene.
Machine Vision and ApplicationsMixing synthetic and video images of an outdoor urban environment
23 Citations1999Marie‐Odile Berger, Brigitte Wrobel-Dautcourt +2 more
This paper presents a fully augmented 300-image sequence of a specific bridge, the Pont Neuf, and details the techniques used for matching 2D and 3D primitives and for tracking features over the sequence.
Real-time Panoramic Mosaics and Augmented Reality
23 Citations1998Manish Jethwa, Andrew Zisserman +1 more
It is shown that in certain common computer vision situations the transformation required can be defined by a small number of parameters, and consequently the search algorithms to estimate the transformation can be run at frame rate, without sacrificing robustness or accuracy.
Scholarworks (University of Massachusetts Amherst)Tracking Object Motion Across Aspect Changes for Augmented Reality
13 Citations1996Sai Ravela
A model registration system capable of tracking an object through distinct aspects in real-time is presented, which integrates tracking, pose determination, and aspect graph indexing.
Improving Augmented Reality using Image and Scene Constraints
12 Citations1999Robert A. Smith, Andrew Fitzgibbon +1 more
By incorporating image-based geometric constraints over multiple views, this paper improves on traditional techniques which use purely 3D information and directly target perceptual cues, important to the human visual system, by which errors in AR are most readily perceived.