A system for automatic pose-estimation from a single image in a city scene
Published 16 September 2002
Tomas Johansson, Roberto Cipolla
Citations37
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
An automatic system for pose-estimation from a single image in a city scene where each building has a model consisting of a number of parallel planes associated with it and the model having the best match is used to determine the position and orientation of the camera.
Abstract
We describe an automatic system for pose-estimation from a single image in a city scene. Each building has a model consisting of a number of parallel planes associated with it. The homographies for the best match of the planes to the image is estimated automatically for each of the possible buildings. We show how the estimation of homographies can be done effectively by reducing the search space and using fast convolution. The model having the best match is then used to determine the position and orientation of the camera. The results
Keywords
Computer ScienceEngineering
On plane-based camera calibration: A general algorithm, singularities, applications
544 Citations2003Peter Sturm, Stephen J. Maybank
A general algorithm for plane-based calibration that can deal with arbitrary numbers of views and calibration planes and it is easy to incorporate known values of intrinsic parameters is presented.
Lecture notes in computer scienceAutocalibration from planar scenes
348 Citations1998Bill Triggs
The theory and a practical algorithm for the autocalibration of a moving projective camera, from m ≥ 5 views of a planar scene, which generalizes Hartley's method for the internal calibration of a rotating camera to allow camera translation and to provide 3D as well as calibration information.
Metric rectification for perspective images of planes
337 Citations2002David Liebowitz, Andrew Zisserman
The novel contributions are that in a stratified context the various forms of providing metric information can be represented as circular constraints on the parameters of an affine transformation of the plane, providing a simple and uniform framework for integrating constraints.
International Journal of Computer VisionPlanar object recognition using projective shape representation
133 Citations1995C. Rothwell, Andrew Zisserman +2 more
This work describes a model based recognition system, called LEWIS, for the identification of planar objects based on a projectively invariant representation of shape, and provides an analysis of the combinatorial advantages of using index functions.
Algorithms for plane-based pose estimation
125 Citations2002Peter Sturm
A factorization-based method for the estimation of relative pose between planes and cameras is proposed, for the general case of n planes seen in m views, and a mechanism for computing missing data, i.e. when one or several of the planes are not visible in one orSeveral of the images, is described.
Image and Vision ComputingPlanar grouping for automatic detection of vanishing lines and points
113 Citations2000F. Schaffalitzky, Andrew Zisserman
It is demonstrated that the idea of grouping together features that satisfy a geometric relationship can be used, both for (automatic) detection and estimation of vanishing points and lines.
The cascaded Hough transform as an aid in aerial image interpretation
93 Citations2002Tinne Tuytelaars, Luc Van Gool +2 more
The iterated application of the Hough transform is presented as a means to exploit the degree of regularity in man-made structures to exploit regularities inCartography and other applications of remote sensing.
Efficient model library access by projectively invariant indexing functions
45 Citations2003C. Rothwell, Andrew Zisserman +2 more
Progress in building a model-based vision system for plane objects that uses algebraic projective invariants and the recognition system is described, giving examples of the invariant techniques working on real images.
Matching perspective views of coplanar structures using projective unwarping and similarity matching
39 Citations2002Robert T. Collins, J. Ross Beveridge
The problem of matching perspective views of coplanar structures composed of line segments is considered and both model-to-image and image- to-image correspondence matching are given a consistent treatment.
Using scene constraints during the calibration procedure
12 Citations2002Didier Bondyfalat, T. Papdopoulo +1 more
This paper focuses on the problem of calibration from a single view and a map of a scene and shows how some scenes constraints can be used to achieve a calibration like procedure.
Lecture notes in computer scienceDetecting Windows in City Scenes
2 Citations2002Björn Johansson, Fredrik Kahl
The performance of the system has been evaluated on an independent training set and the results show that the object category "window" can be reliably detected under various poses and lighting conditions.