Results 1  10
of
44
Single View Metrology
, 1999
"... We describe how 3D affine measurements may be computed from a single perspective view of a scene given only minimal geometric information determined from the image. This minimal information is typically the vanishing line of a reference plane, and a vanishing point for a direction not parallel to th ..."
Abstract

Cited by 181 (4 self)
 Add to MetaCart
(Show Context)
We describe how 3D affine measurements may be computed from a single perspective view of a scene given only minimal geometric information determined from the image. This minimal information is typically the vanishing line of a reference plane, and a vanishing point for a direction not parallel to the plane. It is shown that affine scene structure may then be determined from the image, without knowledge of the camera's internal calibration (e.g. focal length), nor of the explicit relation between camera and world (pose). In particular, we show how to (i) compute the distance between planes parallel to the reference plane (up to a common scale factor); (ii) compute area and length ratios on any plane parallel to the reference plane; (iii) determine the camera's (viewer's) location. Simple geometric derivations are given for these results. We also develop an algebraic representation which unifies the three types of measurement and, amongst other advantages, permits a first order error pr...
Metric calibration of a stereo rig
 In Workshop on Representation of Visual Scenes
, 1995
"... ..."
(Show Context)
Canonical Frames for Planar Object Recognition
, 1992
"... We present a canonical frame construction for determining projectively invariant indexing functions for nonalgebraic smooth plane curves. These invariants are semilocal rather than global, which promotes tolerance to occlusion. Two applications are demonstrated. Firstly, we report preliminary work ..."
Abstract

Cited by 60 (10 self)
 Add to MetaCart
We present a canonical frame construction for determining projectively invariant indexing functions for nonalgebraic smooth plane curves. These invariants are semilocal rather than global, which promotes tolerance to occlusion. Two applications are demonstrated. Firstly, we report preliminary work on building a model based recognition system for planar objects. We demonstrate that the invariant measures, derived from the canonical frame, provide sufficient discrimination between objects to be useful for recognition. Recognition is of partially occluded objects in cluttered scenes. Secondly, jigsaw puzzles are assembled and rendered from a single strongly perspective view of the separate pieces. Both applications require no camera calibration or pose information, and models are generated and verified directly from images.
Active visual navigation using nonmetric structure
 In 5th IEEE Int. Conf. on Computer Vision
, 1995
"... ..."
(Show Context)
Affine calibration of mobile vehicles
 EuropeChina Workshop on Geometrical Modelling and Invariants for Computer Vision
, 1995
"... ..."
(Show Context)
Multiview Constraints on Homographies
 ieee Transactions on Pattern Analysis and Machine Intelligence
, 2002
"... The image motion of a planar surface between two camera views is captured by a homography (a 2D projective transformation). The homography depends on the intrinsic and extrinsic camera parameters, as well as on the 3D plane parameters. ..."
Abstract

Cited by 36 (0 self)
 Add to MetaCart
(Show Context)
The image motion of a planar surface between two camera views is captured by a homography (a 2D projective transformation). The homography depends on the intrinsic and extrinsic camera parameters, as well as on the 3D plane parameters.
A Comparison of Projective Reconstruction Methods for Pairs of Views
, 1995
"... Recently, different approaches for uncalibrated stereo have been suggested which permit projective reconstructions from multiple views. These use weak calibration which is represented by the epipolar geometry, and so we require no knowledge of the intrinsic or extrinsic camera parameters. In this pa ..."
Abstract

Cited by 36 (5 self)
 Add to MetaCart
Recently, different approaches for uncalibrated stereo have been suggested which permit projective reconstructions from multiple views. These use weak calibration which is represented by the epipolar geometry, and so we require no knowledge of the intrinsic or extrinsic camera parameters. In this paper we consider projective reconstructions from pairs of views, and compare a number of the available methods. Projective stereo algorithms can be categorized by the way in which the 3D coordinates are computed. The first class is similar to traditional stereo algorithms in that the 3D world geometry is made explicit; the initial phase of the processing always involves the estimation of the camera matrices from which the 3D coordinates are computed. We show how the camera matrices can be computed either from point correspondences, or how they are constrained by the fundamental matrices. The second class of algorithms are based on implicit image measurements which are used to compute project...
3D Object Recognition using Invariance
, 1994
"... The systems and concepts described in this paper document the evolution of the geometric invariance approach to object recognition over the last five years. Invariance overcomes one of the fundamental difficulties in recognising objects from images: that the appearance of an object depends on viewpo ..."
Abstract

Cited by 35 (5 self)
 Add to MetaCart
The systems and concepts described in this paper document the evolution of the geometric invariance approach to object recognition over the last five years. Invariance overcomes one of the fundamental difficulties in recognising objects from images: that the appearance of an object depends on viewpoint. This problem is entirely avoided if the geometric description is unaffected by the imaging transformation. Such invariant descriptions can be measured from images without any prior knowledge of the position, orientation and calibration of the camera. These invariant measurements can be used to index a library of object models for recognition and provide a principled basis for the other stages of the recognition process such as feature grouping and hypothesis verification. Object models can be acquired directly from images, allowing efficient construction of model libraries without manual intervention. A significant part of the paper is a summary of recent results on the construction of ...
Planar Grouping for Automatic Detection of Vanishing Lines and Points
 Image and Vision Computing
, 2000
"... It is demonstrated that grouping together features which satisfy a geometric relationship can be used both for (automatic) detection and estimation of vanishing points and lines. We describe the geometry of three commonly occurring types of geometric grouping and present efficient grouping algorithm ..."
Abstract

Cited by 34 (1 self)
 Add to MetaCart
(Show Context)
It is demonstrated that grouping together features which satisfy a geometric relationship can be used both for (automatic) detection and estimation of vanishing points and lines. We describe the geometry of three commonly occurring types of geometric grouping and present efficient grouping algorithms which exploit these geometries. The three types of grouping are : (1) a family of equally spaced coplanar parallel lines, (2) a planar pattern obtained by repeating some element by translation in the plane, and (3) a set of elements arranged in a regular planar grid. Examples of automatically computing groupings, together with their vanishing points and lines, are given for a number of real images. Key words: Grouping, Vanishing Point and Line Detection, Repetition. 1 Introduction Suppose a plane in the world is imaged by a perspective camera. Then the line at infinity of the plane is projected to a line in the image, the vanishing line. The objective of this paper is to automatically e...
Plane + Parallax, Tensors and Factorization
 In Proc. of ECCV
, 2000
"... Abstract. We study the special form that the general multiimage tensor formalism takes under the plane + parallax decomposition, including matching tensors and constraints, closure and depth recovery relations, and intertensor consistency constraints. Plane + parallax alignment greatly simplifies ..."
Abstract

Cited by 31 (1 self)
 Add to MetaCart
(Show Context)
Abstract. We study the special form that the general multiimage tensor formalism takes under the plane + parallax decomposition, including matching tensors and constraints, closure and depth recovery relations, and intertensor consistency constraints. Plane + parallax alignment greatly simplifies the algebra, and uncovers the underlying geometric content. We relate plane + parallax to the geometry of translating, calibrated cameras, and introduce a new parallaxfactorizing projective reconstruction method based on this. Initial plane + parallax alignment reduces the problem to a single rankone factorization of a matrix of rescaled parallaxes into a vector of projection centres and a vector of projective heights above the reference plane. The method extends to 3D lines represented by viapoints and 3D planes represented by homographies.