Results 1  10
of
179
Reliable Feature Matching Across Widely Separated Views
, 2000
"... In this paper we present a robust method for automatically matching features in images corresponding to the same physical point on an object seen from two arbitrary viewpoints. Unlike conventional stereo matching approaches we assume no prior knowledge about the relative camera positions and orienta ..."
Abstract

Cited by 308 (0 self)
 Add to MetaCart
(Show Context)
In this paper we present a robust method for automatically matching features in images corresponding to the same physical point on an object seen from two arbitrary viewpoints. Unlike conventional stereo matching approaches we assume no prior knowledge about the relative camera positions and orientations. In fact in our application this is the information we wish to determine from the image feature matches. Features are detected in two or more images and characterised using affine texture invariants. The problem of window effects is explicitly addressed by our method  our feature characterisation is invariant to linear transformations of the image data including rotation, stretch and skew. The feature matching process is optimised for a structurefrommotion application where we wish to ignore unreliable matches at the expense of reducing the number of feature matches.
Advances in computational stereo
 IEEE Transactions on Pattern Analysis and Machine Intelligence
, 2003
"... Abstract—Extraction of threedimensional structure of a scene from stereo images is a problem that has been studied by the computer vision community for decades. Early work focused on the fundamentals of image correspondence and stereo geometry. Stereo research has matured significantly throughout t ..."
Abstract

Cited by 224 (3 self)
 Add to MetaCart
(Show Context)
Abstract—Extraction of threedimensional structure of a scene from stereo images is a problem that has been studied by the computer vision community for decades. Early work focused on the fundamentals of image correspondence and stereo geometry. Stereo research has matured significantly throughout the years and many advances in computational stereo continue to be made, allowing stereo to be applied to new and more demanding problems. In this paper, we review recent advances in computational stereo, focusing primarily on three important topics: correspondence methods, methods for occlusion, and realtime implementations. Throughout, we present tables that summarize and draw distinctions among key ideas and approaches. Where available, we provide comparative analyses and we make suggestions for analyses yet to be done. Index Terms—Computational stereo, stereo correspondence, occlusion, realtime stereo, review. æ 1
Occlusions and binocular stereo
 International Journal of Computer Vision
, 1996
"... A pair of frames eyes and an epipolar line in the left frame A matching space has elements M lr that decide if a feature at pixel l in the left epipolar line matches to a feature at pixel r in the right epipolar line Two dierent potentials that enforce piecew ..."
Abstract

Cited by 144 (5 self)
 Add to MetaCart
A pair of frames eyes and an epipolar line in the left frame A matching space has elements M lr that decide if a feature at pixel l in the left epipolar line matches to a feature at pixel r in the right epipolar line Two dierent potentials that enforce piecewise smoothness It is desirable to use potentials Ux with large derivative where x eg x to avoid the creation of many small regions with small disparity changes Here x represents the disparity change between neighbouring pixel sites a A polyhedron shaded area with self occluding regions and with a discontinuity in the surfaceorientation at feature D and a depth discontinuity at feature C b A diagram of
Least squares 3D surface and curve matching
 ISPRS Journal of Photogrammetry and Remote Sensing
, 2005
"... The automatic coregistration of point clouds, representing 3D surfaces, is a relevant problem in 3D modeling. This multiple registration problem can be defined as a surface matching task. We treat it as least squares matching of overlapping surfaces. The surface may have been digitized/sampled poin ..."
Abstract

Cited by 104 (17 self)
 Add to MetaCart
The automatic coregistration of point clouds, representing 3D surfaces, is a relevant problem in 3D modeling. This multiple registration problem can be defined as a surface matching task. We treat it as least squares matching of overlapping surfaces. The surface may have been digitized/sampled point by point using a laser scanner device, a photogrammetric method or other surface measurement techniques. Our proposed method estimates the transformation parameters of one or more 3D search surfaces with respect to a 3D template surface, using the Generalized GaussMarkoff model, minimizing the sum of squares of the Euclidean distances between the surfaces. This formulation gives the opportunity of matching arbitrarily oriented 3D surface patches. It fully considers 3D geometry. Besides the mathematical model and execution aspects we address the further extensions of the basic model. We also show how this method can be used for curve matching in 3D space and matching of curves to surfaces. Some practical examples based on the registration of closerange laser scanner and photogrammetric point clouds are presented for the demonstration of the method. This surface matching technique is a generalization of the least squares image matching concept and offers high flexibility for any kind of 3D surface correspondence problem, as well as statistical tools for the analysis of the quality of final matching results.
The Geometry and Matching of Lines and Curves Over Multiple Views
"... This paper describes the geometry of imaged curves in two and three views. Multiview relationships are developed for lines, conics and nonalgebraic curves. The new relationships focus on determining the plane of the curve in a projective reconstruction, and in particular using the homography in ..."
Abstract

Cited by 52 (1 self)
 Add to MetaCart
This paper describes the geometry of imaged curves in two and three views. Multiview relationships are developed for lines, conics and nonalgebraic curves. The new relationships focus on determining the plane of the curve in a projective reconstruction, and in particular using the homography induced by this plane for transfer from one image to another. It is shown that given the fundamental matrix between two views, and images of the curve in each view, then the plane of a conic may be determined up to a two fold ambiguity, but local curvature of a curve uniquely determines the plane. It is then shown that given the trifocal tensor between three views, this plane defines a homography map which may be used to transfer a conic or the curvature from two views to a third. Simple expressions are developed for the plane and homography in each case.
3D Surface Reconstruction from Stereoscopic Image Sequences
 In Proc. ICCV
, 1995
"... A stereoscopic scene analysis system for 3–D modeling of objects from stereoscopic image sequences is described. A dense map of 3–D surface points is obtained by image correspondence, object segmentation, interpolation, and triangulation. Emphasis is put on the accurate measurement of image correspo ..."
Abstract

Cited by 35 (4 self)
 Add to MetaCart
(Show Context)
A stereoscopic scene analysis system for 3–D modeling of objects from stereoscopic image sequences is described. A dense map of 3–D surface points is obtained by image correspondence, object segmentation, interpolation, and triangulation. Emphasis is put on the accurate measurement of image correspondences from grey level images. The surface geometry of each scene object is approximated by a triangular wire–frame which stores the surface texture in texture maps. Sequence processing serves to track camera motion and to fuse surfaces from different view points into a consistent 3–D surface model. From the textured 3–D models, highly realistic image sequences from arbitrary view points can be synthesized using computer graphics techniques. 1
Least squares 3D surface matching
 IAPRS, 34(5/W16), (on CDROM
, 2004
"... The automatic coregistration of point clouds, representing 3D surfaces, is a relevant problem in 3D modeling. This registration problem can be defined as a surface matching problem. We treat it as least squares matching of overlapping surfaces. The point cloud may have been digitized/sampled point ..."
Abstract

Cited by 31 (5 self)
 Add to MetaCart
(Show Context)
The automatic coregistration of point clouds, representing 3D surfaces, is a relevant problem in 3D modeling. This registration problem can be defined as a surface matching problem. We treat it as least squares matching of overlapping surfaces. The point cloud may have been digitized/sampled point by point using a laser scanner device, a photogrammetric method or other surface measurement techniques. In the past, several efforts have been made concerning the registration of 3D point clouds. One of the most popular methods is the Iterative Closest Point (ICP) algorithm. Several variations and improvements of the ICP method have been proposed. In photogrammetry there have been some studies on the absolute orientation of stereo models using DEMs (Digital Elevation Model) as control information. These works are known as DEM matching, which corresponds mathematically with least squares image matching. The DEM matching concept is only applied to 2.5D surfaces. 2.5D surfaces have limited value, especially in close range applications. Our proposed method estimates the 3D similarity transformation parameters between two or more fully 3D surface patches, minimizing the Euclidean distances between the surfaces by least squares. This formulation gives the opportunity of matching arbitrarily oriented 3D surface patches. An observation equation is written for each surface element on the template surface patch, i.e. for each sampled point. The geometric relationship between the conjugate surface patches is defined as a 7parameter 3D similarity transformation. The constant term of the adjustment is given by the observation vector whose elements are the Euclidean distances between the template and search surface elements. Since the functional model is nonlinear, the solution is iteratively approaching to a global minimum. The unknown transformation parameters are treated as stochastic quantities using
Using Local Planar Geometric Invariants to Match and Model Images of Line Segments
 J. OF COMP. VISION AND IMAGE UNDERST
, 1998
"... Image matching consists of finding features in different images that represent the same feature of the observed scene. It is a basic process in vision whenever several images are used. This paper describes a matching algorithm for lines segments in two images. The key idea of the algorithm is to ass ..."
Abstract

Cited by 23 (5 self)
 Add to MetaCart
(Show Context)
Image matching consists of finding features in different images that represent the same feature of the observed scene. It is a basic process in vision whenever several images are used. This paper describes a matching algorithm for lines segments in two images. The key idea of the algorithm is to assume that the apparent motion between the two images can be approximated by a planar geometric transformation (a similarity or an affine transformation) and to compute such an approximation. Under such an assumption, local planar invariants related the kind of transformation used as approximation, should have the same value in both images. Such invariants are computed for simple segment configurations in both images and matched according to their values. A global constraint is added to insure a global coherency between all the possible matches: all the local matches must define approximately the same geometric transformation between the two images. These first matches are verified and complet...
Accuracy in Image Measure
 In Proc. SPIE, Videometrics III
, 1994
"... The aim of this paper is to show how image points can be extracted accurately. We will restrict our search to specific points identified by corners, which are stable given a sequence. Our approach makes use of a modelbased corner detector. It matches a part of the image containing a corner against ..."
Abstract

Cited by 22 (4 self)
 Add to MetaCart
The aim of this paper is to show how image points can be extracted accurately. We will restrict our search to specific points identified by corners, which are stable given a sequence. Our approach makes use of a modelbased corner detector. It matches a part of the image containing a corner against a predefined corner model. Once the fitting is accomplished, the position of the corner in the image can be deduced by the knowledge of the corner position in the image. The validity of our approach has been proven with 4 independent tests. It is shown that the accuracy which can be achieved is 1/10th of a pixel. Keywords : extraction of corners, modelbased algorithm, accurate location 1 INTRODUCTION Many applications, such as car crash inspection 1 or medical imaging, require very accurate image measurements. In this context the paper deals with the specific case of an image corner detector. Generally, it is hard to obtain accuracy in image measurements because of different source o...
Automated body modeling from video sequences
 in ICCV Workshop on Modeling People
, 1999
"... Synthetic modeling of human bodies and the simulation of motion is a longstanding problem in animation and much work is involved before a nearrealistic performance can be achieved. At present, it takes an experienced designer a very long time to build a complete and realistic model that closely res ..."
Abstract

Cited by 21 (2 self)
 Add to MetaCart
(Show Context)
Synthetic modeling of human bodies and the simulation of motion is a longstanding problem in animation and much work is involved before a nearrealistic performance can be achieved. At present, it takes an experienced designer a very long time to build a complete and realistic model that closely resembles a specific person. Our ultimate goal is to automate the process and to produce realistic animation models given a set of video sequences. In this paper, we show that, given video sequences of a person moving in front of the camera, we can recover shape information and joint locations. Both of which are essential to instantiate a complete and realistic model that closely resembles a specific person and without knowledge about the position of the articulations a character cannot be animated. This is achieved with minimal human intervention. The recovered shape and motion parameters can be used to reconstruct the original movement or to allow other animation models to mimic the subject’s actions. 1 1