Results 1  10
of
69
Evaluation of Interest Point Detectors
, 2000
"... Many different lowlevel feature detectors exist and it is widely agreed that the evaluation of detectors is important. In this paper we introduce two evaluation criteria for interest points: repeatability rate and information content. Repeatability rate evaluates the geometric stability under diff ..."
Abstract

Cited by 295 (7 self)
 Add to MetaCart
Many different lowlevel feature detectors exist and it is widely agreed that the evaluation of detectors is important. In this paper we introduce two evaluation criteria for interest points: repeatability rate and information content. Repeatability rate evaluates the geometric stability under different transformations. Information content measures the distinctiveness of features. Different interest point detectors are compared using these two criteria. We determine which detector gives the best results and show that it satisfies the criteria well.
Recognition without Correspondence using Multidimensional Receptive Field Histograms
 International Journal of Computer Vision
, 2000
"... . The appearance of an object is composed of local structure. This local structure can be described and characterized by a vector of local features measured by local operators such as Gaussian derivatives or Gabor filters. This article presents a technique where appearances of objects are represente ..."
Abstract

Cited by 209 (19 self)
 Add to MetaCart
. The appearance of an object is composed of local structure. This local structure can be described and characterized by a vector of local features measured by local operators such as Gaussian derivatives or Gabor filters. This article presents a technique where appearances of objects are represented by the joint statistics of such local neighborhood operators. As such, this represents a new class of appearance based techniques for computer vision. Based on joint statistics, the paper develops techniques for the identification of multiple objects at arbitrary positions and orientations in a cluttered scene. Experiments show that these techniques can identify over 100 objects in the presence of major occlusions. Most remarkably, the techniques have low complexity and therefore run in realtime. 1. Introduction The paper proposes a framework for the statistical representation of the appearance of arbitrary 3D objects. This representation consists of a probability density function or jo...
Variational principles, Surface Evolution, PDE's, level set methods and the Stereo Problem
 IEEE TRANSACTIONS ON IMAGE PROCESSING
, 1999
"... We present a novel geometric approach for solving the stereo problem for an arbitrary number of images (greater than or equal to 2). It is based upon the denition of a variational principle that must be satisfied by the surfaces of the objects in the scene and their images. The EulerLagrange equati ..."
Abstract

Cited by 194 (21 self)
 Add to MetaCart
We present a novel geometric approach for solving the stereo problem for an arbitrary number of images (greater than or equal to 2). It is based upon the denition of a variational principle that must be satisfied by the surfaces of the objects in the scene and their images. The EulerLagrange equations which are deduced from the variational principle provide a set of PDE's which are used to deform an initial set of surfaces which then move towards the objects to be detected. The level set implementation of these PDE's potentially provides an efficient and robust way of achieving the surface evolution and to deal automatically with changes in the surface topology during the deformation, i.e. to deal with multiple objects. Results of an implementation of our theory also dealing with occlusion and vibility are presented on synthetic and real images.
Efficient and Reliable Schemes for Nonlinear Diffusion Filtering
 IEEE Transactions on Image Processing
, 1998
"... Nonlinear diffusion filtering is usually performed with explicit schemes. They are only stable for very small time steps, which leads to poor efficiency and limits their practical use. Based on a recent discrete nonlinear diffusion scalespace framework we present semiimplicit schemes which are sta ..."
Abstract

Cited by 168 (18 self)
 Add to MetaCart
Nonlinear diffusion filtering is usually performed with explicit schemes. They are only stable for very small time steps, which leads to poor efficiency and limits their practical use. Based on a recent discrete nonlinear diffusion scalespace framework we present semiimplicit schemes which are stable for all time steps. These novel schemes use an additive operator splitting (AOS) which guarantees equal treatment of all coordinate axes. They can be implemented easily in arbitrary dimensions, have good rotational invariance and reveal a computational complexity and memory requirement which is linear in the number of pixels. Examples demonstrate that, under typical accuracy requirements, AOS schemes are at least ten times more efficient than the widelyused explicit schemes.
Complete Dense Stereovision using Level Set Methods
 in Proc. 5th European Conf. on Computer Vision
, 1998
"... We present a novel geometric approach for solving the stereo problem for an arbitrary number of images (greater than or equal to 2). It is based upon the denition of a variational principle that must be satised by the surfaces of the objects in the scene and their images. The EulerLagrange equation ..."
Abstract

Cited by 106 (1 self)
 Add to MetaCart
We present a novel geometric approach for solving the stereo problem for an arbitrary number of images (greater than or equal to 2). It is based upon the denition of a variational principle that must be satised by the surfaces of the objects in the scene and their images. The EulerLagrange equations which are deduced from the variational principle provide a set of PDE's which are used to deform an initial set of surfaces which then move towards the objects to be detected. The level set implementation of these PDE's potentially provides an efficient and robust way of achieving the surface evolution and to deal automatically with changes in the surface topology during the deformation, i.e. to deal with multiple objects. Results of an implementation of our theory also dealing with occlusion and vibility are presented on synthetic and real images.
Comparing and Evaluating Interest Points
, 1998
"... Many computer vision tasks rely on feature extraction. Interest points are such features. This paper shows that interest points are geometrically stable under different transformations and have high information content (distinctiveness). These two properties make interest points very successful in t ..."
Abstract

Cited by 86 (1 self)
 Add to MetaCart
Many computer vision tasks rely on feature extraction. Interest points are such features. This paper shows that interest points are geometrically stable under different transformations and have high information content (distinctiveness). These two properties make interest points very successful in the context of image matching. To measure these two properties quantitatively, we introduce two evaluation criteria : repeatability rate and information content. The quality of the interest points depends on the detector used. In this paper several detectors are compared according to the criteria specified above. We determine which detector gives the best results and show that it satisfies the criteria well. 1 Introduction Interest points are locations in the image where the signal changes twodimensionally. Examples include corners 1 and Tjunctions, as well as locations where the texture varies significantly. Figure 1 shows an example of interest points detected on the "sower" painting...
Computing differential properties of 3D shapes from stereoscopic images without 3D models
, 1994
"... We are considering the problem of recovering the threedimensional geometry of a scene from binoculor stereo disparity. Once a dense disparity map has been computed from a stereo pair of images, one often needs to calculate some local diferential properties of the cowesponding 30 surface such as ..."
Abstract

Cited by 72 (9 self)
 Add to MetaCart
We are considering the problem of recovering the threedimensional geometry of a scene from binoculor stereo disparity. Once a dense disparity map has been computed from a stereo pair of images, one often needs to calculate some local diferential properties of the cowesponding 30 surface such as orientation or curvatures. The wual approach is to build a 30 reconstruction of the surface(s) from which all shape properties will then be derived without ever going back to the original images. In this paper, we depart from this paradigm and propose to w e the images directly to compute the shape properties. We thus propose a new method extending the classical cowelation method to estimate accurately both the disparity and its derivatives directly from the image data. We then relate those derivatives to diferential properties of the surface such as orientation and curvatures.
Straight Lines Have to Be Straight
 In SPIE, volume 2567
, 2001
"... Most algorithms in 3D computer vision rely on the pinhole camera model because of its simplicity, whereas video optics, especially lowcost wideangle or fisheye lenses, generate a lot of nonlinear distortion which can be critical. To find the distortion parameters of a camera, we use the followin ..."
Abstract

Cited by 60 (0 self)
 Add to MetaCart
Most algorithms in 3D computer vision rely on the pinhole camera model because of its simplicity, whereas video optics, especially lowcost wideangle or fisheye lenses, generate a lot of nonlinear distortion which can be critical. To find the distortion parameters of a camera, we use the following fundamental property: a camera follows the pinhole model if and only if the projection of every line in space onto the camera is a line. Consequently, if we find the transformation on the video image so that every line in space is viewed in the transformed image as a line, then we know how to remove the distortion from the image. The algorithm consists of first doing edge extraction on a possibly distorted video sequence, then doing polygonal approximation with a large tolerance on these edges to extract possible lines from the sequence, and then finding the parameters of our distortion model that best transform these edges to segments. Results are presented on real video images, compared with distortion calibration obtained by a full camera calibration method which uses a calibration grid.
Rigid Registration of 3D Ultrasound with MR Images: a New Approach Combining Intensity and Gradient Information
 IEEE Transactions on Medical Imaging
, 2001
"... We present a new imagebased technique to rigidly register intraoperative 3D ultrasound (US) with preoperative Magnetic Resonance (MR) images. Automatic registration is achieved by maximization of a similarity measure which generalizes the correlation ratio (CR), and whose novelty is to incorpo ..."
Abstract

Cited by 49 (10 self)
 Add to MetaCart
We present a new imagebased technique to rigidly register intraoperative 3D ultrasound (US) with preoperative Magnetic Resonance (MR) images. Automatic registration is achieved by maximization of a similarity measure which generalizes the correlation ratio (CR), and whose novelty is to incorporate multivariate information from the MR data (intensity and gradient). In addition, the similarity measure is built upon a robust intensitybased distance measure, which makes it possible to handle a variety of US artifacts. A crossvalidation study has been carried out using a number of phantom and clinical data. This indicates that the method is quite robust and that the worst registration errors are of the order of the MR image resolution. Keywords: image registration, ultrasound, magnetic resonance, correlation ratio, robust estimation. 1
Recursive Gaussian Derivative Filters
, 1998
"... We propose a new strategy to design recursive implementations of the Gaussian filter and Gaussian regularized derivative filters. Each recursive filter consists of a cascade of two stable N order subsystems (causal and anticausal). The computational complexity is 2N multiplications per pixel per d ..."
Abstract

Cited by 35 (2 self)
 Add to MetaCart
We propose a new strategy to design recursive implementations of the Gaussian filter and Gaussian regularized derivative filters. Each recursive filter consists of a cascade of two stable N order subsystems (causal and anticausal). The computational complexity is 2N multiplications per pixel per dimension independent of the size (s) of the Gaussian kernel. The filter coefficients have a closedform solution as a function of scale (s) and recursion order N (N=3,4,5). The recursive filters yield a high accuracy and excellent isotropy in nD space.