Results 1  10
of
29
Fast approximate energy minimization via graph cuts
 IEEE Transactions on Pattern Analysis and Machine Intelligence
, 2001
"... In this paper we address the problem of minimizing a large class of energy functions that occur in early vision. The major restriction is that the energy function’s smoothness term must only involve pairs of pixels. We propose two algorithms that use graph cuts to compute a local minimum even when v ..."
Abstract

Cited by 1384 (52 self)
 Add to MetaCart
In this paper we address the problem of minimizing a large class of energy functions that occur in early vision. The major restriction is that the energy function’s smoothness term must only involve pairs of pixels. We propose two algorithms that use graph cuts to compute a local minimum even when very large moves are allowed. The first move we consider is an αβswap: for a pair of labels α, β, this move exchanges the labels between an arbitrary set of pixels labeled α and another arbitrary set labeled β. Our first algorithm generates a labeling such that there is no swap move that decreases the energy. The second move we consider is an αexpansion: for a label α, this move assigns an arbitrary set of pixels the label α. Our second
The Computation of Optical Flow
, 1995
"... Twodimensional image motion is the projection of the threedimensional motion of objects, relative to a visual sensor, onto its image plane. Sequences of timeordered images allow the estimation of projected twodimensional image motion as either instantaneous image velocities or discrete image dis ..."
Abstract

Cited by 216 (10 self)
 Add to MetaCart
Twodimensional image motion is the projection of the threedimensional motion of objects, relative to a visual sensor, onto its image plane. Sequences of timeordered images allow the estimation of projected twodimensional image motion as either instantaneous image velocities or discrete image displacements. These are usually called the optical flow field or the image velocity field. Provided that optical flow is a reliable approximation to twodimensional image motion, it may then be used to recover the threedimensional motion of the visual sensor (to within a scale factor) and the threedimensional surface structure (shape or relative depth) through assumptions concerning the structure of the optical flow field, the threedimensional environment and the motion of the sensor. Optical flow may also be used to perform motion detection, object segmentation, timetocollision and focus of expansion calculations, motion compensated encoding and stereo disparity measurement. We investiga...
Markov random fields with efficient approximations
 In IEEE Conference on Computer Vision and Pattern Recognition
, 1998
"... Markov Random Fields (MRF’s) can be used for a wide variety of vision problems. In this paper we focus on MRF’s with twovalued clique potentials, which form a generalized Potts model. We show that the maximum a posteriori estimate of such an MRF can be obtained by solving a multiway minimum cut pro ..."
Abstract

Cited by 166 (22 self)
 Add to MetaCart
Markov Random Fields (MRF’s) can be used for a wide variety of vision problems. In this paper we focus on MRF’s with twovalued clique potentials, which form a generalized Potts model. We show that the maximum a posteriori estimate of such an MRF can be obtained by solving a multiway minimum cut problem on a graph. We develop efficient algorithms for computing good approximations to the minimum multiway cut. The visual correspondence problem can be formulated as an MRF in our framework; this yields quite promising results on real data with ground truth. We also apply our techniques to MRF’s with linear clique potentials. 1
Efficient GraphBased Energy Minimization Methods In Computer Vision
, 1999
"... ms (we show that exact minimization in NPhard in these cases). These algorithms produce a local minimum in interesting large move spaces. Furthermore, one of them nds a solution within a known factor from the optimum. The algorithms are iterative and compute several graph cuts at each iteration. Th ..."
Abstract

Cited by 83 (5 self)
 Add to MetaCart
ms (we show that exact minimization in NPhard in these cases). These algorithms produce a local minimum in interesting large move spaces. Furthermore, one of them nds a solution within a known factor from the optimum. The algorithms are iterative and compute several graph cuts at each iteration. The running time at each iteration is eectively linear due to the special graph structure. In practice it takes just a few iterations to converge. Moreover most of the progress happens during the rst iteration. For a certain piecewise constant prior we adapt the algorithms developed for the piecewise smooth prior. One of them nds a solution within a factor of two from the optimum. In addition we develop a third algorithm which nds a local minimum in yet another move space. We demonstrate the eectiveness of our approach on image restoration, stereo, and motion. For the data with ground truth, our methods signicantly outperform standard methods. Biographical Sketch Olga
The Design and Evolution of Modular Neural Network Architectures
 Neural Networks
, 1994
"... To investigate the relations between structure and function in both artificial and natural neural networks, we present a series of simulations and analyses with modular neural networks. We suggest a number of design principles in the form of explicit ways in which neural modules can cooperate in rec ..."
Abstract

Cited by 49 (0 self)
 Add to MetaCart
To investigate the relations between structure and function in both artificial and natural neural networks, we present a series of simulations and analyses with modular neural networks. We suggest a number of design principles in the form of explicit ways in which neural modules can cooperate in recognition tasks. These results may supplement recent accounts of the relation between structure and function in the brain. The networks used consist out of several modules, standard subnetworks that serve as higherorder units with a distinct structure and function. The simulations rely on a particular network module called CALM (Murre, Phaf, and Wolters, 1989, 1992). This module, developed mainly for unsupervised categorization and learning, is able to adjust its local learning dynamics. The way in which modules are interconnected is an important determinant of the learning and categorization behaviour of the network as a whole. Based on arguments derived from neuroscience, psychology, compu...
Bayesian Decision Theory and Psychophysics
 In Perception as Bayesian Inference
, 1994
"... We argue that Bayesian decision theory provides a good theoretical framework for visual perception. Such a theory involves a likelihood function specifying how the scene generates the image(s), a prior assumption about the scene, and a decision rule to determine the scene interpretation. This is ill ..."
Abstract

Cited by 32 (1 self)
 Add to MetaCart
We argue that Bayesian decision theory provides a good theoretical framework for visual perception. Such a theory involves a likelihood function specifying how the scene generates the image(s), a prior assumption about the scene, and a decision rule to determine the scene interpretation. This is illustrated by describing Bayesian theories for individual visual cues and showing that perceptual biases found in psychophysical experiments can be interpreted as biases towards prior assumptions made by the visual system. We then describe the implications of this framework for the integration of different cues. We argue that the dependence of cues on prior assumptions means that care must be taken to model these dependencies during integration. This suggests that a number of proposed schemes for cue integration, which only allow weak interaction between cues, are not adequate and instead stronger coupling is often required. These theories require the choice of decision rules and we argue that...
Steerable Filters and Local Analysis of Image Structure
, 1992
"... Two paradigms for visual analysis are topdown, starting from highlevel models or information about the image, and bottomup, where little is assumed about the image or objects in it. We explore a local, bottomup approach to image analysis. We develop operators to identify and classify image junct ..."
Abstract

Cited by 29 (0 self)
 Add to MetaCart
Two paradigms for visual analysis are topdown, starting from highlevel models or information about the image, and bottomup, where little is assumed about the image or objects in it. We explore a local, bottomup approach to image analysis. We develop operators to identify and classify image junctions, whichcontain important visual cues for identifying occlusion, transparency, and surface bends. Like the human visual system, we begin with the application of linear filters which are oriented in all possible directions. Wedevelop an efficientway to create an oriented filter of arbitrary orientation by describing it as a linear combination of basis filters. This approach to oriented filtering, which we call steerable filters, offers advantages for analysis as well as computation. We design a variety of steerable filters, including steerable quadrature pairs, which measure local energy. We show applications of these filters in orientation and texture analysis, and image representation and enhanc...
Reflectance Function Estimation and Shape Recovery from Image Sequence of a Rotating Object
 Proceedings of International Conference on Computer Vision
, 1995
"... In this paper we describe a technique for surface recovery of a rotating object illuminated under a collinear light source (where the light source lies on or near the optical axis). We show that the surface reflectance function can be directly estimated from the image sequence without any assumption ..."
Abstract

Cited by 25 (3 self)
 Add to MetaCart
In this paper we describe a technique for surface recovery of a rotating object illuminated under a collinear light source (where the light source lies on or near the optical axis). We show that the surface reflectance function can be directly estimated from the image sequence without any assumption on the reflectance property of the object surface. From the image sequence, the 3D locations of some singular surface points are calculated and their brightness values are extracted for the estimation of the reflectance function. We also show that the surface can be recovered by using shading information in two images of the rotating object. Iteratively using the firstorder Taylor serious approximation and the estimated reflectance function, the depth and orientation of the surface can be recovered simultaneously. The experimental results on real image sequences of both matte and specular surfaces demonstrate that the technique is feasible and robust.
Segmentation from Motion: Combining Gabor and MallatWavelets to Overcome the Aperture and Correspondence Problems
 Pattern Recognition
, 1999
"... A new method for segmentation from motion is presented, which is designed to be part of a general objectrecognition system. The key idea is to integrate information from Gabor and Mallatwavelet transforms of an image sequence to overcome the aperture and the correspondence problem. It is assumed ..."
Abstract

Cited by 15 (0 self)
 Add to MetaCart
A new method for segmentation from motion is presented, which is designed to be part of a general objectrecognition system. The key idea is to integrate information from Gabor and Mallatwavelet transforms of an image sequence to overcome the aperture and the correspondence problem. It is assumed that objects move frontoparallel. Gaborwavelet responses allow accurate estimation of image ow vectors with low spatial resolution. A histogram over this image ow eld is evaluated and its local maxima provide a set of motion hypotheses. These serve to reduce the correspondence problem occurring in utilizing the Mallatwavelet transform, which provides the required high spatial resolution in segmentation. Segmentation reliability is improved by integration over time. The system can segment several small, disconnected, and openworked objects, such as dot patterns. Several examples demonstrate the performance of the system and show that the algorithm behaves reasonably well, even if the as...