Results 1  10
of
132
A taxonomy and evaluation of dense twoframe stereo correspondence algorithms
 International Journal of Computer Vision
, 2002
"... Abstract. Stereo matching is one of the most active research areas in computer vision. While a large number of algorithms for stereo correspondence have been developed, relatively little work has been done on characterizing their performance. In this paper, we present a taxonomy of dense, twoframe ..."
Abstract

Cited by 1129 (19 self)
 Add to MetaCart
Abstract. Stereo matching is one of the most active research areas in computer vision. While a large number of algorithms for stereo correspondence have been developed, relatively little work has been done on characterizing their performance. In this paper, we present a taxonomy of dense, twoframe stereo methods. Our taxonomy is designed to assess the different components and design decisions made in individual stereo algorithms. Using this taxonomy, we compare existing stereo methods and present experiments evaluating the performance of many different variants. In order to establish a common software platform and a collection of data sets for easy evaluation, we have designed a standalone, flexible C++ implementation that enables the evaluation of individual components and that can easily be extended to include new algorithms. We have also produced several new multiframe stereo data sets with ground truth and are making both the code and data sets available on the Web. Finally, we include a comparative evaluation of a large set of today’s bestperforming stereo algorithms.
Stereo matching using belief propagation
, 2003
"... In this paper, we formulate the stereo matching problem as a Markov network and solve it using Bayesian belief propagation. The stereo Markov network consists of three coupled Markov random fields that model the following: a smooth field for depth/disparity, a line process for depth discontinuity, ..."
Abstract

Cited by 272 (3 self)
 Add to MetaCart
(Show Context)
In this paper, we formulate the stereo matching problem as a Markov network and solve it using Bayesian belief propagation. The stereo Markov network consists of three coupled Markov random fields that model the following: a smooth field for depth/disparity, a line process for depth discontinuity, and a binary process for occlusion. After eliminating the line process and the binary process by introducing two robust functions, we apply the belief propagation algorithm to obtain the maximum a posteriori (MAP) estimation in the Markov network. Other lowlevel visual cues (e.g., image segmentation) can also be easily incorporated in our stereo model to obtain better stereo results. Experiments demonstrate that our methods are comparable to the stateoftheart stereo algorithms for many test cases.
A MaximumFlow Formulation of the Ncamera Stereo Correspondence Problem
, 1998
"... This paper describes a new algorithm for solving the Ncamera stereo correspondence problem by transforming it into a maximumflow problem. Once solved, the minimumcut associated to the maximumflow yields a disparity surface for the whole image at once. This global approach to stereo analysis provi ..."
Abstract

Cited by 240 (4 self)
 Add to MetaCart
This paper describes a new algorithm for solving the Ncamera stereo correspondence problem by transforming it into a maximumflow problem. Once solved, the minimumcut associated to the maximumflow yields a disparity surface for the whole image at once. This global approach to stereo analysis provides a more accurate and coherent depth map than the traditional linebyline stereo. Moreover, the optimality of the depth surface is guaranteed and can be shown to be a generalization of the dynamic programming approach that is widely used in standard stereo. Results show improved depth estimation as well as better handling of depth discontinuities. While the worst case running time is O(n 2 d 2 log(nd)), the observed average running time is O(n 1:2 d 1:3 ) for an image size of n pixels and depth resolution d. 1 Introduction It is well known that depth related displacements in stereo pairs always occur along lines associated to the camera motion, the epipolar lines. These lines r...
Stereo by Intra and InterScanline Search Using Dynamic Programming
, 1985
"... this paper. Fig. 17 is an isometric plot of the disparity map of Fig. 16 ..."
Abstract

Cited by 228 (6 self)
 Add to MetaCart
this paper. Fig. 17 is an isometric plot of the disparity map of Fig. 16
A maximum likelihood stereo algorithm
 Computer Vision and Image Understanding
, 1996
"... A stereo algorithm is presented that optimizes a maximum likelihood cost function. The maximum likelihood cost function assumes that corresponding features in the left and right images are Normally distributed about a common true value and consists of a weighted squared error term if two features ar ..."
Abstract

Cited by 212 (2 self)
 Add to MetaCart
(Show Context)
A stereo algorithm is presented that optimizes a maximum likelihood cost function. The maximum likelihood cost function assumes that corresponding features in the left and right images are Normally distributed about a common true value and consists of a weighted squared error term if two features are matched or a ( xed) cost if a feature is determined to be occluded. The stereo algorithm nds the set of correspondences that maximize the cost function subject to ordering and uniqueness constraints. The stereo algorithm is independent of the matching primitives. However, for the experiments described in this paper, matching is performed on the individual pixel intensities. Contrary to popular belief, the pixelbased stereo appears to be robust for a variety of images. It also has the advantages of (i) providing a dense disparity map, (ii) requiring no feature extraction and (iii) avoiding the adaptive windowing problem of areabased correlation methods. Because feature extraction and windowing are unnecessary, avery fast implementation is possible. Experimental results reveal that good stereo correspondences can be found using only ordering and uniqueness constraints, i.e. without local smoothness constraints. However, it is shown that the original maximum likelihood stereo algorithm exhibits multiple global minima. The dynamic programming algorithm is guaranteed to nd one, but not necessarily the same one for each epipolar scanline causing erroneous
Advances in Computational Stereo
 IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
, 2003
"... 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 ..."
Abstract

Cited by 163 (2 self)
 Add to MetaCart
(Show Context)
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
Depth Discontinuities by PixeltoPixel Stereo
 International Journal of Computer Vision
, 1996
"... Proceedings of the 1998IEEE International Conference on Computer Vision, Bombay, India An algorithm to detect depth discontinuities from a stereo pair of images is presented. The algorithm matches individual pixels in corresponding scanline pairs while allowing occluded pixels to remain unmatched, t ..."
Abstract

Cited by 150 (4 self)
 Add to MetaCart
(Show Context)
Proceedings of the 1998IEEE International Conference on Computer Vision, Bombay, India An algorithm to detect depth discontinuities from a stereo pair of images is presented. The algorithm matches individual pixels in corresponding scanline pairs while allowing occluded pixels to remain unmatched, then propagates the information between scanlines by means of a fast postprocessor. The algorithm handles large untextured regions, uses a measure of pixel dissimilarity that is insensitive to image sampling, and prunes bad search nodes to increase the speed of dynamic programming. The computation is relatively fast, taking about 1.5 microseconds per pixel per disparity on a workstation. Approximate disparity mapsand precise depth discontinuities (along both horizontal and vertical boundaries) are shown for five stereo images containing textured, untextured, frontoparallel, and slanted objects. 1 Introduction Cartoon artists have known the perceptual importance of depth discontinuities for...
Large Occlusion Stereo
"... A method for solving the stereo matching problem in the presence of large occlusion is presented. A data structure — the disparity space image — is defined to facilitate the description of the effects of occlusion on the stereo matching process and in particular on dynamic programming (DP) solutions ..."
Abstract

Cited by 119 (0 self)
 Add to MetaCart
(Show Context)
A method for solving the stereo matching problem in the presence of large occlusion is presented. A data structure — the disparity space image — is defined to facilitate the description of the effects of occlusion on the stereo matching process and in particular on dynamic programming (DP) solutions that find matches and occlusions simultaneously. We significantly improve upon existing DP stereo matching methods by showing that while some cost must be assigned to unmatched pixels, sensitivity to occlusioncost and algorithmic complexity can be significantly reduced when highlyreliable matches, or ground control points, are incorporated into the matching process. The use of ground control points eliminates both the need for biasing the process towards a smooth solution and the task of selecting critical prior probabilities describing image formation. Finally, we describe how the detection of intensity edges can be used to bias the recovered solution such that occlusion boundaries will tend to be proposed along such edges, reflecting the observation that occlusion boundaries usually cause intensity discontinuities.
Multiway cut for stereo and motion with slanted surfaces
 In International Conference on Computer Vision
, 1999
"... Slanted surfaces pose a problem for correspondence algorithms utilizing search because of the greatly increased number of possibilities, when compared with frontoparallel surfaces. In this paper we propose an algorithm to compute correspondence between stereo images or between frames of a motionsequ ..."
Abstract

Cited by 119 (2 self)
 Add to MetaCart
Slanted surfaces pose a problem for correspondence algorithms utilizing search because of the greatly increased number of possibilities, when compared with frontoparallel surfaces. In this paper we propose an algorithm to compute correspondence between stereo images or between frames of a motionsequence by minimizingan energy functional that accounts for slanted surfaces. The energy is minimized in a greedy strategy that alternates between segmenting the image into a number of nonoverlapping regions (using the multiwaycut algorithm of Boykov, Veksler, and Zabih) and finding the affine parameters describing the displacement function of each region. A followup step enables the algorithm to escape local minima due to oversegmentation. Experiments on real images show the algorithm’s ability to find an accurate segmentation and displacement map, as well as discontinuities and creases, from a wide variety of stereo and motion imagery. 1