Results 1  10
of
36
Ordinal Measures for Image Correspondence
, 1998
"... We present ordinal measures of association for image correspondence in the context of stereo. Linear correspondence measures like correlation and the sum of squared difference between intensity distributions are known to be fragile. Ordinal measures which are based on relative ordering of intensity ..."
Abstract

Cited by 86 (0 self)
 Add to MetaCart
We present ordinal measures of association for image correspondence in the context of stereo. Linear correspondence measures like correlation and the sum of squared difference between intensity distributions are known to be fragile. Ordinal measures which are based on relative ordering of intensity values in windows  rank permutations  have demonstrable robustness. By using distance metrics between two rank permutations, ordinal measures are defined. These measures are independent of absolute intensity scale and invariant to monotone transformations of intensity values like gamma variation between images. We have developed simple algorithms for their efficient implementation. Experiments suggest the superiority of ordinal measures over existing techniques under nonideal conditions. These measures serve as a general tool for image matching that are applicable to other vision problems such as motion estimation and texturebased image retrieval. Keywords: Image matching, Stereo, Ordi...
Approximate NView Stereo
 in Proc. European Conf. on Computer Vision
, 2000
"... . This paper introduces a new multiview reconstruction problem called approximate Nview stereo. The goal of this problem is to recover a oneparameter family of volumes that are increasingly tighter supersets of an unknown, arbitrarilyshaped 3D scene. By studying 3D shapes that reproduce the in ..."
Abstract

Cited by 75 (5 self)
 Add to MetaCart
. This paper introduces a new multiview reconstruction problem called approximate Nview stereo. The goal of this problem is to recover a oneparameter family of volumes that are increasingly tighter supersets of an unknown, arbitrarilyshaped 3D scene. By studying 3D shapes that reproduce the input photographs up to a special image transformation called a shuffle transformation,we prove that (1) these shapes can be organized hierarchically into nested supersets of the scene, and (2) they can be computed using a simple algorithm called Approximate Space Carving that is provablycorrect for arbitrary discrete scenes (i.e., for unknown, arbitrarilyshaped Lambertian scenes that are defined by a finite set of voxels and are viewed from N arbitrarilydistributed viewpoints inside or around them). The approach is specifically designed to attack practical reconstruction problems, including (1) recovering shape from images with inaccurate calibration information, and (2) building ...
Stereo and Specular Reflection
 IJCV
, 1998
"... . The problem of accurate depth estimation using stereo in the presence of specular reflection is addressed. Specular reflection, a fundamental and ubiquitous reflection mechanism, is viewpoint dependent and can cause large intensity differences at corresponding points, resulting in significant dept ..."
Abstract

Cited by 27 (2 self)
 Add to MetaCart
(Show Context)
. The problem of accurate depth estimation using stereo in the presence of specular reflection is addressed. Specular reflection, a fundamental and ubiquitous reflection mechanism, is viewpoint dependent and can cause large intensity differences at corresponding points, resulting in significant depth errors. We analyze the physics of specular reflection and the geometry of stereopsis which lead to a relationship between stereo vergence, surface roughness, and the likelihood of a correct match. Given a lower bound on surface roughness, an optimal binocular stereo configuration can be determined which maximizes precision in depth estimation despite specular reflection. However, surface roughness is difficult to estimate in unstructured environments. Therefore, trinocular configurations, independent of surface roughness, are determined such that at each scene point visible to all sensors, at least one stereo pair can produce correct depth. We have developed a simple algorithm to reconstru...
An intensityaugmented ordinal measure for visual correspondence
 In Proc. IEEE CVPR
, 2006
"... Determining the correspondence of image patches is one of the most important problems in Computer Vision. When the intensity space is variant due to several factors such as the camera gain or gamma correction, one needs methods that are robust to such transformations. While the most common assumptio ..."
Abstract

Cited by 15 (3 self)
 Add to MetaCart
(Show Context)
Determining the correspondence of image patches is one of the most important problems in Computer Vision. When the intensity space is variant due to several factors such as the camera gain or gamma correction, one needs methods that are robust to such transformations. While the most common assumption is that of a linear transformation, a more general assumption is that the change is monotonic. Therefore, methods have been developed previously that work on the rankings between different pixels as opposed to the intensities themselves. In this paper, we develop a new matching method that improves upon existing methods by using a combination of intensity and rank information. The method considers the difference in the intensities of the changed pixels in order to achieve greater robustness to Gaussian noise. Furthermore, only uncorrelated order changes are considered, which makes the method robust to changes in a single or a few pixels. These properties make the algorithm quite robust to different types of noise and other artifacts such as camera shake or image compression. Experiments illustrate the potential of the approach in several different applications such as change detection and feature matching. 1.
Ranklets: Orientation Selective NonParametric Features Applied to Face Detection
, 2002
"... We introduce a family of multiscale, orientationselective, nonparametric features ("ranklets") modelled on Haar wavelets. We clarify their relation to the Wilcoxon ranksum test and the rank transform and provide an efficient scheme for computation based on the MannWhitney statistics. Fi ..."
Abstract

Cited by 14 (5 self)
 Add to MetaCart
We introduce a family of multiscale, orientationselective, nonparametric features ("ranklets") modelled on Haar wavelets. We clarify their relation to the Wilcoxon ranksum test and the rank transform and provide an efficient scheme for computation based on the MannWhitney statistics. Finally, we show that ranklets outperform other rank features, Haar wavelets, SNoW and linear SVMs (based on independently published results) in face detection experiments over the 24 045 test images in the MITCBCL database.
A NonParametric Approach to Visual Correspondence
 IEEE Transactions on Pattern Analysis and Machine Intelligence
"... We describe a method for computing visual correspondence based on the local ordering of intensities. Ordering information is robust to outliers and invariant to monotonic intensity distortions such as image gain. Our approach is based on nonparametric measures of association but also accounts for t ..."
Abstract

Cited by 14 (0 self)
 Add to MetaCart
(Show Context)
We describe a method for computing visual correspondence based on the local ordering of intensities. Ordering information is robust to outliers and invariant to monotonic intensity distortions such as image gain. Our approach is based on nonparametric measures of association but also accounts for the spatial variation of disparities. We describe some of the mathematical properties of our algorithms, and demonstrate their utility on both synthetic and real imagery with ground truth. These methods are extremely efficient, and have been used for videorate stereo and motion. 1 Introduction Given two images of the same scene, a pixel in one image corresponds to a pixel in the other if both pixels are projections along lines of sight of the same physical scene element. If the two images are temporally consecutive, then computing correspondence determines motion. If the two images are spatially separated but simultaneous, then computing correspondence determines stereo depth. Areabased ap...
On Occluding Contour Artifacts in Stereo Vision
 Proc. Int. Conf. Computer Vision and Pattern Recognition, IEEE Computer Society, Puerto Rico
, 1997
"... In this paper we study occluding contour artifacts in the areabased stereo matching. These artifacts are false, although highly correlated responses of the matching operator to the occlusion boundary and cause the objects extend beyond their true boundaries in disparity maps. The effect is so stron ..."
Abstract

Cited by 11 (3 self)
 Add to MetaCart
In this paper we study occluding contour artifacts in the areabased stereo matching. These artifacts are false, although highly correlated responses of the matching operator to the occlusion boundary and cause the objects extend beyond their true boundaries in disparity maps. The effect is so strong that it cannot be ignored. Current matching methods do not attempt to avoid the problem. We show what is the physical phenomenon that gives rise to the artifacts and design a matching criterion that accommodates the presence of the occlusions as opposite to methods that identify and remove the artifacts. This approach leads to the problem of measurement contamination studied in statistics. We show that such problem is hard given finite computational resources, unless more independent measurements directly related to occluding contours is available. What can be achieved is the substantial reduction of the artifacts, especially for large matching templates. Reduced artifacts allow for easier...
Motion Estimation using Ordinal Measures
, 1997
"... We present a method for motion estimation using ordinal measures. Ordinal measures are based on relative ordering of intensity values in a image region called rank permutation. While popular measures like the sumof squareddifference (SSD) and normalized correlation (NCC) rely on linearity between ..."
Abstract

Cited by 6 (2 self)
 Add to MetaCart
We present a method for motion estimation using ordinal measures. Ordinal measures are based on relative ordering of intensity values in a image region called rank permutation. While popular measures like the sumof squareddifference (SSD) and normalized correlation (NCC) rely on linearity between corresponding intensity values, ordinal measures only require them to be monontonically related so that rank permutations between corresponding regions are preserved. This property turns out to be very useful for motion estimation in tagged Magnetic Resonance Images. We study the imaging equation involved in two methods of tagging and observe temporal monotonicity in intensity under certain conditions though the tags themselves fade. We compare our method to SSD and NCC in a simulated rotating ring phantom image sequence. We discuss computational issues and present an experiment on a real heart image sequence, which suggests the suitability of our method. 1 Introduction In motion estimatio...
Video Fingerprinting: Features for Duplicate and Similar Video Detection and Querybased Video Retrieval
"... A video “fingerprint ” is a feature extracted from the video that should represent the video compactly, allowing faster search without compromising the retrieval accuracy. Here, we use a keyframe set to represent a video, motivated by the video summarization approach. We experiment with different fe ..."
Abstract

Cited by 3 (1 self)
 Add to MetaCart
(Show Context)
A video “fingerprint ” is a feature extracted from the video that should represent the video compactly, allowing faster search without compromising the retrieval accuracy. Here, we use a keyframe set to represent a video, motivated by the video summarization approach. We experiment with different features to represent each keyframe with the goal of identifying duplicate and similar videos. Various image processing operations like blurring, gamma correction, JPEG compression, and Gaussian noise addition are applied on the individual video frames to generate duplicate videos. Random and bursty frame drop errors of 20%, 40 % and 60 % (over the entire video) are also applied to create more noisy “duplicate ” videos. The similar videos consist of videos with similar content but with varying camera angles, cuts, and idiosyncrasies that occur during successive retakes of a video. Among the feature sets used for comparison, for duplicate video detection, Compact FourierMellin Transform (CFMT) performs the best while for similar video retrieval, Scale Invariant Feature Transform (SIFT) features are found to be better than comparabledimension features. We also address the problem of retrieval of fulllength videos with shorterlength clip queries. For identical feature size, CFMT performs the best for video retrieval. Keywords: video fingerprinting, FourierMellin Transform, SIFT, ordinal features, querybased video retrieval 1.