Learn More
No feature-based vision system can work unless good features can be identiied and tracked from frame to frame. Although tracking itself is by and large a solved problem, selecting features that can be tracked well and correspond to physical points in the world is still hard. We propose a feature selection criterion that is optimal by construction because it(More)
We investigate the properties of a metric between two distributions, the Earth Mover's Distance (EMD), for content-based image retrieval. The EMD is based on the minimal cost that must be paid to transform one distribution into the other, in a precise sense, and was first proposed for certain vision problems by Peleg, Werman, and Rom. For image retrieval,(More)
Received Abstract Inferring scene geometry and camera motion from a stream of images is possible in principle, but is an ill-conditioned problem when the objects are distant with respect to their size. We have developed a factorization method that can overcome this difficulty by recovering shape and motion under orthography without computing depth as an(More)
Bilateral filtering smooths images while preserving edges, by means of a nonlinear combination of nearby image values. The method is noniterative, local, and simple. It combines gray levels or colors based on both their geometric closeness and their photometric similarity, and prefers near values to distant values in both domain and range. In contrast with(More)
The factorization method described in this series of reports requires an algorithm to track the motion of features in an image stream. Given the small inter-frame displacement made possible by the factorization approach, the best tracking method turns out to be the one proposed by Lucas and Kanade in 1981. The method defines the measure of match between(More)
We introduce a new distance between two distributions that we call the Earth Mover's Distance (EMD), which reflects the minimal amount of work that must be performed to transform one distribution into the other by moving " distribution mass " around. This is a special case of the transportation problem from linear optimization, for which efficient(More)
This paper empirically compares nine image dis-similarity measures that are based on distributions of color and texture features summarizing over 1,000 CPU hours of computational experiments. Ground truth is collected via a novel random sampling scheme for color, and via an image partitioning method for texture. Quantitative performance evaluations are(More)
—Because of image sampling, traditional measures of pixel dissimilarity can assign a large value to two corresponding pixels in a stereo pair, even in the absence of noise and other degrading effects. We propose a measure of dissimilarity that is provably insensitive to sampling because it uses the linearly interpolated intensity functions surrounding the(More)
This report describes a two-pass binocular stereo algorithm that is specifically geared towards the detection of depth discontinuities. In the rst pass, introduced in part I of the report, stereo matching is performed independently on each epipolar pair for maximum eeciency. In the second pass, described in part II, disparity information is propagated(More)
In this paper we present a n o vel approach t o t h e problem of navigating through a database of color images. We consider the images as points in a metric space in which w e wish to move around so as to locate image neighborhoods of interest, based on color information. The data base images are mapped to distributions in color space, these distributions(More)