A paraperspective factorization method for shape and motionrecovery

The factorization method, first developed by Tomasi and Kanade (1992), recovers both the shape of an object and its motion from a sequence of images, using many images and tracking many feature points to obtain highly redundant feature position information. The method robustly processes the feature trajectory information using singular value decomposition (SVD), taking advantage of the linear algebraic properties of orthographic projection. However, an orthographic formulation limits the range of motions the method can accommodate. Paraperspective projection, first introduced by Ohta et al. (1981), is a projection model that closely approximates perspective projection by modeling several effects not modeled under orthographic projection, while retaining linear algebraic properties. Our paraperspective factorization method can be applied to a much wider range of motion scenarios, including image sequences containing motion toward the camera and aerial image sequences of terrain taken from a low-altitude airplane     

On Metric Clustering to Minimize the Sum of Radii

Given an n-point metric (P,d) and an integer k>0, we consider the problem of covering P by k balls so as to minimize the sum of the radii of the balls. We present a randomized algorithm that runs in n ^{O(log n⋅log Δ)} time and returns with high probability the optimal solution. Here, Δ is the ratio between the maximum and minimum interpoint distances in the metric space. We also show that the problem is NP-hard, even in metrics induced by weighted planar graphs and in metrics of constant doubling dimension.     

A new layer perovskites Pb2Ga2Nb2O10 and RbPb2Nb2O7: An efficient visible light driven photocatalysts to hydrogen generation

We report here the novel approach to synthesis of layer perovskite photocatalysts, Pb₂Ga₂Nb₂O₁₀ and RbPb₂Nb₂O₇ using solid state route (SSR) and molten salt synthesis (MSS) method. The reported modified MSS method has advantage over conventional SSR method for uniform particle size, well-defined crystal structure, controlled morphology and stoichiometry vis-à-vis photocatalysis. The structural study was performed using X-ray difractometry (XRD) and computation based on density functional theory (DFT). The simulation study showed that both the compounds belong to the Ruddlesden-Popper phase (A′₂A_n−1B_nO_3n+1; n = 2 or 3). The surface morphology of the materials was studied using field emission scanning electron microscope (FESEM) and high resolution transmission electron microscope (HRTEM). The average particles size of perovskites Pb₂Ga₂Nb₂O₁₀ and RbPb₂Nb₂O₇ was in the range 20–40 and 70–90 nm respectively. The efficacy of these materials was studied to particle size and morphology as a visible light driven photocatalyst for the hydrogen generation from H₂S. Electronic band structure with DOS has also been performed for both the materials. Being a stable single-phase ternary-layered oxide perovskites and band gap (2.75 eV) in visible domain, they may have potential applications in electronic devices as well.     

A locally adaptive window for signal matching

This article presents a signal matching algorithm that can select an appropriate window size adaptively so as to obtain both precise and stable estimation of correspondences.Matching two signals by calculating the sum of squared differences (SSD) over a certain window is a basic technique in computer vision. Given the signals and a window, there are two factors that determine the difficulty of obtaining precise matching. The first is the variation of the signal within the window, which must be large enough, relative to noise, that the SSD values exhibit a clear and sharp minimum at the correct disparity. The second factor is the variation of disparity within the window, which must be small enough that signals of corresponding positions are duly compared. These two factors present conflicting requirements to the size of the matching window, since a larger window tends to increase the signal variation, but at the same time tends to include points of different disparity. A window size must be adaptively selected depending on local variations of signal and disparity in order to compute a most-certain estimate of disparity at each point.There has been little work on a systematic method for automatic window-size selection. The major difficulty is that, while the signal variation is measurable from the input, the disparity variation is not, since disparities are what we wish to calculate. We introduce here a statistical model of disparity variation within a window, and employ it to establish a link between the window size and the uncertainty of the computed disparity. This allows us to choose the window size that minimizes uncertainty in the disparity computed at each point. This article presents a theory for the model and the resultant algorithm, together with analytical and experimental results that demonstrate their effectiveness.     

The measurement of highlights in color images

In this paper, we present an approach to color image understanding that accounts for color variations due to highlights and shading. We demonstrate that the reflected light from every point on a dielectric object, such as plastic, can be described as a linear combination of the object color and the highlight color. The colors of all light rays reflected from one object then form a planar cluster in the color space. The shape of this cluster is determined by the object and highlight colors and by the object shape and illumination geometry. We present a method that exploits the difference between object color and highlight color to separate the color of every pixel into a matte component and a highlight component. This generates two intrinsic images, one showing the scene without highlights, and the other one showing only the highlights. The intrinsic images may be a useful tool for a variety of algorithms in computer vision, such as stereo vision, motion analysis, shape from shading, and shape from highlights. Our method combines the analysis of matte and highlight reflection with a sensor model that accounts for camera limitations. This enables us to successfully run our algorithm on real images taken in a laboratory setting. We show and discuss the results.This material is based upon work supported by the National Science Foundation under Grant DCR-8419990 and by the Defense Advanced Research Projects Agency (DOD), ARPA Order No. 4976, monitored by the Air Force Avionics Laboratory under contract F33615-84-K-1520. Any opinions, findings, and conclusions or recommendations expressed in this publication are those of the authors and do not necessarily reflect the views of the National Science Foundation, the Defense Advanced Research Projects Agency, or the US Government.     

Multi-PIE

A close relationship exists between the advancement of face recognition algorithms and the availability of face databases varying factors that affect facial appearance in a controlled manner. The CMU PIE database has been very influential in advancing research in face recognition across pose and illumination. Despite its success the PIE database has several shortcomings: a limited number of subjects, a single recording session and only few expressions captured. To address these issues we collected the CMU Multi-PIE database. It contains 337 subjects, imaged under 15 view points and 19 illumination conditions in up to four recording sessions. In this paper we introduce the database and describe the recording procedure. We furthermore present results from baseline experiments using PCA and LDA classifiers to highlight similarities and differences between PIE and Multi-PIE.