The Experts below are selected from a list of 237 Experts worldwide ranked by ideXlab platform

Rama Chellappa - One of the best experts on this subject based on the ideXlab platform.

  • what is the range of surface reconstructions from a gradient field
    Lecture Notes in Computer Science, 2006
    Co-Authors: Amit Agrawal, Ramesh Raskar, Rama Chellappa
    Abstract:

    We propose a generalized equation to represent a continuum of surface reconstruction solutions of a given non-integrable gradient field. We show that common approaches such as Poisson solver and Frankot-Chellappa algorithm are special cases of this generalized equation. For a N x N pixel grid, the subspace of all integrable gradient fields is of dimension N 2 - 1. Our framework can be applied to derive a range of meaningful surface reconstructions from this high dimensional space. The key observation is that the range of solutions is related to the degree of anisotropy in applying weights to the gradients in the integration process. While common approaches use isotropic weights, we show that by using a progression of spatially varying anisotropic weights, we can achieve significant improvement in reconstructions. We propose (a) α-surfaces using binary weights, where the parameter a allows trade off between smoothness and robustness, (b) M-estimators and edge preserving regularization using continuous weights and (c) Diffusion using affine transformation of gradients. We provide results on photometric stereo, compare with previous approaches and show that anisotropic treatment discounts noise while recovering salient features in reconstructions.

  • face recognition from video a condensation approach
    IEEE International Conference on Automatic Face and Gesture Recognition, 2002
    Co-Authors: Shaohua Zhou, V Krueger, Rama Chellappa
    Abstract:

    The aim of this work is to investigate how to exploit the temporal information in a video sequence for the task of face recognition. Following the approach in (Li and Chellappa, 2000), we propose a probabilistic model parameterized by a tracking state vector and a recognizing identity variable, simultaneously characterizing the kinematics and identity of humans. We then invoke a CONDENSATION (Isard and Blake, 1996) approach to provide a numerical solution to the model. Once the joint posterior distribution of the state vector and the identity variable is estimated, we marginalize it over the state vector to yield a robust estimate of the posterior distribution of the identity variable. Due to the propagation of identity and dynamics, a degeneracy in the posterior distribution of the identity variable is achieved to give improved recognition. This evolving behavior is characterized using changes in entropy. The effectiveness of this approach is illustrated using experimental results on low-resolution video data.

  • Face Recognition from Video: A CONDENSATION Approach
    2002
    Co-Authors: Shaohua Zhou, V Krueger, Rama Chellappa
    Abstract:

    The aim of this work is to investigate how to exploit the temporal information in a video sequence for the task of face recognition. Inspired by Li and Chellappa's approach [11], we propose a probabilistic model parameterized by a tracking state vector and a recognizing identity variable, simultaneously characterizing the dynamics and identity of humans. We then invoke a CONDENSATION [8] approach to provide a numerical solution to the model. Once the joint posterior distribution of state vector and identity variable is estimated, we marginalize it over the state vector to yield a robust estimate of the posterior distribution of identity variable. Due to the propagation of identity and dynamics, a degeneracy in the posterior distribution of identity variable is achieved to give improved recognition. This evolving behavior is characterized using changes in entropy. The effectiveness of this approach is illustrated using experimental results on low-resolution video data

  • image stabilization and mosaicking using the overlapped basis optical flow field
    International Conference on Image Processing, 1997
    Co-Authors: S Srinivasan, Rama Chellappa
    Abstract:

    Image stabilization and image mosaicking are fundamental image sequence operations that compensate for camera motion. Stabilization is a precursor to background deletion, region of interest extraction, motion discontinuity estimation and video compression. The effectiveness of an end-to-end algorithm is closely tied to the stabilization accuracy of the input sequence, which in turn depends upon (i) the accuracy of the estimated motion in the scene, (ii) the choice and compliance of the global motion model and (iii) the camera calibration. We deal with (i) and demonstrate the merits of a robust technique for computing optical flow, using overlapped basis functions proposed by Srinivasan and Chellappa (see CAR-TR-845, Univ. of Maryland, 1996). In this technique, we regularize the ill-conditioned gradient constraint equation by modeling optical flow as a linear combination of an overlapped set of basis functions. The solution, which can be shown to be optimal, is obtained by a numerically stable sparse matrix inversion, giving a reliable flow field estimate over a large fraction of the frame. We employ an iterated least squares method for consolidating the local model parameters into a global model, for which we choose a six parameter affine transformation. We argue that our flow field model offers a higher accuracy and robustness than conventional optical flow techniques, and is well suited for image stabilization and mosaicking.

  • Markov Random Field Models in Image Processing
    1995
    Co-Authors: Rama Chellappa, Anand Rangarajan
    Abstract:

    INTRODUCTION Markov random field models have become useful in several areas of image processing. The success of Markov random fields (MRFs) can be attributed to the fact that they give rise to good, flexible, stochastic image models. The goal of image modeling is to find an adequate representation of the intensity distribution of a given image. What is adequate often depends on the task at hand and MRF image models have been versatile enough to be applied in the areas of image and texture synthesis (Chellappa and Kashyap, 1985), image compression, restoration (Geman and Geman, 1984), tomographic reconstruction (Geman and Graffigne, 1987), image and texture segmentation (Rangarajan et al., 1991), texture classification, (Derin and Elliott, 1987), and surface reconstruction (Geiger and Girosi, 1991). Our aim is to highlight the central ideas of this field using illustrative examples and provide pointers to the many applications. A guiding insight underlying most of the work on M

Ramesh Raskar - One of the best experts on this subject based on the ideXlab platform.

  • what is the range of surface reconstructions from a gradient field
    Lecture Notes in Computer Science, 2006
    Co-Authors: Amit Agrawal, Ramesh Raskar, Rama Chellappa
    Abstract:

    We propose a generalized equation to represent a continuum of surface reconstruction solutions of a given non-integrable gradient field. We show that common approaches such as Poisson solver and Frankot-Chellappa algorithm are special cases of this generalized equation. For a N x N pixel grid, the subspace of all integrable gradient fields is of dimension N 2 - 1. Our framework can be applied to derive a range of meaningful surface reconstructions from this high dimensional space. The key observation is that the range of solutions is related to the degree of anisotropy in applying weights to the gradients in the integration process. While common approaches use isotropic weights, we show that by using a progression of spatially varying anisotropic weights, we can achieve significant improvement in reconstructions. We propose (a) α-surfaces using binary weights, where the parameter a allows trade off between smoothness and robustness, (b) M-estimators and edge preserving regularization using continuous weights and (c) Diffusion using affine transformation of gradients. We provide results on photometric stereo, compare with previous approaches and show that anisotropic treatment discounts noise while recovering salient features in reconstructions.

  • What is the Range of Surface Reconstructions from a Gradient Field?
    2006
    Co-Authors: Reconstructions From Graadient A Field, Amit Agrawal, Ramesh Raskar
    Abstract:

    We propose a generalized equation to represent a continuum of surface reconstruction solutions of a given non-integrable gradient field. We show that common approaches such as Poisson solver and Frankot-Chellappa algorithm are special cases of this generalized quation. For a N x N pixel grid, the subspace of all integrable gradient fields is of dimension N2-1. Our framework can be applied to derive a range of meaningful surface reconstructions from this high dimensional space. The key observation is that the range of solutions is related to the degree of anisotropy in applying weights to the gradients in the integration process. While common approaches use isotropic weights, we show that by using a progression of spatially varying anisotropic weights, we can achieve significant improvement in reconstructions. We propose (a) a-surfaces using binary weights, where the parameter a allos trade off between smoothness and robustness, (b) M-estimators and edge preserving regularization using continuous weights and (c) Diffusion using affine transformation of gradients. We provide results on photometric stereo, compare with previous approaches and show that anisotrpoic treatment discounts noise while recovering salient features in reconstructions

  • Gradient Field?
    2006
    Co-Authors: Reconstructions From Graadient A Field, Amit Agrawal, Ramesh Raskar
    Abstract:

    We propose a generalized equation to represent a continuum of surface reconstruction solutions of a given non-integrable gradient field. We show that common approaches such as Poisson solver and Frankot-Chellappa algorithm are special cases of this generalized quation. For a N x N pixel grid, the subspace of all integrable gradient fields is of dimension N2-1. Our framework can be applied to derive a range of meaningful surface reconstructions from this high dimensional space. The key observation is that the range of solutions is related to the degree of anisotropy in applying weights to the gradients in the integration process. While common approaches use isotropic weights, we show that by using a progression of spatially varying anisotropic weights, we can achieve significant improvement in reconstructions. We propose (a) a-surfaces using binary weights, where the parameter a allos trade off between smoothness and robustness, (b) M-estimators and edge preserving regularization using continuous weights and (c) Diffusion using affine transformation of gradients. We provide results on photometric stereo, compare with previous approaches and show that anisotrpoic treatment discounts noise while recovering salient features in reconstructions

Amit Agrawal - One of the best experts on this subject based on the ideXlab platform.

  • what is the range of surface reconstructions from a gradient field
    Lecture Notes in Computer Science, 2006
    Co-Authors: Amit Agrawal, Ramesh Raskar, Rama Chellappa
    Abstract:

    We propose a generalized equation to represent a continuum of surface reconstruction solutions of a given non-integrable gradient field. We show that common approaches such as Poisson solver and Frankot-Chellappa algorithm are special cases of this generalized equation. For a N x N pixel grid, the subspace of all integrable gradient fields is of dimension N 2 - 1. Our framework can be applied to derive a range of meaningful surface reconstructions from this high dimensional space. The key observation is that the range of solutions is related to the degree of anisotropy in applying weights to the gradients in the integration process. While common approaches use isotropic weights, we show that by using a progression of spatially varying anisotropic weights, we can achieve significant improvement in reconstructions. We propose (a) α-surfaces using binary weights, where the parameter a allows trade off between smoothness and robustness, (b) M-estimators and edge preserving regularization using continuous weights and (c) Diffusion using affine transformation of gradients. We provide results on photometric stereo, compare with previous approaches and show that anisotropic treatment discounts noise while recovering salient features in reconstructions.

  • What is the Range of Surface Reconstructions from a Gradient Field?
    2006
    Co-Authors: Reconstructions From Graadient A Field, Amit Agrawal, Ramesh Raskar
    Abstract:

    We propose a generalized equation to represent a continuum of surface reconstruction solutions of a given non-integrable gradient field. We show that common approaches such as Poisson solver and Frankot-Chellappa algorithm are special cases of this generalized quation. For a N x N pixel grid, the subspace of all integrable gradient fields is of dimension N2-1. Our framework can be applied to derive a range of meaningful surface reconstructions from this high dimensional space. The key observation is that the range of solutions is related to the degree of anisotropy in applying weights to the gradients in the integration process. While common approaches use isotropic weights, we show that by using a progression of spatially varying anisotropic weights, we can achieve significant improvement in reconstructions. We propose (a) a-surfaces using binary weights, where the parameter a allos trade off between smoothness and robustness, (b) M-estimators and edge preserving regularization using continuous weights and (c) Diffusion using affine transformation of gradients. We provide results on photometric stereo, compare with previous approaches and show that anisotrpoic treatment discounts noise while recovering salient features in reconstructions

  • Gradient Field?
    2006
    Co-Authors: Reconstructions From Graadient A Field, Amit Agrawal, Ramesh Raskar
    Abstract:

    We propose a generalized equation to represent a continuum of surface reconstruction solutions of a given non-integrable gradient field. We show that common approaches such as Poisson solver and Frankot-Chellappa algorithm are special cases of this generalized quation. For a N x N pixel grid, the subspace of all integrable gradient fields is of dimension N2-1. Our framework can be applied to derive a range of meaningful surface reconstructions from this high dimensional space. The key observation is that the range of solutions is related to the degree of anisotropy in applying weights to the gradients in the integration process. While common approaches use isotropic weights, we show that by using a progression of spatially varying anisotropic weights, we can achieve significant improvement in reconstructions. We propose (a) a-surfaces using binary weights, where the parameter a allos trade off between smoothness and robustness, (b) M-estimators and edge preserving regularization using continuous weights and (c) Diffusion using affine transformation of gradients. We provide results on photometric stereo, compare with previous approaches and show that anisotrpoic treatment discounts noise while recovering salient features in reconstructions

Gerda Kamberova - One of the best experts on this subject based on the ideXlab platform.

  • Geometric Integrability and Consistency of 3D Point Clouds
    2007 IEEE 11th International Conference on Computer Vision, 2007
    Co-Authors: George Kamberov, Gerda Kamberova
    Abstract:

    Numerous applications processing 3D point data will gain from the ability to estimate reliably normals and differential geometric properties. Normal estimates are notoriously noisy, the errors propagate and may lead to flawed, inaccurate, and inconsistent curvature estimates. Frankot-Chellappa introduced the use of integrability constraints in normal estimation. Their approach deals with graphs z = f(x,y)- We present a newly discovered general orientability constraint (GOC) for 3D point clouds sampled from general surfaces, not just graphs. It provides a tool to quantify the confidence in the estimation of normals, topology, and geometry from a point cloud. Furthermore, similarly to the Frankot-Chellappa constraint, the GOC can be used directly to extract the topology and the geometry of the manifolds underlying 3D point clouds. As an illustration we describe an automatic Cloud-to-Geometry pipeline which exploits the GOC.

  • Orientation Integrability and Consistency of 3D Cloud Geometry 1
    2007
    Co-Authors: George Kamberov, Gerda Kamberova
    Abstract:

    Numerous applications processing 3D point data will gain from the ability to estimate reliably normals and differential geometric properties encoding curvature. In general, normal estimation is notoriously unreliable, the errors propagate and lead to unreliable curvature estimates. Frankot-Chellappa introduced the use of integrability constraints in normal estimation. Their approach deals with graphs z = f(x, y). We present a newly discovered General Orientability Constraint (GOC) for 3D point clouds sampled from general scenes. It provides a tool to quantify the confidence in the estimation of normals, topology, and geometry from a point cloud. The GOC is used in the development of an automatic Cloud-to-Geometry pipeline (C2G) which takes as input an unorganized 3D point cloud and outputs a point-based reconstruction of the scene geometry. Each point is equipped with a normal and a neighborhood in terms of surface distance. The scene is segmented into 0D,1D, and 2D sub-manifold components. Differential geometric properties are estimated at each surface point.

Anand Rangarajan - One of the best experts on this subject based on the ideXlab platform.

  • Markov Random Field Models in Image Processing
    1995
    Co-Authors: Rama Chellappa, Anand Rangarajan
    Abstract:

    INTRODUCTION Markov random field models have become useful in several areas of image processing. The success of Markov random fields (MRFs) can be attributed to the fact that they give rise to good, flexible, stochastic image models. The goal of image modeling is to find an adequate representation of the intensity distribution of a given image. What is adequate often depends on the task at hand and MRF image models have been versatile enough to be applied in the areas of image and texture synthesis (Chellappa and Kashyap, 1985), image compression, restoration (Geman and Geman, 1984), tomographic reconstruction (Geman and Graffigne, 1987), image and texture segmentation (Rangarajan et al., 1991), texture classification, (Derin and Elliott, 1987), and surface reconstruction (Geiger and Girosi, 1991). Our aim is to highlight the central ideas of this field using illustrative examples and provide pointers to the many applications. A guiding insight underlying most of the work on M