The Experts below are selected from a list of 324 Experts worldwide ranked by ideXlab platform

D.a. Wilson - One of the best experts on this subject based on the ideXlab platform.

Sai-kit Yeung - One of the best experts on this subject based on the ideXlab platform.

  • Rotation Invariant Convolutions for 3D Point Clouds Deep Learning
    2019 International Conference on 3D Vision (3DV), 2019
    Co-Authors: Zhiyuan Zhang, David W. Rosen, Sai-kit Yeung
    Abstract:

    Recent progresses in 3D deep learning has shown that it is possible to design special Convolution Operators to consume point cloud data. However, a typical drawback is that rotation invariance is often not guaranteed, resulting in networks that generalizes poorly to arbitrary rotations. In this paper, we introduce a novel Convolution Operator for point clouds that achieves rotation invariance. Our core idea is to use low-level rotation invariant geometric features such as distances and angles to design a Convolution Operator for point cloud learning. The well-known point ordering problem is also addressed by a binning approach seamlessly built into the Convolution. This Convolution Operator then serves as the basic building block of a neural network that is robust to point clouds under 6-DoF transformations such as translation and rotation. Our experiment shows that our method performs with high accuracy in common scene understanding tasks such as object classification and segmentation. Compared to previous and concurrent works, most importantly, our method is able to generalize and achieve consistent results across different scenarios in which training and testing can contain arbitrary rotations. Our implementation is publicly available at our project page.

Stanley H. Chan - One of the best experts on this subject based on the ideXlab platform.

  • ICIP - Constructing a sparse Convolution matrix for shift varying image restoration problems
    2010 IEEE International Conference on Image Processing, 2010
    Co-Authors: Stanley H. Chan
    Abstract:

    Convolution Operator is a linear Operator characterized by a point spread functions (PSF). In classical image restoration problems, the blur is usually shift invariant and so the Convolution Operator can be characterized by one single PSF. This assumption allows one to use fast operations such as Fast Fourier Transform (FFT) to perform a matrix-vector computation efficiently. However, as in most of the video motion deblurring problems, the blur is shift variant and so the matrix-vector multiplication can be difficult to perform. In this paper, we propose an efficient method to construct the Convolution matrix explicitly. We exploit the submatrix structure of the Convolution matrix and systematically assigning values to the nonzero locations. For small to medium sized images, the Convolution matrix gives superior speed than some state-of-art Convolution Operators.

  • Constructing a sparse Convolution matrix for shift varying image restoration problems
    2010 IEEE International Conference on Image Processing, 2010
    Co-Authors: Stanley H. Chan
    Abstract:

    Convolution Operator is a linear Operator characterized by a point spread functions (PSF). In classical image restoration problems, the blur is usually shift invariant and so the Convolution Operator can be characterized by one single PSF. This assumption allows one to use fast operations such as Fast Fourier Transform (FFT) to perform a matrix-vector computation efficiently. However, as in most of the video motion deblurring problems, the blur is shift variant and so the matrix-vector multiplication can be difficult to perform. In this paper, we propose an efficient method to construct the Convolution matrix explicitly. We exploit the submatrix structure of the Convolution matrix and systematically assigning values to the nonzero locations. For small to medium sized images, the Convolution matrix gives superior speed than some state-of-art Convolution Operators.

V. Chellaboina - One of the best experts on this subject based on the ideXlab platform.

  • Induced Convolution Operator norms of linear dynamical systems
    Proceedings of the 1999 American Control Conference (Cat. No. 99CH36251), 1999
    Co-Authors: V. Chellaboina, W.m. Haddad, D.s. Bernstein, D.a. Wilson
    Abstract:

    In this paper we develop explicit formulas for induced Convolution Operator norms and their bounds. These results generalize established induced Operator norms for linear dynamical systems with various classes of input-output signal pairs.

  • Induced Convolution Operator norms for discrete-time linear systems
    Proceedings of the 38th IEEE Conference on Decision and Control (Cat. No.99CH36304), 1999
    Co-Authors: V. Chellaboina, W.m. Haddad, D.s. Bernstein, D.a. Wilson
    Abstract:

    In this paper we develop explicit formulas for induced Convolution Operator norms and their bounds. These results generalize the established induced Operator norms for discrete-time linear systems with various classes of input-output signal pairs.

  • Fixed-order dynamic compensation for linear systems with actuator amplitude and rate saturation constraints
    Proceedings of the 1998 American Control Conference. ACC (IEEE Cat. No.98CH36207), 1998
    Co-Authors: V. Chellaboina, W.m. Haddad
    Abstract:

    We develop fixed-order (i.e., full- and reduced-order) controllers for linear systems with actuator amplitude and rate saturation constraints. The problem is formulated as a multiobjective problem involving a convex combination of an L/sub 1/ norm and the H/sub 2/ norm to capture actuator saturation constraints and closed-loop system performance in the face of exogenous white noise disturbances. The L/sub 1/ Convolution Operator norm considered is induced by bounded amplitude persistent L/sub /spl infin// disturbances and L/sub /spl infin// performance variables involving the actuator amplitude and rate signals. Hence, the peak point-wise-in-time actuator amplitude and actuator rate excursion is guaranteed to be less than the product of the L/sub 1/ Convolution Operator norm and the L/sub /spl infin// disturbance amplitude bound. Application of the proposed framework to the design of multivariable saturation controllers for the control of a bank-to-turn missile is demonstrated.

W.m. Haddad - One of the best experts on this subject based on the ideXlab platform.

  • Induced Convolution Operator norms of linear dynamical systems
    Proceedings of the 1999 American Control Conference (Cat. No. 99CH36251), 1999
    Co-Authors: V. Chellaboina, W.m. Haddad, D.s. Bernstein, D.a. Wilson
    Abstract:

    In this paper we develop explicit formulas for induced Convolution Operator norms and their bounds. These results generalize established induced Operator norms for linear dynamical systems with various classes of input-output signal pairs.

  • Induced Convolution Operator norms for discrete-time linear systems
    Proceedings of the 38th IEEE Conference on Decision and Control (Cat. No.99CH36304), 1999
    Co-Authors: V. Chellaboina, W.m. Haddad, D.s. Bernstein, D.a. Wilson
    Abstract:

    In this paper we develop explicit formulas for induced Convolution Operator norms and their bounds. These results generalize the established induced Operator norms for discrete-time linear systems with various classes of input-output signal pairs.

  • Fixed-order dynamic compensation for linear systems with actuator amplitude and rate saturation constraints
    Proceedings of the 1998 American Control Conference. ACC (IEEE Cat. No.98CH36207), 1998
    Co-Authors: V. Chellaboina, W.m. Haddad
    Abstract:

    We develop fixed-order (i.e., full- and reduced-order) controllers for linear systems with actuator amplitude and rate saturation constraints. The problem is formulated as a multiobjective problem involving a convex combination of an L/sub 1/ norm and the H/sub 2/ norm to capture actuator saturation constraints and closed-loop system performance in the face of exogenous white noise disturbances. The L/sub 1/ Convolution Operator norm considered is induced by bounded amplitude persistent L/sub /spl infin// disturbances and L/sub /spl infin// performance variables involving the actuator amplitude and rate signals. Hence, the peak point-wise-in-time actuator amplitude and actuator rate excursion is guaranteed to be less than the product of the L/sub 1/ Convolution Operator norm and the L/sub /spl infin// disturbance amplitude bound. Application of the proposed framework to the design of multivariable saturation controllers for the control of a bank-to-turn missile is demonstrated.