Kernel adaptive filter

About: Kernel adaptive filter is a research topic. Over the lifetime, 8771 publications have been published within this topic receiving 142711 citations.

Rao-Blackwellised particle filter for tracking with application in visual surveillance

Abstract: Particle filters have become popular tools for visual tracking since they do not require the modeling system to be Gaussian and linear However, when applied to a high dimensional state-space, particle filters can be inefficient because a prohibitively large number of samples may be required in order to approximate the underlying density functions with desired accuracy In this paper, by proposing a tracking algorithm based on Rao-Blackwellised particle filter (RBPF), we show how to exploit the analytical relationship between state variables to improve the efficiency and accuracy of a regular particle filter Essentially, we estimate some of the state variables as in a regular particle filter, and the distributions of the remaining variables are updated analytically using an exact filter (Kalman filter in this paper) We discuss how the proposed method can be applied to facilitate the visual tracking task in typical surveillance applications Experiments using both simulated data and real video sequences show that the proposed method results in more accurate and more efficient tracking than a regular particle filter

Adaptive filtering using filter banks

Abstract: This paper derives a theory for adaptive filters which operate on filter bank outputs, here called filter bank adaptive filters (FBAFs). It is shown how the FBAFs are a generalization of transform domain adaptive filters and adaptive filters based on structural subband decompositions. The minimum mean-square error performance and convergence properties of FBAFs are determined as a function of filter bank used. A parametrization for a class of FIR perfect reconstruction filter banks is derived which is used to design FBAF's having optimal error performance given prior knowledge of the application. Simulations are performed to illustrate the derived theory and demonstrate the improved error performance of the FBAFs relative to the LMS algorithm, when prior knowledge is incorporated.

Digital image appearance enhancement and compressibility improvement method and system

Abstract: A method and system for processing a digital image and improving the appearance of the image while enhancing the compressibility of the image. The digital image has a plurality of input pixels. The image processing system has a filter selection mechanism for receiving a filter selection window corresponding to a current input pixel and responsive thereto for generating a filter identifier based on either an edge parameter computed based on the filter selection window or an activity metric computed based on the filter selection window. A filter application unit that is coupled to the filter selection mechanism for receiving the filter identifier and applying a filter identified by the filter identifier to an input pixel window to generate an output pixel is also provided.

NeuMIP: multi-resolution neural materials

Abstract: We propose NeuMIP, a neural method for representing and rendering a variety of material appearances at different scales. Classical prefiltering (mipmapping) methods work well on simple material properties such as diffuse color, but fail to generalize to normals, self-shadowing, fibers or more complex microstructures and reflectances. In this work, we generalize traditional mipmap pyramids to pyramids of neural textures, combined with a fully connected network. We also introduce neural offsets, a novel method which enables rendering materials with intricate parallax effects without any tessellation. This generalizes classical parallax mapping, but is trained without supervision by any explicit heightfield. Neural materials within our system support a 7-dimensional query, including position, incoming and outgoing direction, and the desired filter kernel size. The materials have small storage (on the order of standard mipmapping except with more texture channels), and can be integrated within common Monte-Carlo path tracing systems. We demonstrate our method on a variety of materials, resulting in complex appearance across levels of detail, with accurate parallax, self-shadowing, and other effects.

Ultrasound imaging system and method employing an adaptive filter

Abstract: An ultrasound imaging system is provided with an adaptive filter for transforming an input signal to produce an output signal having one or more desired signal statistics (e.g., signal-to-noise ratio, Gaussian function specification, etc.). The adaptive filter includes a digital filter configured to receive input signals and produce output signals. The adaptive filter exhibits a transfer function H defined by one or more coefficients C. A controller is configured to generate the filter coefficients based upon one or more signal constraints that are provided to the controller by a user and a sample signal that exhibits one or more sample signal statistics and that is communicated to the digital filter. The controller communicates the filter coefficients to the adaptive filter. The filter coefficients cause the adaptive filter to transform input data, based upon the transfer function H(C), to produce output data exhibiting (at least approximately) the one or more desired signal statistics, the desired signal statistics based upon the sample signal statistics and the constraints. Several different coefficient sets may be utilized in the adaptive filter for different object parts (e.g., blood, tissue, etc.) to be imaged. Furthermore, the adaptive filter may be operated by a designer so as to preset the coefficients, periodically initiated by a user/operator to reset the coefficients, and/or automatically initiated by the system, perhaps periodically or upon detection of a certain event, during operation to reset the coefficients.