Parallel Computer Vision Algorithms for Graphics Processing Units

La evolución de los teléfonos móviles inteligentes, dotados de cámaras digitales, está provocando una creciente demanda de aplicaciones cada vez más complejas que necesitan algoritmos de visión artificial en tiempo real; puesto que el tamaño de las señales de vídeo no hace sino aumentar y en cambio el rendimiento de los procesadores de un solo núcleo se ha estancado, los nuevos algoritmos que se diseñen para visión artificial han de ser paralelos para poder ejecutarse en múltiples procesadores y ser computacionalmente escalables. Una de las clases de procesadores más interesantes en la actualidad se encuentra en las tarjetas gráficas (GPU), que son dispositivos que ofrecen un alto grado de paralelismo, un excelente rendimiento numérico y una creciente versatilidad, lo que los hace interesantes para llevar a cabo computación científica. En esta tesis se exploran dos aplicaciones de visión artificial que revisten una gran complejidad computacional y no pueden ser ejecutadas en tiempo real empleando procesadores tradicionales. En cambio, como se demuestra en esta tesis, la paralelización de las distintas subtareas y su implementación sobre una GPU arrojan los resultados deseados de ejecución con tasas de refresco interactivas. Asimismo, se propone una técnica para la evaluación rápida de funciones de complejidad arbitraria especialmente indicada para su uso en una GPU. En primer lugar se estudia la aplicación de técnicas de síntesis de imágenes virtuales a partir de únicamente dos cámaras lejanas y no paralelas—en contraste con la configuración habitual en TV 3D de cámaras cercanas y paralelas—con información de color y profundidad. Empleando filtros de mediana modificados para la elaboración de un mapa de profundidad virtual y proyecciones inversas, se comprueba que estas técnicas son adecuadas para una libre elección del punto de vista. Además, se demuestra que la codificación de la información de profundidad con respecto a un sistema de referencia global es sumamente perjudicial y debería ser evitada. Por otro lado se propone un sistema de detección de objetos móviles basado en técnicas de estimación de densidad con funciones locales. Este tipo de técnicas es muy adecuada para el modelado de escenas complejas con fondos multimodales, pero ha recibido poco uso debido a su gran complejidad computacional. El sistema propuesto, implementado en tiempo real sobre una GPU, incluye propuestas para la estimación dinámica de los anchos de banda de las funciones locales, actualización selectiva del modelo de fondo, actualización de la posición de las muestras de referencia del modelo de primer plano empleando un filtro de partículas multirregión y selección automática de regiones de interés para reducir el coste computacional. Los resultados, evaluados sobre diversas bases de datos y comparados con otros algoritmos del estado del arte, demuestran la gran versatilidad y calidad de la propuesta. Finalmente se propone un método para la aproximación de funciones arbitrarias empleando funciones continuas lineales a tramos, especialmente indicada para su implementación en una GPU mediante el uso de las unidades de filtraje de texturas, normalmente no utilizadas para cómputo numérico. La propuesta incluye un riguroso análisis matemático del error cometido en la aproximación en función del número de muestras empleadas, así como un método para la obtención de una partición cuasióptima del dominio de la función para minimizar el error. ABSTRACT The evolution of smartphones, all equipped with digital cameras, is driving a growing demand for ever more complex applications that need to rely on real-time computer vision algorithms. However, video signals are only increasing in size, whereas the performance of single-core processors has somewhat stagnated in the past few years. Consequently, new computer vision algorithms will need to be parallel to run on multiple processors and be computationally scalable. One of the most promising classes of processors nowadays can be found in graphics processing units (GPU). These are devices offering a high parallelism degree, excellent numerical performance and increasing versatility, which makes them interesting to run scientific computations. In this thesis, we explore two computer vision applications with a high computational complexity that precludes them from running in real time on traditional uniprocessors. However, we show that by parallelizing subtasks and implementing them on a GPU, both applications attain their goals of running at interactive frame rates. In addition, we propose a technique for fast evaluation of arbitrarily complex functions, specially designed for GPU implementation. First, we explore the application of depth-image–based rendering techniques to the unusual configuration of two convergent, wide baseline cameras, in contrast to the usual configuration used in 3D TV, which are narrow baseline, parallel cameras. By using a backward mapping approach with a depth inpainting scheme based on median filters, we show that these techniques are adequate for free viewpoint video applications. In addition, we show that referring depth information to a global reference system is ill-advised and should be avoided. Then, we propose a background subtraction system based on kernel density estimation techniques. These techniques are very adequate for modelling complex scenes featuring multimodal backgrounds, but have not been so popular due to their huge computational and memory complexity. The proposed system, implemented in real time on a GPU, features novel proposals for dynamic kernel bandwidth estimation for the background model, selective update of the background model, update of the position of reference samples of the foreground model using a multi-region particle filter, and automatic selection of regions of interest to reduce computational cost. The results, evaluated on several databases and compared to other state-of-the-art algorithms, demonstrate the high quality and versatility of our proposal. Finally, we propose a general method for the approximation of arbitrarily complex functions using continuous piecewise linear functions, specially formulated for GPU implementation by leveraging their texture filtering units, normally unused for numerical computation. Our proposal features a rigorous mathematical analysis of the approximation error in function of the number of samples, as well as a method to obtain a suboptimal partition of the domain of the function to minimize approximation error.

ParAlign: a parallel sequence alignment algorithm for rapid and sensitive database searches

There is a need for faster and more sensitive algorithms for sequence similarity searching in view of the rapidly increasing amounts of genomic sequence data available. Parallel processing capabilities in the form of the single instruction, multiple data (SIMD) technology are now available in common microprocessors and enable a single microprocessor to perform many operations in parallel. The ParAlign algorithm has been specifically designed to take advantage of this technology. The new algorithm initially exploits parallelism to perform a very rapid computation of the exact optimal ungapped alignment score for all diagonals in the alignment matrix. Then, a novel heuristic is employed to compute an approximate score of a gapped alignment by combining the scores of several diagonals. This approximate score is used to select the most interesting database sequences for a subsequent Smith–Waterman alignment, which is also parallelised. The resulting method represents a substantial improvement compared to existing heuristics. The sensitivity and specificity of ParAlign was found to be as good as Smith–Waterman implementations when the same method for computing the statistical significance of the matches was used. In terms of speed, only the significantly less sensitive NCBI BLAST 2 program was found to outperform the new approach. Online searches are available at http://dna.uio.no/search/

Parallel human genome analysis: microarray-based expression monitoring of 1000 genes.

Microarrays containing 1046 human cDNAs of unknown sequence were printed on glass with high-speed robotics. These 1.0-cm2 DNA "chips" were used to quantitatively monitor differential expression of the cognate human genes using a highly sensitive two-color hybridization assay. Array elements that displayed differential expression patterns under given experimental conditions were characterized by sequencing. The identification of known and novel heat shock and phorbol ester-regulated genes in human T cells demonstrates the sensitivity of the assay. Parallel gene analysis with microarrays provides a rapid and efficient method for large-scale human gene discovery.

Sequential and parallel synchronous alternating iterative methods

The so-called parallel multisplitting nonstationary iterative Model A was introduced by Bru, Elsner, and Neumann [Linear Algebra and its Applications 103:175-192 (1988)] for solving a nonsingular linear system Ax = b using a weak nonnegative multisplitting of the first type. In this paper new results are introduced when A is a monotone matrix using a weak nonnegative multisplitting of the second type and when A is a symmetric positive definite matrix using a P -regular multisplitting. Also, nonstationary alternating iterative methods are studied. Finally, combining Model A and alternating iterative methods, two new models of parallel multisplitting nonstationary iterations are introduced. When matrix A is monotone and the multisplittings are weak nonnegative of the first or of the second type, both models lead to convergent schemes. Also, when matrix A is symmetric positive definite and the multisplittings are P -regular, the schemes are also convergent.

Coreferentiality: A New Method for the Hypothesis-Based Analysis of Phenotypes Characterized by Multivariate Data

Many multifactorial biologic effects, particularly in the context of complex human diseases, are still poorly understood. At the same time, the systematic acquisition of multivariate data has become increasingly easy. The use of such data to analyze and model complex phenotypes, however, remains a challenge. Here, a new analytic approach is described, termed coreferentiality, together with an appropriate statistical test. Coreferentiality is the indirect relation of two variables of functional interest in respect to whether they parallel each other in their respective relatedness to multivariate reference data, which can be informative for a complex effect or phenotype. It is shown that the power of coreferentiality testing is comparable to multiple regression analysis, sufficient even when reference data are informative only to a relatively small extent of 2.5%, and clearly exceeding the power of simple bivariate correlation testing. Thus, coreferentiality testing uses the increased power of multivariate analysis, however, in order to address a more straightforward interpretable bivariate relatedness. Systematic application of this approach could substantially improve the analysis and modeling of complex phenotypes, particularly in the context of human study where addressing functional hypotheses by direct experimentation is often difficult.

The pocket lawyer, or self-conveyancer : containing all the most useful forms, rendered so plain, that every man can draw any instrument of writing, wihout the assistance of an attorney ; in a method entirely new.

Text, except t.-p. and index, runs parallel with back of cover.

A new and easy method of learning Hebrew without points. : To which is annex'd, by way of praxis, The book of Proverbs, divided according to the metre: with the masoretical reading in Roman letters, the interlinear version of Santes Pagninus, &c. A grammatical analysis, and short notes critical and explanatory ... /

Errata: p. [2]-[3] at end.

A Kinetic Vlasov Model for Plasma Simulation Using Discontinuous Galerkin Method on Many-Core Architectures

Thesis (Ph.D.)--University of Washington, 2016-03

A parallel implementation of the lattice solid model for the simulation of rock mechanics and earthquake dynamics

The Lattice Solid Model has been used successfully as a virtual laboratory to simulate fracturing of rocks, the dynamics of faults, earthquakes and gouge processes. However, results from those simulations show that in order to make the next step towards more realistic experiments it will be necessary to use models containing a significantly larger number of particles than current models. Thus, those simulations will require a greatly increased amount of computational resources. Whereas the computing power provided by single processors can be expected to increase according to Moore's law, i.e., to double every 18-24 months, parallel computers can provide significantly larger computing power today. In order to make this computing power available for the simulation of the microphysics of earthquakes, a parallel version of the Lattice Solid Model has been implemented. Benchmarks using large models with several millions of particles have shown that the parallel implementation of the Lattice Solid Model can achieve a high parallel-efficiency of about 80% for large numbers of processors on different computer architectures.

Focused, eight-element transceive phased array coil for parallel magnetic resonance imaging of the chest-theoretical considerations

A new transceive system for chest imaging for MRI applications is presented. A focused, eight-element transceive torso phased array coil is designed to investigate transmitting a focused radiofrequency field deep within the torso and to enhance signal homogeneity in the heart region. The system is used in conjunction with the SENSE reconstruction technique to enable focused parallel imaging. A hybrid finite-difference-time-domain/method-of-moments method is used to accurately predict the radiofrequency behavior inside the human torso. The simulation results reported herein demonstrate the feasibility of the design concept, which shows that radiofrequency field focusing with SENSE reconstruction is theoretically achievable. (c) 2005 Wiley-Liss, Inc.

Multiple-acquisition parallel imaging combined with a transceive array for the amelioration of high-field RF distortion: a modeling study

A new method for ameliorating high-field image distortion caused by radio frequency/tissue interaction is presented and modeled, The proposed method uses, but is not restricted to, a shielded four-element transceive phased array coil and involves performing two separate scans of the same slice with each scan using different excitations during transmission. By optimizing the amplitudes and phases for each scan, antipodal signal profiles can be obtained, and by combining both images together, the image distortion can be reduced several-fold. A hybrid finite-difference time-domain/method-of-moments method is used to theoretically demonstrate the method and also to predict the radio frequency behavior inside the human head. in addition, the proposed method is used in conjunction with the GRAPPA reconstruction technique to enable rapid imaging. Simulation results reported herein for IIT (470 MHz) brain imaging applications demonstrate the feasibility of the concept where multiple acquisitions using parallel imaging elements with GRAPPA reconstruction results in improved image quality. (c) 2006 Wiley Periodicals, Inc.

Parallel 3D Simulation of a Fault Gouge using the Lattice Solid Model

Despite the insight gained from 2-D particle models, and given that the dynamics of crustal faults occur in 3-D space, the question remains, how do the 3-D fault gouge dynamics differ from those in 2-D? Traditionally, 2-D modeling has been preferred over 3-D simulations because of the computational cost of solving 3-D problems. However, modern high performance computing architectures, combined with a parallel implementation of the Lattice Solid Model (LSM), provide the opportunity to explore 3-D fault micro-mechanics and to advance understanding of effective constitutive relations of fault gouge layers. In this paper, macroscopic friction values from 2-D and 3-D LSM simulations, performed on an SGI Altix 3700 super-cluster, are compared. Two rectangular elastic blocks of bonded particles, with a rough fault plane and separated by a region of randomly sized non-bonded gouge particles, are sheared in opposite directions by normally-loaded driving plates. The results demonstrate that the gouge particles in the 3-D models undergo significant out-of-plane motion during shear. The 3-D models also exhibit a higher mean macroscopic friction than the 2-D models for varying values of interparticle friction. 2-D LSM gouge models have previously been shown to exhibit accelerating energy release in simulated earthquake cycles, supporting the Critical Point hypothesis. The 3-D models are shown to also display accelerating energy release, and good fits of power law time-to-failure functions to the cumulative energy release are obtained.

Optimum switching point assessment of parallel braking resistor and serial current limiter for power system stability enhancement

A new control algorithm using parallel braking resistor (BR) and serial fault current limiter (FCL) for power system transient stability enhancement is presented in this paper. The proposed control algorithm can prevent transient instability during first swing by immediately taking away the transient energy gained in faulted period. It can also reduce generator oscillation time and efficiently make system back to the post-fault equilibrium. The algorithm is based on a new system energy function based method to choose optimal switching point. The parallel BR and serial FCL resistor can be switched at the calculated optimal point to get the best control result. This method allows optimum dissipation of the transient energy caused by disturbance so to make system back to equilibrium in minimum time. Case studies are given to verify the efficiency and effectiveness of this new control algorithm.

Parallel implementation of image segmentation algorithms on a network of transputers

Image segmentation is one of the most computationally intensive operations in image processing and computer vision. This is because a large volume of data is involved and many different features have to be extracted from the image data. This thesis is concerned with the investigation of practical issues related to the implementation of several classes of image segmentation algorithms on parallel architectures. The Transputer is used as the basic building block of hardware architectures and Occam is used as the programming language. The segmentation methods chosen for implementation are convolution, for edge-based segmentation; the Split and Merge algorithm for segmenting non-textured regions; and the Granlund method for segmentation of textured images. Three different convolution methods have been implemented. The direct method of convolution, carried out in the spatial domain, uses the array architecture. The other two methods, based on convolution in the frequency domain, require the use of the two-dimensional Fourier transform. Parallel implementations of two different Fast Fourier Transform algorithms have been developed, incorporating original solutions. For the Row-Column method the array architecture has been adopted, and for the Vector-Radix method, the pyramid architecture. The texture segmentation algorithm, for which a system-level design is given, demonstrates a further application of the Vector-Radix Fourier transform. A novel concurrent version of the quad-tree based Split and Merge algorithm has been implemented on the pyramid architecture. The performance of the developed parallel implementations is analysed. Many of the obtained speed-up and efficiency measures show values close to their respective theoretical maxima. Where appropriate comparisons are drawn between different implementations. The thesis concludes with comments on general issues related to the use of the Transputer system as a development tool for image processing applications; and on the issues related to the engineering of concurrent image processing applications.

The application of parallel processing methods to vibrational analysis

The trend in modal extraction algorithms is to use all the available frequency response functions data to obtain a global estimate of the natural frequencies, damping ratio and mode shapes. Improvements in transducer and signal processing technology allow the simultaneous measurement of many hundreds of channels of response data. The quantity of data available and the complexity of the extraction algorithms make considerable demands on the available computer power and require a powerful computer or dedicated workstation to perform satisfactorily. An alternative to waiting for faster sequential processors is to implement the algorithm in parallel, for example on a network of Transputers. Parallel architectures are a cost effective means of increasing computational power, and a larger number of response channels would simply require more processors. This thesis considers how two typical modal extraction algorithms, the Rational Fraction Polynomial method and the Ibrahim Time Domain method, may be implemented on a network of transputers. The Rational Fraction Polynomial Method is a well known and robust frequency domain 'curve fitting' algorithm. The Ibrahim Time Domain method is an efficient algorithm that 'curve fits' in the time domain. This thesis reviews the algorithms, considers the problems involved in a parallel implementation, and shows how they were implemented on a real Transputer network.