A Novel Architecture of Vision Chip for Fast Traffic Lane Detection and FPGA Implementation

This paper presents a novel architecture of vision chip for fast traffic lane detection (FTLD). The architecture consists of a 32*32 SIMD processing element (PE) array processor and a dual-core RISC processor. The PE array processor performs low-level pixel-parallel image processing at high speed and outputs image features for high-level image processing without I/O bottleneck. The dual-core processor carries out high-level image processing. A parallel fast lane detection algorithm for this architecture is developed. The FPGA system with a CMOS image sensor is used to implement the architecture. Experiment results show that the system can perform the fast traffic lane detection at 50fps rate. It is much faster than previous works and has good robustness that can operate in various intensity of light. The novel architecture of vision chip is able to meet the demand of real-time lane departure warning system.

Pipeline Architecture and Parallel Computation-Based Real-Time Stereovision Tracking System for Surgical Navigation

This paper studies the development of a real-time stereovision system to track multiple infrared markers attached to a surgical instrument. Multiple stages of pipeline in field-programmable gate array (FPGA) are developed to recognize the targets in both left and right image planes and to give each target a unique label. The pipeline architecture includes a smoothing filter, an adaptive threshold module, a connected component labeling operation, and a centroid extraction process. A parallel distortion correction method is proposed and implemented in a dual-core DSP. A suitable kinematic model is established for the moving targets, and a novel set of parallel and interactive computation mechanisms is proposed to position and track the targets, which are carried out by a cross-computation method in a dual-core DSP. The proposed tracking system can track the 3-D coordinate, velocity, and acceleration of four infrared markers with a delay of 9.18 ms. Furthermore, it is capable of tracking a maximum of 110 infrared markers without frame dropping at a frame rate of 60 f/s. The accuracy of the proposed system can reach the scale of 0.37 mm RMS along the x- and y-directions and 0.45 mm RMS along the depth direction (the depth is from 0.8 to 0.45 m). The performance of the proposed system can meet the requirements of applications such as surgical navigation, which needs high real time and accuracy capability.

Pipeline Architecture and Parallel Computation-Based Real-Time Stereovision Tracking System for Surgical Navigation

This paper studies the development of a real-time stereovision system to track multiple infrared markers attached to a surgical instrument. Multiple stages of pipeline in field-programmable gate array (FPGA) are developed to recognize the targets in both left and right image planes and to give each target a unique label. The pipeline architecture includes a smoothing filter, an adaptive threshold module, a connected component labeling operation, and a centroid extraction process. A parallel distortion correction method is proposed and implemented in a dual-core DSP. A suitable kinematic model is established for the moving targets, and a novel set of parallel and interactive computation mechanisms is proposed to position and track the targets, which are carried out by a cross-computation method in a dual-core DSP. The proposed tracking system can track the 3-D coordinate, velocity, and acceleration of four infrared markers with a delay of 9.18 ms. Furthermore, it is capable of tracking a maximum of 110 infrared markers without frame dropping at a frame rate of 60 f/s. The accuracy of the proposed system can reach the scale of 0.37 mm RMS along the x- and y-directions and 0.45 mm RMS along the depth direction (the depth is from 0.8 to 0.45 m). The performance of the proposed system can meet the requirements of applications such as surgical navigation, which needs high real time and accuracy capability.

Multi-resolução com fóvea móvel para redução e abstração de dados em tempo real

We propose a new approach to reduction and abstraction of visual information for robotics vision applications. Basically, we propose to use a multi-resolution representation in combination with a moving fovea for reducing the amount of information from an image. We introduce the mathematical formalization of the moving fovea approach and mapping functions that help to use this model. Two indexes (resolution and cost) are proposed that can be useful to choose the proposed model variables. With this new theoretical approach, it is possible to apply several filters, to calculate disparity and to obtain motion analysis in real time (less than 33ms to process an image pair at a notebook AMD Turion Dual Core 2GHz). As the main result, most of time, the moving fovea allows the robot not to perform physical motion of its robotics devices to keep a possible region of interest visible in both images. We validate the proposed model with experimental results

Solitons in Bose-Einstein condensates trapped in a double-well potential

We investigate, analytically and numerically, families of bright solitons in a system of two linearly coupled nonlinear Schrodinger/Gross-Pitaevskii equations, describing two Bose-Einstein condensates trapped in an asymmetric double-well potential, in particular, when the scattering lengths in the condensates have arbitrary magnitudes and opposite signs. The solitons are found to exist everywhere where they are permitted by the dispersion law. Using the Vakhitov-Kolokolov criterion and numerical methods, we show that, except for small regions in the parameter space, the solitons are stable to small perturbations. Some of them feature self-trapping of almost all the atoms in the condensate with no atomic interaction or weak repulsion is coupled to the self-attractive condensate. An unusual bifurcation is found, when the soliton bifurcates from the zero solution with vanishing amplitude and width simultaneously diverging but at a finite number of atoms in the soliton. By means of numerical simulations, it is found that, depending on values of the parameters and the initial perturbation, unstable solitons either give rise to breathers or completely break down into incoherent waves (radiation). A version of the model with the self-attraction in both components, which applies to the description of dual-core fibers in nonlinear optics, is considered too, and new results are obtained for this much studied system. (C) 2003 Elsevier B.V. All rights reserved.

Comparação entre modelos de análise genômica utilizando dados simulados e dados reais em ovinos

Pós-graduação em Genética e Melhoramento Animal - FCAV

Large-scale Network Analysis on Distributed Architectures

Questa dissertazione esamina le sfide e i limiti che gli algoritmi di analisi di grafi incontrano in architetture distribuite costituite da personal computer. In particolare, analizza il comportamento dell'algoritmo del PageRank così come implementato in una popolare libreria C++ di analisi di grafi distribuiti, la Parallel Boost Graph Library (Parallel BGL). I risultati qui presentati mostrano che il modello di programmazione parallela Bulk Synchronous Parallel è inadatto all'implementazione efficiente del PageRank su cluster costituiti da personal computer. L'implementazione analizzata ha infatti evidenziato una scalabilità negativa, il tempo di esecuzione dell'algoritmo aumenta linearmente in funzione del numero di processori. Questi risultati sono stati ottenuti lanciando l'algoritmo del PageRank della Parallel BGL su un cluster di 43 PC dual-core con 2GB di RAM l'uno, usando diversi grafi scelti in modo da facilitare l'identificazione delle variabili che influenzano la scalabilità. Grafi rappresentanti modelli diversi hanno dato risultati differenti, mostrando che c'è una relazione tra il coefficiente di clustering e l'inclinazione della retta che rappresenta il tempo in funzione del numero di processori. Ad esempio, i grafi Erdős–Rényi, aventi un basso coefficiente di clustering, hanno rappresentato il caso peggiore nei test del PageRank, mentre i grafi Small-World, aventi un alto coefficiente di clustering, hanno rappresentato il caso migliore. Anche le dimensioni del grafo hanno mostrato un'influenza sul tempo di esecuzione particolarmente interessante. Infatti, si è mostrato che la relazione tra il numero di nodi e il numero di archi determina il tempo totale.

A Precharge-Absorbed DPL Logic for Reducing Early Propagation Effects on FPGA Implementations

In this paper, a new countermeasure against power and electromagnetic (EM) Side Channel Attacks (SCA) on FPGA implemented cryptographic algorithms is proposed. This structure mainly focuses on a critical vulnerability, Early Evaluation, also known as Early Propagation Effect (EPE), which exists in most conventional SCA-hardened DPL (Dual-rail with Precharge Logic) solutions. The main merit of this proposal is that the EPE can be effectively prevented by using a synchronized non regular precharge network, which maintains identical routing between the original and mirror parts, where costs and design complexity compared with previous EPE-resistant countermeasures are reduced, while security level is not sacrificed. Another advantage for our Precharge Absorbed(PA) - DPL method is that its Dual-Core style (independent architecture for true and false parts) could be generated using partial reconfiguration. This helps to get a dynamic security protection with better energy planning. That means system only keeps the true part which fulfills the normal en/decryption task in low security level, and reconfigures the false parts once high security level is required. A relatively limited clock speed is a compromise, since signal propagation is restricted to a portion of the clock period. In this paper, we explain the principles of PA-DPL and provide the guidelines to design this structure. We experimentally validate our methods in a minimized AES co-processor on Xilinx Virtex-5 board using electromagnetic (EM) attacks.

An Interleaved EPE-Immune PA-DPL Structure for Resisting Concentrated EM Side Channel Attacks on FPGA Implementation

Early propagation effect (EPE) is a critical problem in conventional dual-rail logic implementations against Side Channel Attacks (SCAs). Among previous EPE-resistant architectures, PA-DPL logic offers EPE-free capability at relatively low cost. However, its separate dual core structure is a weakness when facing concentrated EM attacks where a tiny EM probe can be precisely positioned closer to one of the two cores. In this paper, we present an PA-DPL dual-core interleaved structure to strengthen resistance against sophisticated EM attacks on Xilinx FPGA implementations. The main merit of the proposed structure is that every two routing in each signal pair are kept identical even the dual cores are interleaved together. By minimizing the distance between the complementary routings and instances of both cores, even the concentrated EM measurement cannot easily distinguish the minor EM field unbalance. In PA- DPL, EPE is avoided by compressing the evaluation phase to a small portion of the clock period, therefore, the speed is inevitably limited. Regarding this, we made an improvement to extend the duty cycle of evaluation phase to more than 40 percent, yielding a larger maximum working frequency. The detailed design flow is also presented. We validate the security improvement against EM attack by implementing a simplified AES co-processor in Virtex-5 FPGA.

Development of Embedded Linux Applications Using ZedBoard

The purpose of this document is to create a modest integration guide for embedding a Linux Operating System on ZedBoard development platform, based on Xilinx’s Zynq-7000 All Programmable System on Chip which contains a dual core ARM Cortex-A9 and a 7 Series FPGA Artix-7. The integration process has been structured in four chapters according to the logic generation of the different parts that compose the embedded system. With the intention of automating the generation process of a complete Linux distribution specific for ZedBoard platform, BuildRoot development platform it is used. Once the embedding process finished, it was decided to add to the system the required functionalities for adding support for IEEE1588 Standard for Precision Clock Synchronization Protocol for Networked Measurement and Control Systems, through a user space Linux program which implements the protocol. That PTP user space implementation program has been cross-compiled, executed on target and tested for evaluating the functionalities added. RESUMEN El propósito de este documento es crear una modesta guía de integración de un sistema operativo Linux para la plataforma de desarrollo ZedBoard, basada en un System on Chip del fabricante Xilinx llamado Zynq-7000. Este System on Chip está compuesto por un procesador de doble núcleo ARM Cortex-A9 y una FPGA de la Serie 7 equiparable a una Artix-7. El proceso de integración se ha estructurado en cuatro grandes capítulos que se rigen según el orden lógico de generación de las distintas partes por las que el sistema empotrado está compuesto. Con el ánimo de automatizar el proceso de creación de una distribución de Linux específica para la plataforma ZedBoard, se ha utilizado la plataforma de desarrollo BuildRoot. Una vez terminado el proceso de integración del sistema empotrado, se procedió a dar dotar al sistema de las funcionalidades necesarias para dar soporte al estándar de sincronización de relojes en redes de área local, PTP IEEE1588, a través de una implementación del mismo en un programa de lado de usuario el cual ha sido compilado, ejecutado y testeado para evaluar el correcto funcionamiento de las funcionalidades añadidas.

Embedded Linux integration using Linuxlink tool and peripheral driver development for Zedboard

This project is divided into two main parts: The first part shows the integration of an Embedded Linux operating system on a development hardware platform named Zedboard. This platform contains a Zynq-7000 System on Chip (Soc) which is composed by two dual core ARM Cortex-A9 processors and a FPGA Artix-7. The Embedded Linux is built with Linuxlink, a Timesys tool. Meanwhile, the platform hardware configuration is done with Xilinx Vivado. The system is loaded with an SD card which requires to have every files needed for the booting process and for the operation. Some of these files are generated with Xilinx SDK software. The second part starts up from the system already built to integrate a peripheral in the Zynq-7000 FPGA. Also the drivers for controlling the peripheral from the operating system are developed. Finally, a user space program is created to test both of them. RESUMEN. Este proyecto consta de dos partes: La primera muestra la integración de un sistema operativo Linux embebido en una plataforma de desarrollo hardware llamada Zedboard. Esta plataforma utiliza un System on Chip (SoC) Zynq-7000 que está formado por dos procesadores ARM Cortex-A9 de doble núcleo y una FPGA Artix-7. El Linux embebido se construye utilizando la herramienta Linuxlink de Timesys, mientras que el hardware de la plataforma de desarrollo se configura con Vivado de Xilinx. El sistema se carga en una tarjeta SD que debe tener todos los archivos necesarios para completar el arranque y hacer funcionar el sistema. Algunos de esos archivos se generan con la herramienta SDK de Xilinx. En la segunda parte se utiliza el sistema construido para integrar un periférico en la FPGA del Zynq-7000, haciendo uso de Vivado, y se desarrollan los drivers necesarios para utilizarlo mediante el sistema operativo. Para probar esta última parte se desarrolla un programa de espacio de usuario.

Procesamiento de imágenes y control de un hexacóptero

En este proyecto se pretende diseñar un sistema embebido capaz de realizar procesamiento de imágenes y guiado de un hexacóptero. El hexacóptero dispondrá a bordo de una cámara así como las baterías y todo el hardware necesario para realizar el procesamiento de la información visual obtenida e implementar el controlador necesario para permitir su guiado. OpenCV es una biblioteca de primitivas de procesado de imagen que permite crear algoritmos de Visión por Computador de última generación. OpenCV fue desarrollado originalmente por Intel en 1999 para mostrar la capacidad de procesamiento de los micros de Intel, por lo que la mayoría de la biblioteca está optimizada para correr en estos micros, incluyendo las extensiones MMX y SSE. http://en.wikipedia.org/wiki/OpenCV Actualmente es ampliamente utilizada tanto por la comunidad científica como por la industria, para desarrollar nuevos algoritmos para equipos de sobremesa y sobre todo para sistemas empotrados (robots móviles, cámaras inteligentes, sistemas de inspección, sistemas de vigilancia, etc..). Debido a su gran popularidad se han realizado compilaciones de la biblioteca para distintos sistemas operativos tradicionales (Windows, Linux, Mac), para dispositivos móviles (Android, iOS) y para sistemas embebidos basados en distintos tipos de procesadores (ARM principalmente). - iPhone port: http://www.eosgarden.com/en/opensource/opencv-ios/overview/ - Android port: http://opencv.willowgarage.com/wiki/AndroidExperimental Un ejemplo de plataforma embebida es la tarjeta Zedboard (http://www.zedboard.org/), que representa el estado del arte en dispositivos embebidos basados en la arquitectura Cortex de ARM. La tarjeta incluye un procesador Cortex-A9 dual core junto con una gran cantidad de periféricos y posibilidades de conexión a tarjetas de expansión de terceras partes, lo que permite desarrollar aplicaciones en muy distintos campos de la Visión por Computador.

Parallel geostatistics for sparse and dense datasets

Very large spatially-referenced datasets, for example, those derived from satellite-based sensors which sample across the globe or large monitoring networks of individual sensors, are becoming increasingly common and more widely available for use in environmental decision making. In large or dense sensor networks, huge quantities of data can be collected over small time periods. In many applications the generation of maps, or predictions at specific locations, from the data in (near) real-time is crucial. Geostatistical operations such as interpolation are vital in this map-generation process and in emergency situations, the resulting predictions need to be available almost instantly, so that decision makers can make informed decisions and define risk and evacuation zones. It is also helpful when analysing data in less time critical applications, for example when interacting directly with the data for exploratory analysis, that the algorithms are responsive within a reasonable time frame. Performing geostatistical analysis on such large spatial datasets can present a number of problems, particularly in the case where maximum likelihood. Although the storage requirements only scale linearly with the number of observations in the dataset, the computational complexity in terms of memory and speed, scale quadratically and cubically respectively. Most modern commodity hardware has at least 2 processor cores if not more. Other mechanisms for allowing parallel computation such as Grid based systems are also becoming increasingly commonly available. However, currently there seems to be little interest in exploiting this extra processing power within the context of geostatistics. In this paper we review the existing parallel approaches for geostatistics. By recognising that diffeerent natural parallelisms exist and can be exploited depending on whether the dataset is sparsely or densely sampled with respect to the range of variation, we introduce two contrasting novel implementations of parallel algorithms based on approximating the data likelihood extending the methods of Vecchia [1988] and Tresp [2000]. Using parallel maximum likelihood variogram estimation and parallel prediction algorithms we show that computational time can be significantly reduced. We demonstrate this with both sparsely sampled data and densely sampled data on a variety of architectures ranging from the common dual core processor, found in many modern desktop computers, to large multi-node super computers. To highlight the strengths and weaknesses of the diffeerent methods we employ synthetic data sets and go on to show how the methods allow maximum likelihood based inference on the exhaustive Walker Lake data set.

Synthesis and characterization of dual-functionalized core-shell fluorescent microspheres for bioconjugation and cellular delivery

The efficient transport of micron-sized beads into cells, via a non-endocytosis mediated mechanism, has only recently been described. As such there is considerable scope for optimization and exploitation of this procedure to enable imaging and sensing applications to be realized. Herein, we report the design, synthesis and characterization of fluorescent microsphere-based cellular delivery agents that can also carry biological cargoes. These core-shell polymer microspheres possess two distinct chemical environments; the core is hydrophobic and can be labeled with fluorescent dye, to permit visual tracking of the microsphere during and after cellular delivery, whilst the outer shell renders the external surfaces of the microspheres hydrophilic, thus facilitating both bioconjugation and cellular compatibility. Cross-linked core particles were prepared in a dispersion polymerization reaction employing styrene, divinylbenzene and a thiol-functionalized co-monomer. These core particles were then shelled in a seeded emulsion polymerization reaction, employing styrene, divinylbenzene and methacrylic acid, to generate orthogonally functionalized core-shell microspheres which were internally labeled via the core thiol moieties through reaction with a thiol reactive dye (DY630-maleimide). Following internal labeling, bioconjugation of green fluorescent protein (GFP) to their carboxyl-functionalized surfaces was successfully accomplished using standard coupling protocols. The resultant dual-labeled microspheres were visualized by both of the fully resolvable fluorescence emissions of their cores (DY630) and shells (GFP). In vitro cellular uptake of these microspheres by HeLa cells was demonstrated conventionally by fluorescence-based flow cytometry, whilst MTT assays demonstrated that 92% of HeLa cells remained viable after uptake. Due to their size and surface functionalities, these far-red-labeled microspheres are ideal candidates for in vitro, cellular delivery of proteins, as described in the accompanying paper.

Dual-polarization multi-band OFDM signals for next generation core networks

Dual-polarization multi-band orthogonal frequency-division multiplexing (DP-MB-OFDM) signals are optimized at data rates up to 500 Gb/s in dispersion compensation fiber (DCF)-free long-haul links. We compare different polarization crosstalk compensation techniques and explore the DP-MB-OFDM transmission distance limitations. In addition, the impact of the OFDM subcarrier number and high-level modulation format on the transmission performance are also investigated. Finally, a comparison is made between DP-MB-OFDM and the industrial solution of single-carrier DP quaternary phase-shift keying (DP-QPSK) at 1000 km.