Real time motion estimation using a neural architecture implemented on GPUs

This work describes a neural network based architecture that represents and estimates object motion in videos. This architecture addresses multiple computer vision tasks such as image segmentation, object representation or characterization, motion analysis and tracking. The use of a neural network architecture allows for the simultaneous estimation of global and local motion and the representation of deformable objects. This architecture also avoids the problem of finding corresponding features while tracking moving objects. Due to the parallel nature of neural networks, the architecture has been implemented on GPUs that allows the system to meet a set of requirements such as: time constraints management, robustness, high processing speed and re-configurability. Experiments are presented that demonstrate the validity of our architecture to solve problems of mobile agents tracking and motion analysis.

Functionally partitioned module-based programmable architecture for wireless base-band processing

A specialised reconfigurable architecture is targeted at wireless base-band processing. It is built to cater for multiple wireless standards. It has lower power consumption than the processor-based solution. It can be scaled to run in parallel for processing multiple channels. Test resources are embedded on the architecture and testing strategies are included. This architecture is functionally partitioned according to the common operations found in wireless standards, such as CRC error correction, convolution and interleaving. These modules are linked via Virtual Wire Hardware modules and route-through switch matrices. Data can be processed in any order through this interconnect structure. Virtual Wire ensures the same flexibility as normal interconnects, but the area occupied and the number of switches needed is reduced. The testing algorithm scans all possible paths within the interconnection network exhaustively and searches for faults in the processing modules. The testing algorithm starts by scanning the externally addressable memory space and testing the master controller. The controller then tests every switch in the route-through switch matrix by making loops from the shared memory to each of the switches. The local switch matrix is also tested in the same way. Next the local memory is scanned. Finally, pre-defined test vectors are loaded into local memory to check the processing modules. This paper compares various base-band processing solutions. It describes the proposed platform and its implementation. It outlines the test resources and algorithm. It concludes with the mapping of Bluetooth and GSM base-band onto the platform.

An FPGA network architecture for accelerating 3DES - CBC

This paper presents a DES/3DES core that will support cipher block chaining (CBC) and also has a built in keygen that together take up about 10% of the resources in a Xilinx Virtex II 1000-4. The core will achieve up to 200Mbit/s of encryption or decryption. Also presented is a network architecture that will allow these CBC capable 3DES cores to perform their processing in parallel.

A real-time asymmetric multiprocessor-reconfigurable system-on-chip architecture

We propose an asymmetric multi-processor SoC architecture, featuring a master CPU running uClinux, and multiple loosely-coupled slave CPUs running real-time threads assigned by the master CPU. Real-time SoC architectures often demand a compromise between a generic platform for different applications, and application-specific customizations to achieve performance requirements. Our proposed architecture offers a generic platform running a conventional embedded operating system providing a traditional software-oriented development approach, while multiple slave CPUs act as a dedicated independent real-time threads execution unit running in parallel of master CPU to achieve performance requirements. In this paper, the architecture is described, including the application / threading development environment. The performance of the architecture with several standard benchmark routines is also analysed.

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.

Towards Active Vision in the DUAL Cognitive Architecture

The paper describes an extension of the cognitive architecture DUAL with a model of visual attention and perception. The goal of this attempt is to account for the construction and the categorization of object and scene representations derived from visual stimuli in the TextWorld microdomain. Low-level parallel computations are combined with an active serial deployment of visual attention enabling the construction of abstract symbolic representations. A limited-capacity short-term visual store holding information across attention shifts forms the core of the model interfacing between the low-level representation of the stimulus and DUAL’s semantic memory. The model is validated by comparing the results of a simulation with real data from an eye movement experiment with human subjects.

The Architecture of Looking

In 2010 the architects of thebigairworld participated in the creation of a film about Marcel Duchamp's Etant donnes. The film stages two architectural doctors, Haralambidou and Watson discussing Duchamp's piece with images of the work running in parallel. Off camera but by no means absent from the production the Mobile Studio act as camera man, director and grip.

A green perspective on Structured parallel programming

Structured parallel programming, and in particular programming models using the algorithmic skeleton or parallel design pattern concepts, are increasingly considered to be the only viable means of supporting effective development of scalable and efficient parallel programs. Structured parallel programming models have been assessed in a number of works in the context of performance. In this paper we consider how the use of structured parallel programming models allows knowledge of the parallel patterns present to be harnessed to address both performance and energy consumption. We consider different features of structured parallel programming that may be leveraged to impact the performance/energy trade-off and we discuss a preliminary set of experiments validating our claims.

FPGA-based architecture for hyperspectral endmember extraction

Hyperspectral instruments have been incorporated in satellite missions, providing data of high spectral resolution of the Earth. This data can be used in remote sensing applications, such as, target detection, hazard prevention, and monitoring oil spills, among others. In most of these applications, one of the requirements of paramount importance is the ability to give real-time or near real-time response. Recently, onboard processing systems have emerged, in order to overcome the huge amount of data to transfer from the satellite to the ground station, and thus, avoiding delays between hyperspectral image acquisition and its interpretation. For this purpose, compact reconfigurable hardware modules, such as field programmable gate arrays (FPGAs) are widely used. This paper proposes a parallel FPGA-based architecture for endmember’s signature extraction. This method based on the Vertex Component Analysis (VCA) has several advantages, namely it is unsupervised, fully automatic, and it works without dimensionality reduction (DR) pre-processing step. The architecture has been designed for a low cost Xilinx Zynq board with a Zynq-7020 SoC FPGA based on the Artix-7 FPGA programmable logic and tested using real hyperspectral data sets collected by the NASA’s Airborne Visible Infra-Red Imaging Spectrometer (AVIRIS) over the Cuprite mining district in Nevada. Experimental results indicate that the proposed implementation can achieve real-time processing, while maintaining the methods accuracy, which indicate the potential of the proposed platform to implement high-performance, low cost embedded systems, opening new perspectives for onboard hyperspectral image processing.

Modelling continuum mechanics phenomena using three dimensional unstructured meshes on massively parallel processors

The difficulties encountered in implementing large scale CM codes on multiprocessor systems are now fairly well understood. Despite the claims of shared memory architecture manufacturers to provide effective parallelizing compilers, these have not proved to be adequate for large or complex programs. Significant programmer effort is usually required to achieve reasonable parallel efficiencies on significant numbers of processors. The paradigm of Single Program Multi Data (SPMD) domain decomposition with message passing, where each processor runs the same code on a subdomain of the problem, communicating through exchange of messages, has for some time been demonstrated to provide the required level of efficiency, scalability, and portability across both shared and distributed memory systems, without the need to re-author the code into a new language or even to support differing message passing implementations. Extension of the methods into three dimensions has been enabled through the engineering of PHYSICA, a framework for supporting 3D, unstructured mesh and continuum mechanics modeling. In PHYSICA, six inspectors are used. Part of the challenge for automation of parallelization is being able to prove the equivalence of inspectors so that they can be merged into as few as possible.

The MUSE Machine -- an Architecture for Structured Data Flow Computation

Computers employing some degree of data flow organisation are now well established as providing a possible vehicle for concurrent computation. Although data-driven computation frees the architecture from the constraints of the single program counter, processor and global memory, inherent in the classic von Neumann computer, there can still be problems with the unconstrained generation of fresh result tokens if a pure data flow approach is adopted. The advantages of allowing serial processing for those parts of a program which are inherently serial, and of permitting a demand-driven, as well as data-driven, mode of operation are identified and described. The MUSE machine described here is a structured architecture supporting both serial and parallel processing which allows the abstract structure of a program to be mapped onto the machine in a logical way.

Architecture for machining process and production monitoring based in open computer numerical control

This paper proposes an architecture for machining process and production monitoring to be applied in machine tools with open Computer numerical control (CNC). A brief description of the advantages of using open CNC for machining process and production monitoring is presented with an emphasis on the CNC architecture using a personal computer (PC)-based human-machine interface. The proposed architecture uses the CNC data and sensors to gather information about the machining process and production. It allows the development of different levels of monitoring systems with mininium investment, minimum need for sensor installation, and low intrusiveness to the process. Successful examples of the utilization of this architecture in a laboratory environment are briefly described. As a Conclusion, it is shown that a wide range of monitoring solutions can be implemented in production processes using the proposed architecture.

A molecular phylogeny and the evolution of nest architecture and behavior in Trigona s.s. (Hymenoptera : Apidae : Meliponini)

Stingless bees exhibit extraordinary variation in nest architecture within and among species. To test for phylogenetic association of behavioral traits for species of the Neotropical stingless bee genus Trigona s.s., a phylogenetic hypothesis was generated by combining sequence data of 24 taxa from one mitochondrial (16S rRNA) and four nuclear gene fragments (long-wavelength rhodopsin copy 1 (opsin), elongation factor-1 alpha copy F2, arginine kinase, and 28S rRNA). Fifteen characteristics of the nest architecture were coded and tested for phylogenetic association. Several characters have significant phylogenetic signal, including type of nesting substrate, nest construction material, and hemipterophily, the tending of hemipteroid insects in exchange for sugar excretions. Phylogenetic independent habits encountered in Trigona s.s. include coprophily and necrophagy.

Status of Early 19th-Century Names Authored in Parallel by Wied and Schinz for South American Reptiles and Amphibians, with Designations of Three Nomina Protecta

Prince Maximilian zu Wied's great exploration of coastal Brazil in 1815-1817 resulted in important collections of reptiles, amphibians, birds, and mammals, many of which were new species later described by Wied himself The bulk of his collection was purchased for the American Museum of Natural History in 1869, although many ""type specimens"" had disappeared earlier. Wied carefully identified his localities but did not designate type specimens or type localities, which are taxonomic concepts that were not yet established. Information and manuscript names on a fraction (17 species) of his Brazilian reptiles and amphibians were transmitted by Wied to Prof. Heinrich Rudolf Schinz at the University of Zurich. Schinz included these species (credited to their discoverer ""Princ. Max."") in the second volume of Das Thierreich ... (1822). Most are junior objective synonyms of names published by Wied. However, six of the 17 names used by Schinz predate Wied's own publications. Three were manuscript names never published by Wied because he determined the species to be previously known. (1) Lacerta vittata Schinz, 1822 (a nomen oblitum) = Lacerta striata sensu Wied (a misidentification, non Linnaeus nec sensu Merrem) = Kentropyx calcarata Spix, 1825, herein qualified as a nomen protectum. (2) Polychrus virescens Schinz, 1822 = Lacerta marmorata Linnaeus, 1758 (now Polychrus marmoratus). (3) Scincus cyanurus Schinz, 1822 (a nomen oblitum) = Gymnophthalmus quadrilineatus sensu Wied (a misidentification, non Linnaeus nec sensu Merrem) = Micrablepharus maximiliani (Reinhardt and Lutken, ""1861"" [1862]), herein qualified as a nomen protectum. Qualifying Scincus cyanurus Schinz, 1822, as a nomen oblitum also removes the problem of homonymy with the later-named Pacific skink Scincus cyanurus Lesson (= Emoia cyanura). The remaining three names used by Schinz are senior objective synonyms that take priority over Wied's names. (4) Bufo cinctus Schinz, 1822, is senior to Bufo cinctus Wied, 1823; both, however, are junior synonyms of Bufo crucifer Wied, 1821 = Chaunus crucifer (Wied). (5) Agama picta Schinz, 1822, is senior to Agama picta Wied, 1823, requiring a change of authorship for this poorly known species, to be known as Enyalius pictus (Schinz). (6) Lacerta cyanomelas Schinz, 1822, predates Teius cyanomelas Wied, 1824 (1822-1831) both nomina oblita. Wied's illustration and description shows cyanomelas as apparently conspecific with the recently described but already well-known Cnemidophorus nativo Rocha et al., 1997, which is the valid name because of its qualification herein as a nomen protectum. The preceding specific name cyanomelas (as corrected in an errata section) is misspelled several ways in different copies of Schinz's original description (""cyanom las,"" ""cyanomlas,"" and cyanom""). Loosening, separation, and final loss of the last three letters of movable type in the printing chase probably accounts for the variant misspellings.

Optimized architecture for Tyrosinase-containing Langmuir-Blodgett films to detect pyrogallol

The control of molecular architectures has been a key factor for the use of Langmuir-Blodgett (LB) films in biosensors, especially because biomolecules can be immobilized with preserved activity. In this paper we investigated the incorporation of tyrosinase (Tyr) in mixed Langmuir films of arachidic acid (AA) and a lutetium bisphthalocyanine (LuPc(2)), which is confirmed by a large expansion in the surface pressure isotherm. These mixed films of AA-LuPc(2) + Tyr could be transferred onto ITO and Pt electrodes as indicated by FTIR and electrochemical measurements, and there was no need for crosslinking of the enzyme molecules to preserve their activity. Significantly, the activity of the immobilised Tyr was considerably higher than in previous work in the literature, which allowed Tyr-containing LB films to be used as highly sensitive voltammetric sensors to detect pyrogallol. Linear responses have been found up to 400 mu M, with a detection limit of 4.87 x 10(-2) mu M (n = 4) and a sensitivity of 1.54 mu A mu M(-1) cm(-2). In addition, the Hill coefficient (h = 1.27) indicates cooperation with LuPc(2) that also acts as a catalyst. The enhanced performance of the LB-based biosensor resulted therefore from a preserved activity of Tyr combined with the catalytic activity of LuPc(2), in a strategy that can be extended to other enzymes and analytes upon varying the LB film architecture.