Flutter margin with non-linearities: real-time prediction of flutter onset speed

The present article shows a procedure to predict the flutter speed based on real-time tuning of a quasi non-linear aeroelastic model. A two-dimensional non-linear (freeplay) aeroeslastic model is implemented inMatLab/Simulink with incompressible aerodynamic conditions. A comparison with real compressible conditions is provided. Once the numerical validation is accomplished, a parametric aeroelastic model is built in order to describe the proposed procedure and contribute to reduce the number of flight hours needed to expand the flutter envelope.

Multiple Hashing Integration for Real-Time Large Scale Part-to-Part Video Matching

A real-time large scale part-to-part video matching algorithm, based on the cross correlation of the intensity of motion curves, is proposed with a view to originality recognition, video database cleansing, copyright enforcement, video tagging or video result re-ranking. Moreover, it is suggested how the most representative hashes and distance functions - strada, discrete cosine transformation, Marr-Hildreth and radial - should be integrated in order for the matching algorithm to be invariant against blur, compression and rotation distortions: (R; _) 2 [1; 20]_[1; 8], from 512_512 to 32_32pixels2 and from 10 to 180_. The DCT hash is invariant against blur and compression up to 64x64 pixels2. Nevertheless, although its performance against rotation is the best, with a success up to 70%, it should be combined with the Marr-Hildreth distance function. With the latter, the image selected by the DCT hash should be at a distance lower than 1.15 times the Marr-Hildreth minimum distance.

Temporal segmentation tool for high-quality real time video editing software

The increasing use of video editing software requires faster and more efficient editing tools. As a first step, these tools perform a temporal segmentation in shots that allows a later building of indexes describing the video content. Here, we propose a novel real-time high-quality shot detection strategy, suitable for the last generation of video editing software requiring both low computational cost and high quality results. While abrupt transitions are detected through a very fast pixel-based analysis, gradual transitions are obtained from an efficient edge-based analysis. Both analyses are reinforced with a motion analysis that helps to detect and discard false detections. This motion analysis is carried out exclusively over a reduced set of candidate transitions, thus maintaining the computational requirements demanded by new applications to fulfill user needs.

Moving object detection for real-time augmented reality applications in a GPGPU

The last generation of consumer electronic devices is endowed with Augmented Reality (AR) tools. These tools require moving object detection strategies, which should be fast and efficient, to carry out higher level object analysis tasks. We propose a lightweight spatio-temporal-based non-parametric background-foreground modeling strategy in a General Purpose Graphics Processing Unit (GPGPU), which provides real-time high-quality results in a great variety of scenarios and is suitable for AR applications.

A Structure of Problem Solving Methods for Real Time Decision Support in Traffic Control

This article describes a knowledge-based application in the domain of road traffic management that we have developed following a knowledge modeling approach and the notion of problem-solving method. The article presents first a domain-independent model for real-time decision support as a structured collection of problem solving methods. Then, it is described how this general model is used to develop an operational version for the domain of traffic management. For this purpose, a particular knowledge modeling tool, called KSM (Knowledge Structure Manager), was applied. Finally, the article shows an application developed for a traffic network of the city of Madrid and it is compared with a second application developed for a different traffic area of the city of Barcelona.

A Propose-and-revise System for Real-time Traffic Management

The aim of this paper is to describe an intelligent system for the problem of real time road traffic control. The purpose of the system is to help traffic engineers in the selection of the state of traffic control devices on real time, using data recorded by traffic detectors on motorways. The system follows an advanced knowledge-based approach that implements an abstract generic problem solving method, called propose-and-revise, which was proposed in Artificial Intelligence, within the knowledge engineering field, as a standard cognitive structure oriented to solve configuration design problems. The paper presents the knowledge model of such a system together with the strategy of inference and describes how it was applied for the case of the M-40 urban ring for the city of Madrid.

Real time monitoring of click chemistry self-healing in polymer composites

A photo-healable rubber composite based on effective and fast thiol-alkyne click chemistry as a selfhealing agent prestored in glass capillaries is reported. The click reaction and its effect on the mechanical properties of the composite are monitored in real time by dynamic mechanical analysis, showing that the successful bleeding of healing agents to the crack areas and the effective photoinitiated click reaction result in a 30% storage modulus increase after only 5 min of UV light exposure. X-ray tomography confirms capillary-driven bleeding of reactants to the damaged areas. The effect of storing the click chemistry reactants in separate capillaries is also studied, and results show the importance of stoichiometry in achieving a significant level of repair of the composite. No reactant degradation or premature chemical reaction is observed over time in samples stored in the absence of UV radiation; they are able to undergo the self-healing reaction even one month after preparation.

Real-Time Adaptive Multi-Classifier Multi-Resolution Visual Tracking Framework for Unmanned Aerial Vehicles

This paper presents a novel robust visual tracking framework, based on discriminative method, for Unmanned Aerial Vehicles (UAVs) to track an arbitrary 2D/3D target at real-time frame rates, that is called the Adaptive Multi-Classifier Multi-Resolution (AMCMR) framework. In this framework, adaptive Multiple Classifiers (MC) are updated in the (k-1)th frame-based Multiple Resolutions (MR) structure with compressed positive and negative samples, and then applied them in the kth frame-based Multiple Resolutions (MR) structure to detect the current target. The sample importance has been integrated into this framework to improve the tracking stability and accuracy. The performance of this framework was evaluated with the Ground Truth (GT) in different types of public image databases and real flight-based aerial image datasets firstly, then the framework has been applied in the UAV to inspect the Offshore Floating Platform (OFP). The evaluation and application results show that this framework is more robust, efficient and accurate against the existing state-of-art trackers, overcoming the problems generated by the challenging situations such as obvious appearance change, variant illumination, partial/full target occlusion, blur motion, rapid pose variation and onboard mechanical vibration, among others. To our best knowledge, this is the first work to present this framework for solving the online learning and tracking freewill 2D/3D target problems, and applied it in the UAVs.

A framework for mixed-criticality partitioned real-time embedded systems

Los sistemas empotrados son cada día más comunes y complejos, de modo que encontrar procesos seguros, eficaces y baratos de desarrollo software dirigidos específicamente a esta clase de sistemas es más necesario que nunca. A diferencia de lo que ocurría hasta hace poco, en la actualidad los avances tecnológicos en el campo de los microprocesadores de los últimos tiempos permiten el desarrollo de equipos con prestaciones más que suficientes para ejecutar varios sistemas software en una única máquina. Además, hay sistemas empotrados con requisitos de seguridad (safety) de cuyo correcto funcionamiento depende la vida de muchas personas y/o grandes inversiones económicas. Estos sistemas software se diseñan e implementan de acuerdo con unos estándares de desarrollo software muy estrictos y exigentes. En algunos casos puede ser necesaria también la certificación del software. Para estos casos, los sistemas con criticidades mixtas pueden ser una alternativa muy valiosa. En esta clase de sistemas, aplicaciones con diferentes niveles de criticidad se ejecutan en el mismo computador. Sin embargo, a menudo es necesario certificar el sistema entero con el nivel de criticidad de la aplicación más crítica, lo que hace que los costes se disparen. La virtualización se ha postulado como una tecnología muy interesante para contener esos costes. Esta tecnología permite que un conjunto de máquinas virtuales o particiones ejecuten las aplicaciones con unos niveles de aislamiento tanto temporal como espacial muy altos. Esto, a su vez, permite que cada partición pueda ser certificada independientemente. Para el desarrollo de sistemas particionados con criticidades mixtas se necesita actualizar los modelos de desarrollo software tradicionales, pues estos no cubren ni las nuevas actividades ni los nuevos roles que se requieren en el desarrollo de estos sistemas. Por ejemplo, el integrador del sistema debe definir las particiones o el desarrollador de aplicaciones debe tener en cuenta las características de la partición donde su aplicación va a ejecutar. Tradicionalmente, en el desarrollo de sistemas empotrados, el modelo en V ha tenido una especial relevancia. Por ello, este modelo ha sido adaptado para tener en cuenta escenarios tales como el desarrollo en paralelo de aplicaciones o la incorporación de una nueva partición a un sistema ya existente. El objetivo de esta tesis doctoral es mejorar la tecnología actual de desarrollo de sistemas particionados con criticidades mixtas. Para ello, se ha diseñado e implementado un entorno dirigido específicamente a facilitar y mejorar los procesos de desarrollo de esta clase de sistemas. En concreto, se ha creado un algoritmo que genera el particionado del sistema automáticamente. En el entorno de desarrollo propuesto, se han integrado todas las actividades necesarias para desarrollo de un sistema particionado, incluidos los nuevos roles y actividades mencionados anteriormente. Además, el diseño del entorno de desarrollo se ha basado en la ingeniería guiada por modelos (Model-Driven Engineering), la cual promueve el uso de los modelos como elementos fundamentales en el proceso de desarrollo. Así pues, se proporcionan las herramientas necesarias para modelar y particionar el sistema, así como para validar los resultados y generar los artefactos necesarios para el compilado, construcción y despliegue del mismo. Además, en el diseño del entorno de desarrollo, la extensión e integración del mismo con herramientas de validación ha sido un factor clave. En concreto, se pueden incorporar al entorno de desarrollo nuevos requisitos no-funcionales, la generación de nuevos artefactos tales como documentación o diferentes lenguajes de programación, etc. Una parte clave del entorno de desarrollo es el algoritmo de particionado. Este algoritmo se ha diseñado para ser independiente de los requisitos de las aplicaciones así como para permitir al integrador del sistema implementar nuevos requisitos del sistema. Para lograr esta independencia, se han definido las restricciones al particionado. El algoritmo garantiza que dichas restricciones se cumplirán en el sistema particionado que resulte de su ejecución. Las restricciones al particionado se han diseñado con una capacidad expresiva suficiente para que, con un pequeño grupo de ellas, se puedan expresar la mayor parte de los requisitos no-funcionales más comunes. Las restricciones pueden ser definidas manualmente por el integrador del sistema o bien pueden ser generadas automáticamente por una herramienta a partir de los requisitos funcionales y no-funcionales de una aplicación. El algoritmo de particionado toma como entradas los modelos y las restricciones al particionado del sistema. Tras la ejecución y como resultado, se genera un modelo de despliegue en el que se definen las particiones que son necesarias para el particionado del sistema. A su vez, cada partición define qué aplicaciones deben ejecutar en ella así como los recursos que necesita la partición para ejecutar correctamente. El problema del particionado y las restricciones al particionado se modelan matemáticamente a través de grafos coloreados. En dichos grafos, un coloreado propio de los vértices representa un particionado del sistema correcto. El algoritmo se ha diseñado también para que, si es necesario, sea posible obtener particionados alternativos al inicialmente propuesto. El entorno de desarrollo, incluyendo el algoritmo de particionado, se ha probado con éxito en dos casos de uso industriales: el satélite UPMSat-2 y un demostrador del sistema de control de una turbina eólica. Además, el algoritmo se ha validado mediante la ejecución de numerosos escenarios sintéticos, incluyendo algunos muy complejos, de más de 500 aplicaciones. ABSTRACT The importance of embedded software is growing as it is required for a large number of systems. Devising cheap, efficient and reliable development processes for embedded systems is thus a notable challenge nowadays. Computer processing power is continuously increasing, and as a result, it is currently possible to integrate complex systems in a single processor, which was not feasible a few years ago.Embedded systems may have safety critical requirements. Its failure may result in personal or substantial economical loss. The development of these systems requires stringent development processes that are usually defined by suitable standards. In some cases their certification is also necessary. This scenario fosters the use of mixed-criticality systems in which applications of different criticality levels must coexist in a single system. In these cases, it is usually necessary to certify the whole system, including non-critical applications, which is costly. Virtualization emerges as an enabling technology used for dealing with this problem. The system is structured as a set of partitions, or virtual machines, that can be executed with temporal and spatial isolation. In this way, applications can be developed and certified independently. The development of MCPS (Mixed-Criticality Partitioned Systems) requires additional roles and activities that traditional systems do not require. The system integrator has to define system partitions. Application development has to consider the characteristics of the partition to which it is allocated. In addition, traditional software process models have to be adapted to this scenario. The V-model is commonly used in embedded systems development. It can be adapted to the development of MCPS by enabling the parallel development of applications or adding an additional partition to an existing system. The objective of this PhD is to improve the available technology for MCPS development by providing a framework tailored to the development of this type of system and by defining a flexible and efficient algorithm for automatically generating system partitionings. The goal of the framework is to integrate all the activities required for developing MCPS and to support the different roles involved in this process. The framework is based on MDE (Model-Driven Engineering), which emphasizes the use of models in the development process. The framework provides basic means for modeling the system, generating system partitions, validating the system and generating final artifacts. The framework has been designed to facilitate its extension and the integration of external validation tools. In particular, it can be extended by adding support for additional non-functional requirements and support for final artifacts, such as new programming languages or additional documentation. The framework includes a novel partitioning algorithm. It has been designed to be independent of the types of applications requirements and also to enable the system integrator to tailor the partitioning to the specific requirements of a system. This independence is achieved by defining partitioning constraints that must be met by the resulting partitioning. They have sufficient expressive capacity to state the most common constraints and can be defined manually by the system integrator or generated automatically based on functional and non-functional requirements of the applications. The partitioning algorithm uses system models and partitioning constraints as its inputs. It generates a deployment model that is composed by a set of partitions. Each partition is in turn composed of a set of allocated applications and assigned resources. The partitioning problem, including applications and constraints, is modeled as a colored graph. A valid partitioning is a proper vertex coloring. A specially designed algorithm generates this coloring and is able to provide alternative partitions if required. The framework, including the partitioning algorithm, has been successfully used in the development of two industrial use cases: the UPMSat-2 satellite and the control system of a wind-power turbine. The partitioning algorithm has been successfully validated by using a large number of synthetic loads, including complex scenarios with more that 500 applications.

Real-Time Dynamic PGD Calculation of Non-Linear Soil Behavior

El estudio sísmico en los últimos 50 años y el análisis del comportamiento dinámico del suelo revelan que el comportamiento del suelo es altamente no lineal e histéretico incluso para pequeñas deformaciones. El comportamiento no lineal del suelo durante un evento sísmico tiene un papel predominante en el análisis de la respuesta de sitio. Los análisis unidimensionales de la respuesta sísmica del suelo son a menudo realizados utilizando procedimientos lineales equivalentes, que requieren generalmente pocos parámetros conocidos. Los análisis de respuesta de sitio no lineal tienen el potencial para simular con mayor precisión el comportamiento del suelo, pero su aplicación en la práctica se ha visto limitada debido a la selección de parámetros poco documentadas y poco claras, así como una inadecuada documentación de los beneficios del modelado no lineal en relación al modelado lineal equivalente. En el análisis del suelo, el comportamiento del suelo es aproximado como un sólido Kelvin-Voigt con un módulo de corte elástico y amortiguamiento viscoso. En el análisis lineal y no lineal del suelo se están considerando geometrías y modelos reológicos más complejos. El primero está siendo dirigido por considerar parametrizaciones más ricas del comportamiento linealizado y el segundo mediante el uso de multi-modo de los elementos de resorte-amortiguador con un eventual amortiguador fraccional. El uso del cálculo fraccional está motivado en gran parte por el hecho de que se requieren menos parámetros para lograr la aproximación exacta a los datos experimentales. Basándose en el modelo de Kelvin-Voigt, la viscoelasticidad es revisada desde su formulación más estándar a algunas descripciones más avanzada que implica la amortiguación dependiente de la frecuencia (o viscosidad), analizando los efectos de considerar derivados fraccionarios para representar esas contribuciones viscosas. Vamos a demostrar que tal elección se traduce en modelos más ricos que pueden adaptarse a diferentes limitaciones relacionadas con la potencia disipada, amplitud de la respuesta y el ángulo de fase. Por otra parte, el uso de derivados fraccionarios permite acomodar en paralelo, dentro de un análogo de Kelvin-Voigt generalizado, muchos amortiguadores que contribuyen a aumentar la flexibilidad del modelado para la descripción de los resultados experimentales. Obviamente estos modelos ricos implican muchos parámetros, los asociados con el comportamiento y los relacionados con los derivados fraccionarios. El análisis paramétrico de estos modelos requiere técnicas numéricas eficientemente capaces de simular comportamientos complejos. El método de la Descomposición Propia Generalizada (PGD) es el candidato perfecto para la construcción de este tipo de soluciones paramétricas. Podemos calcular off-line la solución paramétrica para el depósito de suelo, para todos los parámetros del modelo, tan pronto como tales soluciones paramétricas están disponibles, el problema puede ser resuelto en tiempo real, porque no se necesita ningún nuevo cálculo, el solucionador sólo necesita particularizar on-line la solución paramétrica calculada off-line, que aliviará significativamente el procedimiento de solución. En el marco de la PGD, parámetros de los materiales y los diferentes poderes de derivación podrían introducirse como extra-coordenadas en el procedimiento de solución. El cálculo fraccional y el nuevo método de reducción modelo llamado Descomposición Propia Generalizada han sido aplicado en esta tesis tanto al análisis lineal como al análisis no lineal de la respuesta del suelo utilizando un método lineal equivalente. ABSTRACT Studies of earthquakes over the last 50 years and the examination of dynamic soil behavior reveal that soil behavior is highly nonlinear and hysteretic even at small strains. Nonlinear behavior of soils during a seismic event has a predominant role in current site response analysis. One-dimensional seismic ground response analysis are often performed using equivalent-linear procedures, which require few, generally well-known parameters. Nonlinear analyses have the potential to more accurately simulate soil behavior, but their implementation in practice has been limited because of poorly documented and unclear parameter selection, as well as inadequate documentation of the benefits of nonlinear modeling relative to equivalent linear modeling. In soil analysis, soil behaviour is approximated as a Kelvin-Voigt solid with a elastic shear modulus and viscous damping. In linear and nonlinear analysis more complex geometries and more complex rheological models are being considered. The first is being addressed by considering richer parametrizations of the linearized behavior and the second by using multi-mode spring-dashpot elements with eventual fractional damping. The use of fractional calculus is motivated in large part by the fact that fewer parameters are required to achieve accurate approximation of experimental data. Based in Kelvin-Voigt model the viscoelastodynamics is revisited from its most standard formulation to some more advanced description involving frequency-dependent damping (or viscosity), analyzing the effects of considering fractional derivatives for representing such viscous contributions. We will prove that such a choice results in richer models that can accommodate different constraints related to the dissipated power, response amplitude and phase angle. Moreover, the use of fractional derivatives allows to accommodate in parallel, within a generalized Kelvin-Voigt analog, many dashpots that contribute to increase the modeling flexibility for describing experimental findings. Obviously these rich models involve many parameters, the ones associated with the behavior and the ones related to the fractional derivatives. The parametric analysis of all these models require efficient numerical techniques able to simulate complex behaviors. The Proper Generalized Decomposition (PGD) is the perfect candidate for producing such kind of parametric solutions. We can compute off-line the parametric solution for the soil deposit, for all parameter of the model, as soon as such parametric solutions are available, the problem can be solved in real time because no new calculation is needed, the solver only needs particularize on-line the parametric solution calculated off-line, which will alleviate significantly the solution procedure. Within the PGD framework material parameters and the different derivation powers could be introduced as extra-coordinates in the solution procedure. Fractional calculus and the new model reduction method called Proper Generalized Decomposition has been applied in this thesis to the linear analysis and nonlinear soil response analysis using a equivalent linear method.

Real-time quantitative measurement of autocrine ligand binding indicates that autocrine loops are spatially localized

Autocrine ligands are important regulators of many normal tissues and have been implicated in a number of disease states, including cancer. However, because by definition autocrine ligands are synthesized, secreted, and bound to cell receptors within an intrinsically self-contained “loop,” standard pharmacological approaches cannot be used to investigate relationships between ligand/receptor binding and consequent cellular responses. We demonstrate here a new approach for measurement of autocrine ligand binding to cells, using a microphysiometer assay originally developed for investigating cell responses to exogenous ligands. This technique permits quantitative measurements of autocrine responses on the time scale of receptor binding and internalization, thus allowing investigation of the role of receptor trafficking and dynamics in cellular responses. We used this technique to investigate autocrine signaling through the epidermal growth factor receptor by transforming growth factor alpha (TGFα) and found that anti-receptor antibodies are far more effective than anti-ligand antibodies in inhibiting autocrine signaling. This result indicates that autocrine-based signals can operate in a spatially restricted, local manner and thus provide cells with information on their local microenvironment.

Real-time detection of DNA hybridization and melting on oligonucleotide arrays by using optical wave guides.

The challenge of the Human Genome Project is to increase the rate of DNA sequence acquisition by two orders of magnitude to complete sequencing of the human genome by the year 2000. The present work describes a rapid detection method using a two-dimensional optical wave guide that allows measurement of real-time binding or melting of a light-scattering label on a DNA array. A particulate label on the target DNA acts as a light-scattering source when illuminated by the evanescent wave of the wave guide and only the label bound to the surface generates a signal. Imaging/visual examination of the scattered light permits interrogation of the entire array simultaneously. Hybridization specificity is equivalent to that obtained with a conventional system using autoradiography. Wave guide melting curves are consistent with those obtained in the liquid phase and single-base discrimination is facile. Dilution experiments showed an apparent lower limit of detection at 0.4 nM oligonucleotide. This performance is comparable to the best currently known fluorescence-based systems. In addition, wave guide detection allows manipulation of hybridization stringency during detection and thereby reduces DNA chip complexity. It is anticipated that this methodology will provide a powerful tool for diagnostic applications that require rapid cost-effective detection of variations from known sequences.

Real time optimization in chemical process: evaluation of strategies, improvements and industrial application.

The increasing economic competition drives the industry to implement tools that improve their processes efficiencies. The process automation is one of these tools, and the Real Time Optimization (RTO) is an automation methodology that considers economic aspects to update the process control in accordance with market prices and disturbances. Basically, RTO uses a steady-state phenomenological model to predict the process behavior, and then, optimizes an economic objective function subject to this model. Although largely implemented in industry, there is not a general agreement about the benefits of implementing RTO due to some limitations discussed in the present work: structural plant/model mismatch, identifiability issues and low frequency of set points update. Some alternative RTO approaches have been proposed in literature to handle the problem of structural plant/model mismatch. However, there is not a sensible comparison evaluating the scope and limitations of these RTO approaches under different aspects. For this reason, the classical two-step method is compared to more recently derivative-based methods (Modifier Adaptation, Integrated System Optimization and Parameter estimation, and Sufficient Conditions of Feasibility and Optimality) using a Monte Carlo methodology. The results of this comparison show that the classical RTO method is consistent, providing a model flexible enough to represent the process topology, a parameter estimation method appropriate to handle measurement noise characteristics and a method to improve the sample information quality. At each iteration, the RTO methodology updates some key parameter of the model, where it is possible to observe identifiability issues caused by lack of measurements and measurement noise, resulting in bad prediction ability. Therefore, four different parameter estimation approaches (Rotational Discrimination, Automatic Selection and Parameter estimation, Reparametrization via Differential Geometry and classical nonlinear Least Square) are evaluated with respect to their prediction accuracy, robustness and speed. The results show that the Rotational Discrimination method is the most suitable to be implemented in a RTO framework, since it requires less a priori information, it is simple to be implemented and avoid the overfitting caused by the Least Square method. The third RTO drawback discussed in the present thesis is the low frequency of set points update, this problem increases the period in which the process operates at suboptimum conditions. An alternative to handle this problem is proposed in this thesis, by integrating the classic RTO and Self-Optimizing control (SOC) using a new Model Predictive Control strategy. The new approach demonstrates that it is possible to reduce the problem of low frequency of set points updates, improving the economic performance. Finally, the practical aspects of the RTO implementation are carried out in an industrial case study, a Vapor Recompression Distillation (VRD) process located in Paulínea refinery from Petrobras. The conclusions of this study suggest that the model parameters are successfully estimated by the Rotational Discrimination method; the RTO is able to improve the process profit in about 3%, equivalent to 2 million dollars per year; and the integration of SOC and RTO may be an interesting control alternative for the VRD process.

Real-time 3D semi-local surface patch extraction using GPGPU

Feature vectors can be anything from simple surface normals to more complex feature descriptors. Feature extraction is important to solve various computer vision problems: e.g. registration, object recognition and scene understanding. Most of these techniques cannot be computed online due to their complexity and the context where they are applied. Therefore, computing these features in real-time for many points in the scene is impossible. In this work, a hardware-based implementation of 3D feature extraction and 3D object recognition is proposed to accelerate these methods and therefore the entire pipeline of RGBD based computer vision systems where such features are typically used. The use of a GPU as a general purpose processor can achieve considerable speed-ups compared with a CPU implementation. In this work, advantageous results are obtained using the GPU to accelerate the computation of a 3D descriptor based on the calculation of 3D semi-local surface patches of partial views. This allows descriptor computation at several points of a scene in real-time. Benefits of the accelerated descriptor have been demonstrated in object recognition tasks. Source code will be made publicly available as contribution to the Open Source Point Cloud Library.

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.