Brain structures identification based on feature descriptor

Traumatic Brain Injury -TBI- -1- is defined as an acute event that causes certain damage to areas of the brain. TBI may result in a significant impairment of an individuals physical, cognitive and psychosocial functioning. The main consequence of TBI is a dramatic change in the individuals daily life involving a profound disruption of the family, a loss of future income capacity and an increase of lifetime cost. One of the main challenges of TBI Neuroimaging is to develop robust automated image analysis methods to detect signatures of TBI, such as: hyper-intensity areas, changes in image contrast and in brain shape. The final goal of this research is to develop a method to identify the altered brain structures by automatically detecting landmarks on the image where signal changes and to provide comprehensive information to the clinician about them. These landmarks identify injured structures by co-registering the patient?s image with an atlas where landmarks have been previously detected. The research work has been initiated by identifying brain structures on healthy subjects to validate the proposed method. Later, this method will be used to identify modified structures on TBI imaging studies.

MIA - a free and open source software for gray scale medical image analysis

Background Gray scale images make the bulk of data in bio-medical image analysis, and hence, the main focus of many image processing tasks lies in the processing of these monochrome images. With ever improving acquisition devices, spatial and temporal image resolution increases, and data sets become very large. Various image processing frameworks exists that make the development of new algorithms easy by using high level programming languages or visual programming. These frameworks are also accessable to researchers that have no background or little in software development because they take care of otherwise complex tasks. Specifically, the management of working memory is taken care of automatically, usually at the price of requiring more it. As a result, processing large data sets with these tools becomes increasingly difficult on work station class computers. One alternative to using these high level processing tools is the development of new algorithms in a languages like C++, that gives the developer full control over how memory is handled, but the resulting workflow for the prototyping of new algorithms is rather time intensive, and also not appropriate for a researcher with little or no knowledge in software development. Another alternative is in using command line tools that run image processing tasks, use the hard disk to store intermediate results, and provide automation by using shell scripts. Although not as convenient as, e.g. visual programming, this approach is still accessable to researchers without a background in computer science. However, only few tools exist that provide this kind of processing interface, they are usually quite task specific, and don’t provide an clear approach when one wants to shape a new command line tool from a prototype shell script. Results The proposed framework, MIA, provides a combination of command line tools, plug-ins, and libraries that make it possible to run image processing tasks interactively in a command shell and to prototype by using the according shell scripting language. Since the hard disk becomes the temporal storage memory management is usually a non-issue in the prototyping phase. By using string-based descriptions for filters, optimizers, and the likes, the transition from shell scripts to full fledged programs implemented in C++ is also made easy. In addition, its design based on atomic plug-ins and single tasks command line tools makes it easy to extend MIA, usually without the requirement to touch or recompile existing code. Conclusion In this article, we describe the general design of MIA, a general purpouse framework for gray scale image processing. We demonstrated the applicability of the software with example applications from three different research scenarios, namely motion compensation in myocardial perfusion imaging, the processing of high resolution image data that arises in virtual anthropology, and retrospective analysis of treatment outcome in orthognathic surgery. With MIA prototyping algorithms by using shell scripts that combine small, single-task command line tools is a viable alternative to the use of high level languages, an approach that is especially useful when large data sets need to be processed.

Massively parallelizable list-mode reconstruction using a Monte Carlo-based elliptical Gaussian model

Purpose: A fully three-dimensional (3D) massively parallelizable list-mode ordered-subsets expectation-maximization (LM-OSEM) reconstruction algorithm has been developed for high-resolution PET cameras. System response probabilities are calculated online from a set of parameters derived from Monte Carlo simulations. The shape of a system response for a given line of response (LOR) has been shown to be asymmetrical around the LOR. This work has been focused on the development of efficient region-search techniques to sample the system response probabilities, which are suitable for asymmetric kernel models, including elliptical Gaussian models that allow for high accuracy and high parallelization efficiency. The novel region-search scheme using variable kernel models is applied in the proposed PET reconstruction algorithm. Methods: A novel region-search technique has been used to sample the probability density function in correspondence with a small dynamic subset of the field of view that constitutes the region of response (ROR). The ROR is identified around the LOR by searching for any voxel within a dynamically calculated contour. The contour condition is currently defined as a fixed threshold over the posterior probability, and arbitrary kernel models can be applied using a numerical approach. The processing of the LORs is distributed in batches among the available computing devices, then, individual LORs are processed within different processing units. In this way, both multicore and multiple many-core processing units can be efficiently exploited. Tests have been conducted with probability models that take into account the noncolinearity, positron range, and crystal penetration effects, that produced tubes of response with varying elliptical sections whose axes were a function of the crystal's thickness and angle of incidence of the given LOR. The algorithm treats the probability model as a 3D scalar field defined within a reference system aligned with the ideal LOR. Results: This new technique provides superior image quality in terms of signal-to-noise ratio as compared with the histogram-mode method based on precomputed system matrices available for a commercial small animal scanner. Reconstruction times can be kept low with the use of multicore, many-core architectures, including multiple graphic processing units. Conclusions: A highly parallelizable LM reconstruction method has been proposed based on Monte Carlo simulations and new parallelization techniques aimed at improving the reconstruction speed and the image signal-to-noise of a given OSEM algorithm. The method has been validated using simulated and real phantoms. A special advantage of the new method is the possibility of defining dynamically the cut-off threshold over the calculated probabilities thus allowing for a direct control on the trade-off between speed and quality during the reconstruction.

Higher-order regularization and morphological techniques for image segmentation

La segmentación de imágenes es un campo importante de la visión computacional y una de las áreas de investigación más activas, con aplicaciones en comprensión de imágenes, detección de objetos, reconocimiento facial, vigilancia de vídeo o procesamiento de imagen médica. La segmentación de imágenes es un problema difícil en general, pero especialmente en entornos científicos y biomédicos, donde las técnicas de adquisición imagen proporcionan imágenes ruidosas. Además, en muchos de estos casos se necesita una precisión casi perfecta. En esta tesis, revisamos y comparamos primero algunas de las técnicas ampliamente usadas para la segmentación de imágenes médicas. Estas técnicas usan clasificadores a nivel de pixel e introducen regularización sobre pares de píxeles que es normalmente insuficiente. Estudiamos las dificultades que presentan para capturar la información de alto nivel sobre los objetos a segmentar. Esta deficiencia da lugar a detecciones erróneas, bordes irregulares, configuraciones con topología errónea y formas inválidas. Para solucionar estos problemas, proponemos un nuevo método de regularización de alto nivel que aprende información topológica y de forma a partir de los datos de entrenamiento de una forma no paramétrica usando potenciales de orden superior. Los potenciales de orden superior se están popularizando en visión por computador, pero la representación exacta de un potencial de orden superior definido sobre muchas variables es computacionalmente inviable. Usamos una representación compacta de los potenciales basada en un conjunto finito de patrones aprendidos de los datos de entrenamiento que, a su vez, depende de las observaciones. Gracias a esta representación, los potenciales de orden superior pueden ser convertidos a potenciales de orden 2 con algunas variables auxiliares añadidas. Experimentos con imágenes reales y sintéticas confirman que nuestro modelo soluciona los errores de aproximaciones más débiles. Incluso con una regularización de alto nivel, una precisión exacta es inalcanzable, y se requeire de edición manual de los resultados de la segmentación automática. La edición manual es tediosa y pesada, y cualquier herramienta de ayuda es muy apreciada. Estas herramientas necesitan ser precisas, pero también lo suficientemente rápidas para ser usadas de forma interactiva. Los contornos activos son una buena solución: son buenos para detecciones precisas de fronteras y, en lugar de buscar una solución global, proporcionan un ajuste fino a resultados que ya existían previamente. Sin embargo, requieren una representación implícita que les permita trabajar con cambios topológicos del contorno, y esto da lugar a ecuaciones en derivadas parciales (EDP) que son costosas de resolver computacionalmente y pueden presentar problemas de estabilidad numérica. Presentamos una aproximación morfológica a la evolución de contornos basada en un nuevo operador morfológico de curvatura que es válido para superficies de cualquier dimensión. Aproximamos la solución numérica de la EDP de la evolución de contorno mediante la aplicación sucesiva de un conjunto de operadores morfológicos aplicados sobre una función de conjuntos de nivel. Estos operadores son muy rápidos, no sufren de problemas de estabilidad numérica y no degradan la función de los conjuntos de nivel, de modo que no hay necesidad de reinicializarlo. Además, su implementación es mucho más sencilla que la de las EDP, ya que no requieren usar sofisticados algoritmos numéricos. Desde un punto de vista teórico, profundizamos en las conexiones entre operadores morfológicos y diferenciales, e introducimos nuevos resultados en este área. Validamos nuestra aproximación proporcionando una implementación morfológica de los contornos geodésicos activos, los contornos activos sin bordes, y los turbopíxeles. En los experimentos realizados, las implementaciones morfológicas convergen a soluciones equivalentes a aquéllas logradas mediante soluciones numéricas tradicionales, pero con ganancias significativas en simplicidad, velocidad y estabilidad. ABSTRACT Image segmentation is an important field in computer vision and one of its most active research areas, with applications in image understanding, object detection, face recognition, video surveillance or medical image processing. Image segmentation is a challenging problem in general, but especially in the biological and medical image fields, where the imaging techniques usually produce cluttered and noisy images and near-perfect accuracy is required in many cases. In this thesis we first review and compare some standard techniques widely used for medical image segmentation. These techniques use pixel-wise classifiers and introduce weak pairwise regularization which is insufficient in many cases. We study their difficulties to capture high-level structural information about the objects to segment. This deficiency leads to many erroneous detections, ragged boundaries, incorrect topological configurations and wrong shapes. To deal with these problems, we propose a new regularization method that learns shape and topological information from training data in a nonparametric way using high-order potentials. High-order potentials are becoming increasingly popular in computer vision. However, the exact representation of a general higher order potential defined over many variables is computationally infeasible. We use a compact representation of the potentials based on a finite set of patterns learned fromtraining data that, in turn, depends on the observations. Thanks to this representation, high-order potentials can be converted into pairwise potentials with some added auxiliary variables and minimized with tree-reweighted message passing (TRW) and belief propagation (BP) techniques. Both synthetic and real experiments confirm that our model fixes the errors of weaker approaches. Even with high-level regularization, perfect accuracy is still unattainable, and human editing of the segmentation results is necessary. The manual edition is tedious and cumbersome, and tools that assist the user are greatly appreciated. These tools need to be precise, but also fast enough to be used in real-time. Active contours are a good solution: they are good for precise boundary detection and, instead of finding a global solution, they provide a fine tuning to previously existing results. However, they require an implicit representation to deal with topological changes of the contour, and this leads to PDEs that are computationally costly to solve and may present numerical stability issues. We present a morphological approach to contour evolution based on a new curvature morphological operator valid for surfaces of any dimension. We approximate the numerical solution of the contour evolution PDE by the successive application of a set of morphological operators defined on a binary level-set. These operators are very fast, do not suffer numerical stability issues, and do not degrade the level set function, so there is no need to reinitialize it. Moreover, their implementation is much easier than their PDE counterpart, since they do not require the use of sophisticated numerical algorithms. From a theoretical point of view, we delve into the connections between differential andmorphological operators, and introduce novel results in this area. We validate the approach providing amorphological implementation of the geodesic active contours, the active contours without borders, and turbopixels. In the experiments conducted, the morphological implementations converge to solutions equivalent to those achieved by traditional numerical solutions, but with significant gains in simplicity, speed, and stability.

A novel FPGA-based evolvable hardware system based on multiple processing arrays

In this paper, an architecture based on a scalable and flexible set of Evolvable Processing arrays is presented. FPGA-native Dynamic Partial Reconfiguration (DPR) is used for evolution, which is done intrinsically, letting the system to adapt autonomously to variable run-time conditions, including the presence of transient and permanent faults. The architecture supports different modes of operation, namely: independent, parallel, cascaded or bypass mode. These modes of operation can be used during evolution time or during normal operation. The evolvability of the architecture is combined with fault-tolerance techniques, to enhance the platform with self-healing features, making it suitable for applications which require both high adaptability and reliability. Experimental results show that such a system may benefit from accelerated evolution times, increased performance and improved dependability, mainly by increasing fault tolerance for transient and permanent faults, as well as providing some fault identification possibilities. The evolvable HW array shown is tailored for window-based image processing applications.

Evaluation of cover crops based on characteristics of nitrogen use, and aerial and root growth

La caracterización de los cultivos cubierta (cover crops) puede permitir comparar la idoneidad de diferentes especies para proporcionar servicios ecológicos como el control de la erosión, el reciclado de nutrientes o la producción de forrajes. En este trabajo se estudiaron bajo condiciones de campo diferentes técnicas para caracterizar el dosel vegetal con objeto de establecer una metodología para medir y comparar las arquitecturas de los cultivos cubierta más comunes. Se estableció un ensayo de campo en Madrid (España central) para determinar la relación entre el índice de área foliar (LAI) y la cobertura del suelo (GC) para un cultivo de gramínea, uno de leguminosa y uno de crucífera. Para ello se sembraron doce parcelas con cebada (Hordeum vulgare L.), veza (Vicia sativa L.), y colza (Brassica napus L.). En 10 fechas de muestreo se midieron el LAI (con estimaciones directas y del LAI-2000), la fracción interceptada de la radiación fotosintéticamente activa (FIPAR) y la GC. Un experimento de campo de dos años (Octubre-Abril) se estableció en la misma localización para evaluar diferentes especies (Hordeum vulgare L., Secale cereale L., x Triticosecale Whim, Sinapis alba L., Vicia sativa L.) y cultivares (20) en relación con su idoneidad para ser usadas como cultivos cubierta. La GC se monitorizó mediante análisis de imágenes digitales con 21 y 22 muestreos, y la biomasa se midió 8 y 10 veces, respectivamente para cada año. Un modelo de Gompertz caracterizó la cobertura del suelo hasta el decaimiento observado tras las heladas, mientras que la biomasa se ajustó a ecuaciones de Gompertz, logísticas y lineales-exponenciales. Al final del experimento se determinaron el C, el N y el contenido en fibra (neutrodetergente, ácidodetergente y lignina), así como el N fijado por las leguminosas. Se aplicó el análisis de decisión multicriterio (MCDA) con objeto de obtener un ranking de especies y cultivares de acuerdo con su idoneidad para actuar como cultivos cubierta en cuatro modalidades diferentes: cultivo de cobertura, cultivo captura, abono verde y forraje. Las asociaciones de cultivos leguminosas con no leguminosas pueden afectar al crecimiento radicular y a la absorción de N de ambos componentes de la mezcla. El conocimiento de cómo los sistemas radiculares específicos afectan al crecimiento individual de las especies es útil para entender las interacciones en las asociaciones, así como para planificar estrategias de cultivos cubierta. En un tercer ensayo se combinaron estudios en rhizotrones con extracción de raíces e identificación de especies por microscopía, así como con estudios de crecimiento, absorción de N y 15N en capas profundas del suelo. Las interacciones entre raíces en su crecimiento y en el aprovisionamiento de N se estudiaron para dos de los cultivares mejor valorados en el estudio previo: uno de cebada (Hordeum vulgare L. cv. Hispanic) y otro de veza (Vicia sativa L. cv. Aitana). Se añadió N en dosis de 0 (N0), 50 (N1) y 150 (N2) kg N ha-1. Como resultados del primer estudio, se ajustaron correctamente modelos lineales y cuadráticos a la relación entre la GC y el LAI para todos los cultivos, pero en la gramínea alcanzaron una meseta para un LAI>4. Antes de alcanzar la cobertura total, la pendiente de la relación lineal entre ambas variables se situó en un rango entre 0.025 y 0.030. Las lecturas del LAI-2000 estuvieron correlacionadas linealmente con el LAI, aunque con tendencia a la sobreestimación. Las correcciones basadas en el efecto de aglutinación redujeron el error cuadrático medio del LAI estimado por el LAI-2000 desde 1.2 hasta 0.5 para la crucífera y la leguminosa, no siendo efectivas para la cebada. Esto determinó que para los siguientes estudios se midieran únicamente la GC y la biomasa. En el segundo experimento, las gramíneas alcanzaron la mayor cobertura del suelo (83-99%) y la mayor biomasa (1226-1928 g m-2) al final del mismo. Con la mayor relación C/N (27-39) y contenido en fibra digestible (53-60%) y la menor calidad de residuo (~68%). La mostaza presentó elevadas GC, biomasa y absorción de N en el año más templado en similitud con las gramíneas, aunque escasa calidad como forraje en ambos años. La veza presentó la menor absorción de N (2.4-0.7 g N m-2) debido a la fijación de N (9.8-1.6 g N m-2) y escasa acumulación de N. El tiempo térmico hasta alcanzar el 30% de GC constituyó un buen indicador de especies de rápida cubrición. La cuantificación de las variables permitió hallar variabilidad entre las especies y proporcionó información para posteriores decisiones sobre la selección y manejo de los cultivos cubierta. La agregación de dichas variables a través de funciones de utilidad permitió confeccionar rankings de especies y cultivares para cada uso. Las gramíneas fueron las más indicadas para los usos de cultivo de cobertura, cultivo captura y forraje, mientras que las vezas fueron las mejor como abono verde. La mostaza alcanzó altos valores como cultivo de cobertura y captura en el primer año, pero el segundo decayó debido a su pobre actuación en los inviernos fríos. Hispanic fue el mejor cultivar de cebada como cultivo de cobertura y captura, mientras que Albacete como forraje. El triticale Titania alcanzó la posición más alta como cultiva de cobertura, captura y forraje. Las vezas Aitana y BGE014897 mostraron buenas aptitudes como abono verde y cultivo captura. El MCDA permitió la comparación entre especies y cultivares proporcionando información relevante para la selección y manejo de cultivos cubierta. En el estudio en rhizotrones tanto la mezcla de especies como la cebada alcanzaron mayor intensidad de raíces (RI) y profundidad (RD) que la veza, con valores alrededor de 150 cruces m-1 y 1.4 m respectivamente, comparados con 50 cruces m-1 y 0.9 m para la veza. En las capas más profundas del suelo, la asociación de cultivos mostró valores de RI ligeramente mayores que la cebada en monocultivo. La cebada y la asociación obtuvieron mayores valores de densidad de raíces (RLD) (200-600 m m-3) que la veza (25-130) entre 0.8 y 1.2 m de profundidad. Los niveles de N no mostraron efectos claros en RI, RD ó RLD, sin embargo, el incremento de N favoreció la proliferación de raíces de veza en la asociación en capas profundas del suelo, con un ratio cebada/veza situado entre 25 a N0 y 5 a N2. La absorción de N de la cebada se incrementó en la asociación a expensas de la veza (de ~100 a 200 mg planta-1). Las raíces de cebada en la asociación absorbieron también más nitrógeno marcado de las capas profundas del suelo (0.6 mg 15N planta-1) que en el monocultivo (0.3 mg 15N planta-1). ABSTRACT Cover crop characterization may allow comparing the suitability of different species to provide ecological services such as erosion control, nutrient recycling or fodder production. Different techniques to characterize plant canopy were studied under field conditions in order to establish a methodology for measuring and comparing cover crops canopies. A field trial was established in Madrid (central Spain) to determine the relationship between leaf area index (LAI) and ground cover (GC) in a grass, a legume and a crucifer crop. Twelve plots were sown with either barley (Hordeum vulgare L.), vetch (Vicia sativa L.), or rape (Brassica napus L.). On 10 sampling dates the LAI (both direct and LAI-2000 estimations), fraction intercepted of photosynthetically active radiation (FIPAR) and GC were measured. A two-year field experiment (October-April) was established in the same location to evaluate different species (Hordeum vulgare L., Secale cereale L., x Triticosecale Whim, Sinapis alba L., Vicia sativa L.) and cultivars (20) according to their suitability to be used as cover crops. GC was monitored through digital image analysis with 21 and 22 samples, and biomass measured 8 and 10 times, respectively for each season. A Gompertz model characterized ground cover until the decay observed after frosts, while biomass was fitted to Gompertz, logistic and linear-exponential equations. At the end of the experiment C, N, and fiber (neutral detergent, acid and lignin) contents, and the N fixed by the legumes were determined. Multicriteria decision analysis (MCDA) was applied in order to rank the species and cultivars according to their suitability to perform as cover crops in four different modalities: cover crop, catch crop, green manure and fodder. Intercropping legumes and non-legumes may affect the root growth and N uptake of both components in the mixture. The knowledge of how specific root systems affect the growth of the individual species is useful for understanding the interactions in intercrops as well as for planning cover cropping strategies. In a third trial rhizotron studies were combined with root extraction and species identification by microscopy and with studies of growth, N uptake and 15N uptake from deeper soil layers. The root interactions of root growth and N foraging were studied for two of the best ranked cultivars in the previous study: a barley (Hordeum vulgare L. cv. Hispanic) and a vetch (Vicia sativa L. cv. Aitana). N was added at 0 (N0), 50 (N1) and 150 (N2) kg N ha-1. As a result, linear and quadratic models fitted to the relationship between the GC and LAI for all of the crops, but they reached a plateau in the grass when the LAI > 4. Before reaching full cover, the slope of the linear relationship between both variables was within the range of 0.025 to 0.030. The LAI-2000 readings were linearly correlated with the LAI but they tended to overestimation. Corrections based on the clumping effect reduced the root mean square error of the estimated LAI from the LAI-2000 readings from 1.2 to less than 0.50 for the crucifer and the legume, but were not effective for barley. This determined that in the following studies only the GC and biomass were measured. In the second experiment, the grasses reached the highest ground cover (83- 99%) and biomass (1226-1928 g/m2) at the end of the experiment. The grasses had the highest C/N ratio (27-39) and dietary fiber (53-60%) and the lowest residue quality (~68%). The mustard presented high GC, biomass and N uptake in the warmer year with similarity to grasses, but low fodder capability in both years. The vetch presented the lowest N uptake (2.4-0.7 g N/m2) due to N fixation (9.8-1.6 g N/m2) and low biomass accumulation. The thermal time until reaching 30% ground cover was a good indicator of early coverage species. Variable quantification allowed finding variability among the species and provided information for further decisions involving cover crops selection and management. Aggregation of these variables through utility functions allowed ranking species and cultivars for each usage. Grasses were the most suitable for the cover crop, catch crop and fodder uses, while the vetches were the best as green manures. The mustard attained high ranks as cover and catch crop the first season, but the second decayed due to low performance in cold winters. Hispanic was the most suitable barley cultivar as cover and catch crop, and Albacete as fodder. The triticale Titania attained the highest rank as cover and catch crop and fodder. Vetches Aitana and BGE014897 showed good aptitudes as green manures and catch crops. MCDA allowed comparison among species and cultivars and might provide relevant information for cover crops selection and management. In the rhizotron study the intercrop and the barley attained slightly higher root intensity (RI) and root depth (RD) than the vetch, with values around 150 crosses m-1 and 1.4 m respectively, compared to 50 crosses m-1 and 0.9 m for the vetch. At deep soil layers, intercropping showed slightly larger RI values compared to the sole cropped barley. The barley and the intercropping had larger root length density (RLD) values (200-600 m m-3) than the vetch (25-130) at 0.8-1.2 m depth. The topsoil N supply did not show a clear effect on the RI, RD or RLD; however increasing topsoil N favored the proliferation of vetch roots in the intercropping at deep soil layers, with the barley/vetch root ratio ranging from 25 at N0 to 5 at N2. The N uptake of the barley was enhanced in the intercropping at the expense of the vetch (from ~100 mg plant-1 to 200). The intercropped barley roots took up more labeled nitrogen (0.6 mg 15N plant-1) than the sole-cropped barley roots (0.3 mg 15N plant-1) from deep layers.

Multi-resolution model-based traffic sign detection and tracking

In this paper we propose an innovative approach to tackle the problem of traffic sign detection using a computer vision algorithm and taking into account real-time operation constraints, trying to establish intelligent strategies to simplify as much as possible the algorithm complexity and to speed up the process. Firstly, a set of candidates is generated according to a color segmentation stage, followed by a region analysis strategy, where spatial characteristic of previously detected objects are taken into account. Finally, temporal coherence is introduced by means of a tracking scheme, performed using a Kalman filter for each potential candidate. Taking into consideration time constraints, efficiency is achieved two-fold: on the one side, a multi-resolution strategy is adopted for segmentation, where global operation will be applied only to low-resolution images, increasing the resolution to the maximum only when a potential road sign is being tracked. On the other side, we take advantage of the expected spacing between traffic signs. Namely, the tracking of objects of interest allows to generate inhibition areas, which are those ones where no new traffic signs are expected to appear due to the existence of a TS in the neighborhood. The proposed solution has been tested with real sequences in both urban areas and highways, and proved to achieve higher computational efficiency, especially as a result of the multi-resolution approach.

Region-dependent vehicle classification using PCA features

Video-based vehicle detection is the focus of increasing interest due to its potential towards collision avoidance. In particular, vehicle verification is especially challenging due to the enormous variability of vehicles in size, color, pose, etc. In this paper, a new approach based on supervised learning using Principal Component Analysis (PCA) is proposed that addresses the main limitations of existing methods. Namely, in contrast to classical approaches which train a single classifier regardless of the relative position of the candidate (thus ignoring valuable pose information), a region-dependent analysis is performed by considering four different areas. In addition, a study on the evolution of the classification performance according to the dimensionality of the principal subspace is carried out using PCA features within a SVM-based classification scheme. Indeed, the experiments performed on a publicly available database prove that PCA dimensionality requirements are region-dependent. Hence, in this work, the optimal configuration is adapted to each of them, rendering very good vehicle verification results.

Adaptive protection scheme for MVC-encoded stereoscopic video streaming in IP-based networks

We present an adaptive unequal error protection (UEP) strategy built on the 1-D interleaved parity Application Layer Forward Error Correction (AL-FEC) code for protecting the transmission of stereoscopic 3D video content encoded with Multiview Video Coding (MVC) through IP-based networks. Our scheme targets the minimization of quality degradation produced by packet losses during video transmission in time-sensitive application scenarios. To that end, based on a novel packet-level distortion model, it selects in real time the most suitable packets within each Group of Pictures (GOP) to be protected and the most convenient FEC technique parameters, i.e., the size of the FEC generator matrix. In order to make these decisions, it considers the relevance of the packet, the behavior of the channel, and the available bitrate for protection purposes. Simulation results validate both the distortion model introduced to estimate the importance of packets and the optimization of the FEC technique parameter values.

A Semantic-Based Approach to Attain Reproducibility of Computational Environments in Scientic Work ows: A Case Study

Reproducible research in scientic work ows is often addressed by tracking the provenance of the produced results. While this approach allows inspecting intermediate and nal results, improves understanding, and permits replaying a work ow execution, it does not ensure that the computational environment is available for subsequent executions to reproduce the experiment. In this work, we propose describing the resources involved in the execution of an experiment using a set of semantic vocabularies, so as to conserve the computational environment. We dene a process for documenting the work ow application, management system, and their dependencies based on 4 domain ontologies. We then conduct an experimental evaluation sing a real work ow application on an academic and a public Cloud platform. Results show that our approach can reproduce an equivalent execution environment of a predened virtual machine image on both computing platforms.

Automatic expert system based on images for accuracy crop row detection in maize fields

This paper proposes an automatic expert system for accuracy crop row detection in maize fields based on images acquired from a vision system. Different applications in maize, particularly those based on site specific treatments, require the identification of the crop rows. The vision system is designed with a defined geometry and installed onboard a mobile agricultural vehicle, i.e. submitted to vibrations, gyros or uncontrolled movements. Crop rows can be estimated by applying geometrical parameters under image perspective projection. Because of the above undesired effects, most often, the estimation results inaccurate as compared to the real crop rows. The proposed expert system exploits the human knowledge which is mapped into two modules based on image processing techniques. The first one is intended for separating green plants (crops and weeds) from the rest (soil, stones and others). The second one is based on the system geometry where the expected crop lines are mapped onto the image and then a correction is applied through the well-tested and robust Theil–Sen estimator in order to adjust them to the real ones. Its performance is favorably compared against the classical Pearson product–moment correlation coefficient.

Self-organizing cultured neural networks: Image analysis techniques for longitudinal tracking and modeling of the underlying network structure

Esta tesis estudia la evolución estructural de conjuntos de neuronas como la capacidad de auto-organización desde conjuntos de neuronas separadas hasta que forman una red (clusterizada) compleja. Esta tesis contribuye con el diseño e implementación de un algoritmo no supervisado de segmentación basado en grafos con un coste computacional muy bajo. Este algoritmo proporciona de forma automática la estructura completa de la red a partir de imágenes de cultivos neuronales tomadas con microscopios de fase con una resolución muy alta. La estructura de la red es representada mediante un objeto matemático (matriz) cuyos nodos representan a las neuronas o grupos de neuronas y los enlaces son las conexiones reconstruidas entre ellos. Este algoritmo extrae también otras medidas morfológicas importantes que caracterizan a las neuronas y a las neuritas. A diferencia de otros algoritmos hasta el momento, que necesitan de fluorescencia y técnicas inmunocitoquímicas, el algoritmo propuesto permite el estudio longitudinal de forma no invasiva posibilitando el estudio durante la formación de un cultivo. Además, esta tesis, estudia de forma sistemática un grupo de variables topológicas que garantizan la posibilidad de cuantificar e investigar la progresión de las características principales durante el proceso de auto-organización del cultivo. Nuestros resultados muestran la existencia de un estado concreto correspondiente a redes con configuracin small-world y la emergencia de propiedades a micro- y meso-escala de la estructura de la red. Finalmente, identificamos los procesos físicos principales que guían las transformaciones morfológicas de los cultivos y proponemos un modelo de crecimiento de red que reproduce el comportamiento cuantitativamente de las observaciones experimentales. ABSTRACT The thesis analyzes the morphological evolution of assemblies of living neurons, as they self-organize from collections of separated cells into elaborated, clustered, networks. In particular, it contributes with the design and implementation of a graph-based unsupervised segmentation algorithm, having an associated very low computational cost. The processing automatically retrieves the whole network structure from large scale phase-contrast images taken at high resolution throughout the entire life of a cultured neuronal network. The network structure is represented by a mathematical object (a matrix) in which nodes are identified neurons or neurons clusters, and links are the reconstructed connections between them. The algorithm is also able to extract any other relevant morphological information characterizing neurons and neurites. More importantly, and at variance with other segmentation methods that require fluorescence imaging from immunocyto- chemistry techniques, our measures are non invasive and entitle us to carry out a fully longitudinal analysis during the maturation of a single culture. In turn, a systematic statistical analysis of a group of topological observables grants us the possibility of quantifying and tracking the progression of the main networks characteristics during the self-organization process of the culture. Our results point to the existence of a particular state corresponding to a small-world network configuration, in which several relevant graphs micro- and meso-scale properties emerge. Finally, we identify the main physical processes taking place during the cultures morphological transformations, and embed them into a simplified growth model that quantitatively reproduces the overall set of experimental observations.

Self-organizing cultured neural networks: Image analysis techniques for longitudinal tracking and modeling of the underlying network structure (versión actualizada)

Esta tesis estudia la evolución estructural de conjuntos de neuronas como la capacidad de auto-organización desde conjuntos de neuronas separadas hasta que forman una red (clusterizada) compleja. Esta tesis contribuye con el diseño e implementación de un algoritmo no supervisado de segmentación basado en grafos con un coste computacional muy bajo. Este algoritmo proporciona de forma automática la estructura completa de la red a partir de imágenes de cultivos neuronales tomadas con microscopios de fase con una resolución muy alta. La estructura de la red es representada mediante un objeto matemático (matriz) cuyos nodos representan a las neuronas o grupos de neuronas y los enlaces son las conexiones reconstruidas entre ellos. Este algoritmo extrae también otras medidas morfológicas importantes que caracterizan a las neuronas y a las neuritas. A diferencia de otros algoritmos hasta el momento, que necesitan de fluorescencia y técnicas inmunocitoquímicas, el algoritmo propuesto permite el estudio longitudinal de forma no invasiva posibilitando el estudio durante la formación de un cultivo. Además, esta tesis, estudia de forma sistemática un grupo de variables topológicas que garantizan la posibilidad de cuantificar e investigar la progresión de las características principales durante el proceso de auto-organización del cultivo. Nuestros resultados muestran la existencia de un estado concreto correspondiente a redes con configuracin small-world y la emergencia de propiedades a micro- y meso-escala de la estructura de la red. Finalmente, identificamos los procesos físicos principales que guían las transformaciones morfológicas de los cultivos y proponemos un modelo de crecimiento de red que reproduce el comportamiento cuantitativamente de las observaciones experimentales. ABSTRACT The thesis analyzes the morphological evolution of assemblies of living neurons, as they self-organize from collections of separated cells into elaborated, clustered, networks. In particular, it contributes with the design and implementation of a graph-based unsupervised segmentation algorithm, having an associated very low computational cost. The processing automatically retrieves the whole network structure from large scale phase-contrast images taken at high resolution throughout the entire life of a cultured neuronal network. The network structure is represented by a mathematical object (a matrix) in which nodes are identified neurons or neurons clusters, and links are the reconstructed connections between them. The algorithm is also able to extract any other relevant morphological information characterizing neurons and neurites. More importantly, and at variance with other segmentation methods that require fluorescence imaging from immunocyto- chemistry techniques, our measures are non invasive and entitle us to carry out a fully longitudinal analysis during the maturation of a single culture. In turn, a systematic statistical analysis of a group of topological observables grants us the possibility of quantifying and tracking the progression of the main networks characteristics during the self-organization process of the culture. Our results point to the existence of a particular state corresponding to a small-world network configuration, in which several relevant graphs micro- and meso-scale properties emerge. Finally, we identify the main physical processes taking place during the cultures morphological transformations, and embed them into a simplified growth model that quantitatively reproduces the overall set of experimental observations.

Improving parameters selection of a seeded region growing method for multiband image segmentation

In the last decade, Object Based Image Analysis (OBIA) has been accepted as an effective method for processing high spatial resolution multiband images. This image analysis method is an approach that starts with the segmentation of the image. Image segmentation in general is a procedure to partition an image into homogenous groups (segments). In practice, visual interpretation is often used to assess the quality of segmentation and the analysis relies on the experience of an analyst. In an effort to address the issue, in this study, we evaluate several seed selection strategies for an automatic image segmentation methodology based on a seeded region growing-merging approach. In order to evaluate the segmentation quality, segments were subjected to spatial autocorrelation analysis using Moran's I index and intra-segment variance analysis. We apply the algorithm to image segmentation using an aerial multiband image.

An autostereoscopic device for mobile applications based on a liquid crystal microlens array and an OLED display

In recent years, many experimental and theoretical research groups worldwide have actively worked on demonstrating the use of liquid crystals (LCs) as adaptive lenses for image generation, waveform shaping, and non-mechanical focusing applications. In particular, important achievements have concerned the development of alternative solutions for 3D vision. This work focuses on the design and evaluation of the electro-optic response of a LC-based 2D/3D autostereoscopic display prototype. A strategy for achieving 2D/3D vision has been implemented with a cylindrical LC lens array placed in front of a display; this array acts as a lenticular sheet with a tunable focal length by electrically controlling the birefringence. The performance of the 2D/3D device was evaluated in terms of the angular luminance, image deflection, crosstalk, and 3D contrast within a simulated environment. These measurements were performed with characterization equipment for autostereoscopic 3D displays (angular resolution of 0.03 ).