Kernel bandwidth estimation for moving object detection in non-stabilized cameras

The evolution of the television market is led by 3DTV technology, and this tendency can accelerate during the next years according to expert forecasts. However, 3DTV delivery by broadcast networks is not currently developed enough, and acts as a bottleneck for the complete deployment of the technology. Thus, increasing interest is dedicated to ste-reo 3DTV formats compatible with current HDTV video equipment and infrastructure, as they may greatly encourage 3D acceptance. In this paper, different subsampling schemes for HDTV compatible transmission of both progressive and interlaced stereo 3DTV are studied and compared. The frequency characteristics and preserved frequency content of each scheme are analyzed, and a simple interpolation filter is specially designed. Finally, the advantages and disadvantages of the different schemes and filters are evaluated through quality testing on several progressive and interlaced video sequences.

Segmentación de Secuencias de Vídeo: análisis y desarrollo de estrategias para la detección de cambios de toma y para la detección de objetos móviles

The important technological advances experienced along the last years have resulted in an important demand for new and efficient computer vision applications. On the one hand, the increasing use of video editing software has given rise to a necessity for faster and more efficient editing tools that, in a first step, perform a temporal segmentation in shots. On the other hand, the number of electronic devices with integrated cameras has grown enormously. These devices require new, fast, and efficient computer vision applications that include moving object detection strategies. In this dissertation, we propose a temporal segmentation strategy and several moving object detection strategies, which are suitable for the last generation of computer vision applications requiring both low computational cost and high quality results. First, a novel real-time high-quality shot detection strategy is proposed. 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 allows to detect and discard false detections. This analysis is carried out exclusively over a reduced amount of candidate transitions, thus maintaining the computational requirements. On the other hand, a moving object detection strategy, which is based on the popular Mixture of Gaussians method, is proposed. This strategy, taking into account the recent history of each image pixel, adapts dynamically the amount of Gaussians that are required to model its variations. As a result, we improve significantly the computational efficiency with respect to other similar methods and, additionally, we reduce the influence of the used parameters in the results. Alternatively, in order to improve the quality of the results in complex scenarios containing dynamic backgrounds, we propose different non-parametric based moving object detection strategies that model both background and foreground. To obtain high quality results regardless of the characteristics of the analyzed sequence we dynamically estimate the most adequate bandwidth matrices for the kernels that are used in the background and foreground modeling. Moreover, the application of a particle filter allows to update the spatial information and provides a priori knowledge about the areas to analyze in the following images, enabling an important reduction in the computational requirements and improving the segmentation results. Additionally, we propose the use of an innovative combination of chromaticity and gradients that allows to reduce the influence of shadows and reflects in the detections.

La gestión integrada sostenible del litoral en la actualidad

En nuestros días, en países ubicados en latitudes medias con facahada marítima y estabilidad político-social el litoral es objeto de diversas presiones e influencias por lo que su equilibrio, que es de naturaleza frágil, complicada y variable, se ve amenazado. En estos paises son múltiples los intereses que confluyen en él, lo que hace que sea objeto de numerosas presiones económicas y políticas. Por ello, su gestión adecuada a uno de sus objetivos que se ha planteado la Unión Europea, intentando prevenir la creciente erosión favorecida por la presión humana (edificaciones, infraestructuras, etc) y la amenaza creciente de la posible influencia del calentamiento global con su efecto de cambio climático global, y muy discutible efecto sobre el litoral (cambio de régimen ciertos y variaciones de nivel ficticias). La gestión integrada sostenible del litoral es, por lo tanto, una de las herramientas que se presentan como más eficaz en la actualidad, unida a la gestión de riesgo, y a la evaluación ambiental estratégica (SEA). El adecuado uso de los Sistemas de Información Geográfica constituye una herramienta básica para una gestión integrada del litoral real tecnificada, en vez de una gestión basada en dogmas discutibles no cuestionados. De todo ello se plantea una perspectiva actualizada en el presente trabajo.

Notas para la interpretación de la utilidad de los análisis para hongos fitopatógenos en suelos y sustratos para usos agrícolas

Interpretación de la utilidad de los análisis para hongos fitopatógenos en suelos y sustratos para usos agrícolas

Moving Object Detection for Real-Time High-Quality Lightweight Applications on Smart Cameras

Here, a novel and efficient strategy for moving object detection by non-parametric modeling on smart cameras is presented. Whereas the background is modeled using only color information, the foreground model combines color and spatial information. The application of a particle filter allows the update of the spatial information and provides a priori information about the areas to analyze in the following images, enabling an important reduction in the computational requirements and improving the segmentation results

Automatic Bandwidth Estimation Strategy for High-Quality Non-Parametric Modeling based Moving Object Detection

Here, a novel and efficient moving object detection strategy by non-parametric modeling is presented. Whereas the foreground is modeled by combining color and spatial information, the background model is constructed exclusively with color information, thus resulting in a great reduction of the computational and memory requirements. The estimation of the background and foreground covariance matrices, allows us to obtain compact moving regions while the number of false detections is reduced. Additionally, the application of a tracking strategy provides a priori knowledge about the spatial position of the moving objects, which improves the performance of the Bayesian classifier

Microbiota asociada a la enfermedad de la punta negra del trigo duro. Efectos del riego, el abonado nitrogenado y la variedad cultivada en la incidencia de la enfermedad

La enfermedad fúngica de la punta negra del trigo se caracteriza por provocar en las semillas afectadas un oscurecimiento de la zona del embrión que en ocasiones puede extenderse hacia la hendidura central dejando el grano completamente ennegrecido. Su incidencia en el cultivo de trigo es extremadamente variable y depende en gran medida de las condiciones ambientales, así pues, condiciones de alta humedad pueden incrementar a punta negra. Su presencia en el trigo duro repercute en el rendimiento semolero. Además la pasta elaborada a partir de semilla enferma presenta manchas negras y adquiere color y olor desagradable. Esta enfermedad es poco conocida a nivel europeo, sin embargo existen numerosos estudios para conocer su etiología y los factores que afectan a su aparición en países como Nueva Zelanda, Australia, Estados Unidos o Canadá. El presente trabajo pretende dar a conocer esta patología en España, determinando la influencia del riego, el abonado nitrogenado y la variedad cultivada en la incidencia de la enfermedad. Para ello se ha contado con un diseño experimental basado en 10 cultivares sembrados en parcelas con dos tratamientos de riego y dos de abonado nitrogenado. El análisis de las semillas infectadas en cámara húmeda y medios de cultivo PDA y K reveló 12 géneros fúngicos diferentes, de los cuales Alternaria alternata y Fusarium proliferatum estaban presentes en todas las muestras. El estudio del riego y abonado nitrogenado mostró diferencias significativas en la incidencia de punta negra pero fueron los 10 cultivares incluidos en el ensayo los que mayor importancia cobraron desde el punto de vista de la aparición de la enfermedad. El genotipo resultó determinante a la hora de establecer los niveles de afectación ya que las muestras encuadradas botánicamente como Triticum turgidum subsp. Turgidum convar. Turgidum presentaron una mayor susceptibilidad. las prueas de patogenicidd con los tres principales hongos asociados a la punta negra dieron resultados negativos para la germinación-nascencia de las plántulas de trigo duro inoculadas.

On the Mahalanobis Distance Classification Criterion for Multidimensional Normal Distributions

Many existing engineering works model the statistical characteristics of the entities under study as normal distributions. These models are eventually used for decision making, requiring in practice the definition of the classification region corresponding to the desired confidence level. Surprisingly enough, however, a great amount of computer vision works using multidimensional normal models leave unspecified or fail to establish correct confidence regions due to misconceptions on the features of Gaussian functions or to wrong analogies with the unidimensional case. The resulting regions incur in deviations that can be unacceptable in high-dimensional models. Here we provide a comprehensive derivation of the optimal confidence regions for multivariate normal distributions of arbitrary dimensionality. To this end, firstly we derive the condition for region optimality of general continuous multidimensional distributions, and then we apply it to the widespread case of the normal probability density function. The obtained results are used to analyze the confidence error incurred by previous works related to vision research, showing that deviations caused by wrong regions may turn into unacceptable as dimensionality increases. To support the theoretical analysis, a quantitative example in the context of moving object detection by means of background modeling is given.

Desarrollo y metodología de la gestión integrada de las áreas litorales

El litoral , históricamente considerado un medio físico de recursos inagotables y de tolerancia ilimitada , está actualmente en muchas zonas de nuestro país en un preocupante estado de congestión poniendo en peligro tanto la sostenibilidad de las actividades que en él se desarrollan , como la preservación del medio natural en que se enmarca . Desde hace ya varias décadas se ha creado una economia de servicios florecientes ( turismo ) que exige a su vez una serie de inversiones en actuaciones que necesita de una coordinación territorial y de una planificación temporal ordenadas así como una gestión eficaz . Esta nueva gestión debe resolver los problemas derivados de las interacciones entre los distintos agentes implicados , principalmente , los diferentes que lo componen ( aire , agua y tierra ) , y los tres subsistemas presentes ( físico y ambiental , económico-social e institucional ) . La alteración de cualquiera de ellos modifica el equilibrio existente , por lo que conseguir la preservación de este equilibrio dentro de los límites razonables en una estrategia sostenible e integrada es el objetivo fundamental de la gestión integrada sostenible del litoral .

Comportamiento de patrones de tomate frente a la patogenicidad de Fusarium oxysporum f. sp. radicis-lycopersici

La fusariosis del cuello y de las raíces del tomate ("mancha chocolate"), causada por el hongo F. o. f. sp. radicis-lycopersici, es una micosis cada vez más extendida en los cultivos de tomate de las provincias de Almería y Granada. Su gravedad es alta, llegando a alcanzar al 78% de las plantas en algún invernadero con cultivo sobre fibra de coco. Ante esta situación, se estimó necesario evaluar la resistencia de patrones utilizados para injertar variedades de tomate. Así, 16 patrones fueron valorados frente a una cepa muy patógena del hongo. Los patrones fueron:CLXTPG01, AR9704, AR97015, AR97009, Morgan, Spirit, Herman, Armstrong, Arnold, Big Power, Emperador, 61-071, Montezuma, Beaufort, Multifort, Maxifort, Tovi Star y Alegro. Dos ensayos sobre plantas en estado de 6-8 hojas verdaderas bien formadas, mostraron que todos los patrones expresaron una resistencia completa, exceptuando los denominados CLXTPG01 y AR97015. Entendemos que esta información es necesaria debidio a la escasa disponibilidad.

Investigación, desarrollo y evaluación de metodologías y criterios para la gestión integrada del litoral : aplicación a una costa singular, Marbella (Málaga), España

En la actualidad, el litoral es el objetivo de diversas presiones de toda índole. Por ello, es necesario estudiar e investigar metodologías que ayuden a una gestión eficaz y sostenible de un Sistema con un equilibrio tan frágil y voluble como es el del litoral. De este modo esta tesis estudia las investigaciones y proyectos realizados por el mundo, especialmente en la Unión Europea y se llega a la conclusión de que la utilización combinada de tres metodologías es la solución más eficaz para la gestión litoral. Esta conclusión se aplica a la costa de Marbella, en la provincia de Málaga, debido a sus especiales e importantes circunstancias turísticas, territoriales, físicas y ambientales. Terminada esta Tesis ha entrado en debate un Proyecto de Modificación de la Ley de Costas, que recoge, en parte, los planteamientos de la misma, por lo que el trabajo de investigación se ha complementado, figurando como anejo el Proyecto de Ley. Currently, coast is the target of all kinds of pressures. Due to that, it is necessary to study and research on methodologies to carry out an effective and sustainable management of a system with such a delicate and vulnerable balance. In this way this research work studies the research and projects carried out throughout the World, especially in the European Community to reach the conclusion that the combined use of three methodologies is the more adequate solution for littoral management. This conclusion is applied along the coast of Marbella, in Málaga (Spain) because of its special tourist, territorial, urbanity, physics and environmental circumstances. Once the work finished, a project of Law modification has begun its process at Parliament. New Law takes into consideration some of the results of this investigation, and document is incorporated as annex.

Versatile Bayesian classifier for moving object detection by non-parametric background-foreground modeling

Along the recent years, several moving object detection strategies by non-parametric background-foreground modeling have been proposed. To combine both models and to obtain the probability of a pixel to belong to the foreground, these strategies make use of Bayesian classifiers. However, these classifiers do not allow to take advantage of additional prior information at different pixels. So, we propose a novel and efficient alternative Bayesian classifier that is suitable for this kind of strategies and that allows the use of whatever prior information. Additionally, we present an effective method to dynamically estimate prior probability from the result of a particle filter-based tracking strategy.

Aerial video geo-registration using terrain models from dense and coherent stereo matching

In the context of aerial imagery, one of the first steps toward a coherent processing of the information contained in multiple images is geo-registration, which consists in assigning geographic 3D coordinates to the pixels of the image. This enables accurate alignment and geo-positioning of multiple images, detection of moving objects and fusion of data acquired from multiple sensors. To solve this problem there are different approaches that require, in addition to a precise characterization of the camera sensor, high resolution referenced images or terrain elevation models, which are usually not publicly available or out of date. Building upon the idea of developing technology that does not need a reference terrain elevation model, we propose a geo-registration technique that applies variational methods to obtain a dense and coherent surface elevation model that is used to replace the reference model. The surface elevation model is built by interpolation of scattered 3D points, which are obtained in a two-step process following a classical stereo pipeline: first, coherent disparity maps between image pairs of a video sequence are estimated and then image point correspondences are back-projected. The proposed variational method enforces continuity of the disparity map not only along epipolar lines (as done by previous geo-registration techniques) but also across them, in the full 2D image domain. In the experiments, aerial images from synthetic video sequences have been used to validate the proposed technique.

Broadband access in complex environments: LTE on railway

This paper assesses the main challenges associated with the propagation and channel modeling of broadband radio systems in a complex environment of high speed and metropolitan railways. These challenges comprise practical simulation, modeling interferences, radio planning, test trials and performance evaluation in different railway scenarios using Long Term Evolution (LTE) as test case. This approach requires several steps; the first is the use of a radio propagation simulator based on ray-tracing techniques to accurately predict propagation. Besides the radio propagation simulator, a complete test bed has been constructed to assess LTE performance, channel propagation conditions and interference with other systems in real-world environments by means of standard-compliant LTE transmissions. Such measurement results allowed us to evaluate the propagation and performance of broadband signals and to test the suitability of LTE radio technology for complex railway scenarios.

High-quality real-time temporal segmentation tool for video editing software

The increasing use of video editing software has resulted in a necessity for faster and more efficient editing tools. Here, we propose a lightweight high-quality video indexing tool that is suitable for video editing software.