Vehicular traffic surveillance and road lane detection using radar interferometry

Speed enforcement on public roadways is an important issue in order to guarantee road security and to reduce the number and seriousness of traffic accidents. Traditionally, this task has been partially solved using radar and/or laser technologies and, more recently, using video-camera based systems. All these systems have significant shortcomings that have yet to be overcome. The main drawback of classical Doppler radar technology is that the velocity measurement fails when several vehicles are in the radars beam. Modern radar systems are able to measure speed and range between vehicle and radar. However, this is not enough to discriminate the lane where the vehicle is driving on. The limitation of several vehicles in the beam is overcome using laser technology. However, laser systems have another important limitation: They cannot measure the speed of several vehicles simultaneously. Novel video-camera systems, based on license plate identification, solve the previous drawbacks, but they have the problem that they can only measure average speed but never top-speed. This paper studies the feasibility of using an interferometric linear frequency modulated continuous wave radar to improve top-speed enforcement on roadways. Two different systems based on down-the-road and across-the-road radar configurations are presented. The main advantage of the proposed solutions is they can simultaneously measure speed, range, and lane of several vehicles, allowing the univocal identification of the offenders. A detailed analysis about the operation and accuracy of these solutions is reported. In addition, the feasibility of the proposed techniques has been demonstrated with simulations and real experiments using a Ka-band interferometric radar developed by our research group.

Modelado en alto nivel con SystemC

El presente proyecto final de carrera titulado “Modelado de alto nivel con SystemC” tiene como objetivo principal el modelado de algunos módulos de un codificador de vídeo MPEG-2 utilizando el lenguaje de descripción de sistemas igitales SystemC con un nivel de abstracción TLM o Transaction Level Modeling. SystemC es un lenguaje de descripción de sistemas digitales basado en C++. En él hay un conjunto de rutinas y librerías que implementan tipos de datos, estructuras y procesos especiales para el modelado de sistemas digitales. Su descripción se puede consultar en [GLMS02] El nivel de abstracción TLM se caracteriza por separar la comunicación entre los módulos de su funcionalidad. Este nivel de abstracción hace un mayor énfasis en la funcionalidad de la comunicación entre los módulos (de donde a donde van datos) que la implementación exacta de la misma. En los documentos [RSPF] y [HG] se describen el TLM y un ejemplo de implementación. La arquitectura del modelo se basa en el codificador MVIP-2 descrito en [Gar04], de dicho modelo, los módulos implementados son: · IVIDEOH: módulo que realiza un filtrado del vídeo de entrada en la dimensión horizontal y guarda en memoria el video filtrado. · IVIDEOV: módulo que lee de la memoria el vídeo filtrado por IVIDEOH, realiza el filtrado en la dimensión horizontal y escribe el video filtrado en memoria. · DCT: módulo que lee el video filtrado por IVIDEOV, hace la transformada discreta del coseno y guarda el vídeo transformado en la memoria. · QUANT: módulo que lee el video transformado por DCT, lo cuantifica y guarda el resultado en la memoria. · IQUANT: módulo que lee el video cuantificado por QUANT, realiza la cuantificación inversa y guarda el resultado en memoria. · IDCT: módulo que lee el video procesado por IQUANT, realiza la transformada inversa del coseno y guarda el resultado en memoria. · IMEM: módulo que hace de interfaz entre los módulos anteriores y la memoria. Gestiona las peticiones simultáneas de acceso a la memoria y asegura el acceso exclusivo a la memoria en cada instante de tiempo. Todos estos módulos aparecen en gris en la siguiente figura en la que se muestra la arquitectura del modelo: Figura 1. Arquitectura del modelo (VER PDF DEL PFC) En figura también aparecen unos módulos en blanco, dichos módulos son de pruebas y se han añadido para realizar simulaciones y probar los módulos del modelo: · CAMARA: módulo que simula una cámara en blanco y negro, lee la luminancia de un fichero de vídeo y lo envía al modelo a través de una FIFO. · FIFO: hace de interfaz entre la cámara y el modelo, guarda los datos que envía la cámara hasta que IVIDEOH los lee. · CONTROL: módulo que se encarga de controlar los módulos que procesan el vídeo, estos le indican cuando terminan de procesar un frame de vídeo y este módulo se encarga de iniciar los módulos que sean necesarios para seguir con la codificación. Este módulo se encarga del correcto secuenciamiento de los módulos procesadores de vídeo. · RAM: módulo que simula una memoria RAM, incluye un retardo programable en el acceso. Para las pruebas también se han generado ficheros de vídeo con el resultado de cada módulo procesador de vídeo, ficheros con mensajes y un fichero de trazas en el que se muestra el secuenciamiento de los procesadores. Como resultado del trabajo en el presente PFC se puede concluir que SystemC permite el modelado de sistemas digitales con bastante sencillez (hace falta conocimientos previos de C++ y programación orientada objetos) y permite la realización de modelos con un nivel de abstracción mayor a RTL, el habitual en Verilog y VHDL, en el caso del presente PFC, el TLM. ABSTRACT This final career project titled “High level modeling with SystemC” have as main objective the modeling of some of the modules of an MPEG-2 video coder using the SystemC digital systems description language at the TLM or Transaction Level Modeling abstraction level. SystemC is a digital systems description language based in C++. It contains routines and libraries that define special data types, structures and process to model digital systems. There is a complete description of the SystemC language in the document [GLMS02]. The main characteristic of TLM abstraction level is that it separates the communication among modules of their functionality. This abstraction level puts a higher emphasis in the functionality of the communication (from where to where the data go) than the exact implementation of it. The TLM and an example are described in the documents [RSPF] and [HG]. The architecture of the model is based in the MVIP-2 video coder (described in the document [Gar04]) The modeled modules are: · IVIDEOH: module that filter the video input in the horizontal dimension. It saves the filtered video in the memory. · IVIDEOV: module that read the IVIDEOH filtered video, filter it in the vertical dimension and save the filtered video in the memory. · DCT: module that read the IVIDEOV filtered video, do the discrete cosine transform and save the transformed video in the memory. · QUANT: module that read the DCT transformed video, quantify it and save the quantified video in the memory. · IQUANT: module that read the QUANT processed video, do the inverse quantification and save the result in the memory. · IDCT: module that read the IQUANT processed video, do the inverse cosine transform and save the result in the memory. · IMEM: this module is the interface between the modules described previously and the memory. It manage the simultaneous accesses to the memory and ensure an unique access at each instant of time All this modules are included in grey in the following figure (SEE PDF OF PFC). This figure shows the architecture of the model: Figure 1. Architecture of the model This figure also includes other modules in white, these modules have been added to the model in order to simulate and prove the modules of the model: · CAMARA: simulates a black and white video camera, it reads the luminance of a video file and sends it to the model through a FIFO. · FIFO: is the interface between the camera and the model, it saves the video data sent by the camera until the IVIDEOH module reads it. · CONTROL: controls the modules that process the video. These modules indicate the CONTROL module when they have finished the processing of a video frame. The CONTROL module, then, init the necessary modules to continue with the video coding. This module is responsible of the right sequence of the video processing modules. · RAM: it simulates a RAM memory; it also simulates a programmable delay in the access to the memory. It has been generated video files, text files and a trace file to check the correct function of the model. The trace file shows the sequence of the video processing modules. As a result of the present final career project, it can be deduced that it is quite easy to model digital systems with SystemC (it is only needed previous knowledge of C++ and object oriented programming) and it also allow the modeling with a level of abstraction higher than the RTL used in Verilog and VHDL, in the case of the present final career project, the TLM.

Provisión de servicios de procesado de imágenes basados en arquitecturas orientadas a servicios

Con este proyecto se pretende crear un procedimiento general para la implantación de aplicaciones de procesado de imágenes en cámaras de video IP y la distribución de dicha información mediante Arquitecturas Orientadas a Servicios (SOA). El objetivo principal es crear una aplicación que se ejecute en una cámara de video IP y realice un procesado básico sobre las imágenes capturadas (detección de colores, formas y patrones) permitiendo distribuir el resultado del procesado mediante las arquitecturas SOA descritas en la especificación DPWS (Device Profile for Web Services). El estudio se va a centrar principalmente en la transformación automática de código de procesado de imágenes escrito en Matlab (archivos .m) a un código C ANSI (archivos .c) que posteriormente se compilará para la arquitectura del procesador de la cámara (arquitectura CRIS, similar a la RISC pero con un conjunto reducido de instrucciones). ABSTRACT. This project aims to create a general procedure for the implementation of image processing applications in IP video cameras and the distribution of such information through Service Oriented Architectures (SOA). The main goal is to create an application that runs on IP video camera and carry out a basic processing on the captured images ( color detection, shapes and patterns) allowing to distribute the result of process by SOA architectures described in the DPWS specification (Device Profile for Web Services). The study will focus primarily on the automated transform of image processing code written in Matlab files (. M) to ANSI C code files (. C) which is then compiled to the processor architecture of the camera (CRIS architecture , similar to the RISC but with a reduced instruction set).

Tutoriales multimedia para sistemas de telecomunicación

Este Proyecto Fin de Carrera está destinado a la ilustración y aprendizaje del uso de varios dispositivos de los laboratorios del Departamento de Ingeniería Audiovisual y Comunicaciones, de la Escuela Universitaria de Ingeniería Técnica de Telecomunicación, de la Universidad Politécnica de Madrid, en forma de vídeos tutoriales basados en mediciones y prácticas habituales de las asignaturas del departamento para que puedan ser utilizados por los alumnos de la escuela como apoyo a las explicaciones del profesor en ocasiones puntuales. En concreto se han realizado hasta seis vídeos tutoriales en los que se explica: el diseño de un circuito impreso y la creación y fabricación de éste. Por otro lado, también se ha explicado el fenómeno del ruido de fase y cómo es el proceso de su medida, como una de las muchas características de un analizador de espectros. A modo de análisis, se ha realizado otro tutorial acerca de la modulación en FM, sus características y sus aplicaciones. Por último se ha hecho un estudio del comportamiento de un analizador de redes, exponiendo su funcionamiento y explicando su proceso de calibración. Para la realización de estos tutoriales se han utilizado diferentes aplicaciones sobre creación de vídeos multimedia, animación, producción de audio y narración. En especial se han usado: Sprint-Layout 5.0, Adobe Flash Professional CS5.5, Camtasia studio 7, Corel VideoStudio Pro X4, Loquendo TTS7 y WinPlot. Para el apartado de las grabaciones de las diferentes escenas se ha necesitado el uso de distintos instrumentos de medida del laboratorio tales como: analizador de espectros, analizador de redes, generador de señal, generador de funciones, osciloscopio y otros equipos adicionales como: cámara de vídeo y trípode del departamento. Para la composición de los diferentes tutoriales se ha comenzado creando un guion, para cada uno de ellos, estableciendo la aparición de las imágenes, vídeos, y locución. A continuación se exponen los diferentes temas en los que se han basado estos tutoriales de laboratorio, uno a uno. ABSTRACT. This Project is destined to learn the use of several devices at the laboratory of “Ingeniería Audiovisual y Comunicaciones” Department at “Escuela Universitaria de Ingeniería técnica de Telecomunicaciones” of “Universidad Politécnica de Madrid”, on the way as tutorial videos base on the subjects from this department to be used by the college students as help of the teacher’s explanations. In this project you will find up to six tutorial videos, showing: printed circuit design, printed circuit board manufacture. You can also find an explanation about the phenomenon of phase noise and how it’s its measurement process, as one of the many features of a spectrum analyzer. Another tutorial video is based on FM modulation, its features and applications. The last tutorial explains the networks analyzer functionalities and its calibration process. To carry out these tutorials different applications have been used to create multimedia videos, animation, audio production and storytelling. Such as Sprint Layout 5.0, Camtasia 7.0, Corel VideoStudio Pro X4, Adobe Flash Professional CS5.5, Loquendo TTS7 y WinPlot. About the recording side of the different scenes, several equipment have been required at the laboratory, such as spectrums analyzer, signal generator, oscilloscope, function generator, network analyzer and other additional devices, such as: a video camera with its tripod. The composition of the different tutorials has begun creating a script, for each of them, setting the times of appearance of images, video, speech and music. After this abstract, the different topics of the tutorials are showed, one by one.

Multisensor data fusion for accurate modelling of mobile objects

In the last decade, multi-sensor data fusion has become a broadly demanded discipline to achieve advanced solutions that can be applied in many real world situations, either civil or military. In Defence,accurate detection of all target objects is fundamental to maintaining situational awareness, to locating threats in the battlefield and to identifying and protecting strategically own forces. Civil applications, such as traffic monitoring, have similar requirements in terms of object detection and reliable identification of incidents in order to ensure safety of road users. Thanks to the appropriate data fusion technique, we can give these systems the power to exploit automatically all relevant information from multiple sources to face for instance mission needs or assess daily supervision operations. This paper focuses on its application to active vehicle monitoring in a particular area of high density traffic, and how it is redirecting the research activities being carried out in the computer vision, signal processing and machine learning fields for improving the effectiveness of detection and tracking in ground surveillance scenarios in general. Specifically, our system proposes fusion of data at a feature level which is extracted from a video camera and a laser scanner. In addition, a stochastic-based tracking which introduces some particle filters into the model to deal with uncertainty due to occlusions and improve the previous detection output is presented in this paper. It has been shown that this computer vision tracker contributes to detect objects even under poor visual information. Finally, in the same way that humans are able to analyze both temporal and spatial relations among items in the scene to associate them a meaning, once the targets objects have been correctly detected and tracked, it is desired that machines can provide a trustworthy description of what is happening in the scene under surveillance. Accomplishing so ambitious task requires a machine learning-based hierarchic architecture able to extract and analyse behaviours at different abstraction levels. A real experimental testbed has been implemented for the evaluation of the proposed modular system. Such scenario is a closed circuit where real traffic situations can be simulated. First results have shown the strength of the proposed system.

Evaluación del tiempo de reacción en velocistas con y sin discapacidad auditiva: aplicaciones para la inclusión

Este trabajo de investigación trata de aportar luz al estudio del tiempo de reacción (TR) en velocistas con y sin discapacidad auditiva desde las Ciencias del Deporte. El planteamiento del presente estudio surgió al cuestionarnos la existencia de las diferencias en cuanto al TR visual y auditivo aplicado a velocistas con y sin discapacidad auditiva, pensando en el desarrollo futuro de competiciones inclusivas entre ambos colectivos. Por ello, este estudio trata de resolver las dificultades que los velocistas con discapacidad se encuentran habitualmente en las competiciones. A priori, los atletas con discapacidad auditiva compiten en inferioridad de condiciones como consecuencia de una salida que no parece la más adecuada para ellos (desde los tacos, han de mirar hacia la pistola del juez o el movimiento de un rival). El documento se divide en tres partes. En la primera parte se realiza la pertinente revisión del marco teórico y justificación del estudio. La segunda parte se centra en los objetivos de la investigación, el material y el método, donde se muestran los resultados, discusión y conclusiones del estudio realizado, así como las limitaciones del presente trabajo y sus futuras líneas de investigación. La tercera parte corresponde a la bibliografía y la cuarta parte a los anexos. En la primera parte, presentamos el marco teórico compuesto por cinco capítulos organizan la fundamentación que hemos realizado como revisión sobre los aspectos más destacados del TR, determinado por las características de la tarea y otros factores que influyen en el TR como objeto de nuestro estudio. Después exponemos los principales aspectos estructurales y funcionales del sistema nervioso (SN) relacionados con el TR visual y auditivo. Tras ello se expone la realidad del deporte para personas con discapacidad auditiva, indagando en sus peculiaridades y criterios de elegibilidad que tiene ese colectivo dentro del ámbito deportivo. A continuación abordamos el estudio de la salida de velocidad en el atletismo, como aspecto clave que va a guiar nuestra investigación, especialmente los parámetros determinantes en la colocación de los tacos de salida para atletas con y sin discapacidad auditiva, la posición de salida y la propia colocación de los estímulos en dicha situación. Es la segunda parte se desarrolla el trabajo de investigación que tiene como objetivos estudiar los valores de TR visual simple manual, TR en salida de tacos y los tiempos de desplazamiento a los 10m y 20m de velocistas con y sin discapacidad auditiva, así como analizar las posibles diferencias en TR según posición y tipo de estímulo luminoso, respecto a ambos grupos de atletas. Como tercer objetivo de estudio se evalúa cualitativamente, por parte de los propios atletas, el dispositivo luminoso utilizado. La toma de datos de este estudio se llevó a cabo entre los meses de febrero y mayo del 2014, en el módulo de atletismo del Centro de Alto Rendimiento Joaquín Blume (Madrid), con dos grupos de estudio, uno de 9 velocistas con discapacidad auditiva (VDA), conformando éstos el 60% de toda la población en España, según el número de las licencias de la FEDS en la modalidad de atletismo (velocistas, pruebas de 100 y 200 m.l.), en el momento del estudio, y otro de 13 velocistas sin discapacidad (VsDA) que se presentaron de manera voluntaria con unos mismos criterios de inclusión para ambos grupos. Para la medición y el registro de los datos se utilizaron materiales como hoja de registro, Medidor de Tiempo de Reacción (MTR), tacos de salida, ReacTime®, dispositivo luminoso conectado a los tacos de salida, células fotoeléctricas, ordenador y software del ReacTime, y cámara de video. La metodología utilizada en este estudio fue de tipo correlacional, analizando los resultados del TR simple manual según vía sensitiva (visual y auditiva) entre los dos grupos de VDA y VsDA. También se estudiaron los TR desde la salida de tacos en función de la colocación del dispositivo luminoso (en el suelo y a 5 metros, vía visual) y pistola de salida atlética (vía auditiva) así como el tiempo de desplazamiento a los 10m (t10m) y 20m (t20m) de ambos grupos de velocistas. Finalmente, se desarrolló y llevó a cabo un cuestionario de evaluación por parte de los atletas VDA con el objetivo de conocer el grado de satisfacción después de haber realizado la serie de experimentos con el dispositivo luminoso y adaptado para sistemas de salida en la velocidad atlética. Con el objetivo de comprobar la viabilidad de la metodología descrita y probar en el contexto de análisis real el protocolo experimental, se realizó un estudio piloto con el fin de conocer las posibles diferencias del TR visual desde los tacos de salida en velocistas con discapacidad auditiva, usando para dicha salida un estímulo visual mediante un dispositivo luminoso coordinado con la señal sonora de salida (Soto-Rey, Pérez-Tejero, Rojo-González y Álvarez-Ortiz, 2015). En cuanto a los procedimientos estadísticos utilizados, con el fin de analizar la distribución de los datos y su normalidad, se aplicó la prueba de Kolmogorov-Smirnof, dicha prueba arrojó resultados de normalidad para todas las variables analizadas de las situaciones experimentales EA, EVsuelo y EV5m. Es por ello que en el presente trabajo de investigación se utilizó estadística paramétrica. Como medidas descriptivas, se calcularon el máximo, mínimo, media y la desviación estándar. En relación a las situaciones experimentales, para estudiar las posibles diferencias en las variables estudiadas dentro de cada grupo de velocistas (intragrupo) en la situación experimental 1 (MTR), se empleó una prueba T de Student para muestras independientes. En las situaciones experimentales 2, 3 y 4, para conocer las diferencias entre ambos grupos de velocistas en cada situación, se utilizó igualmente la prueba T para muestras independientes, mientras que un ANOVA simple (con post hoc Bonferroni) se utilizó para analizar las diferencias para cada grupo (VDA y VsDA) por situación experimental. Así mismo, se utilizó un ANOVA de medidas repetidas, donde el tipo de estímulo (situación experimental) fue la variable intra-grupo y el grupo de velocistas participantes (VDA y VsDA) la entre-grupo, realizándose esta prueba para evaluar en cada situación el TR, t1m0 y t20m y las interacciones entre las variables. Para el tratamiento estadístico fue utilizado el paquete estadístico SPSS 18.0 (Chicago, IL, EEUU). Los niveles de significación fueron establecidos para un ≤0.05, indicando el valor de p en cada caso. Uno de los aspectos más relevantes de este trabajo es la medición en diferentes situaciones, con instrumentación distinta y con situaciones experimentales distintas, del TR en velocistas con y sin discapacidad auditiva. Ello supuso el desarrollo de un diseño de investigación que respondió a las necesidades planteadas por los objetivos del estudio, así como el desarrollo de instrumentación específica (Rojo-Lacal, Soto-Rey, Pérez-Tejero y Rojo-González, 2014; Soto-Rey et al., 2015) y distintas situaciones experimentales que reprodujeran las condiciones de práctica y competición real de VsDA y VDA en las pruebas atléticas de velocidad, y más concretamente, en las salidas. El análisis estadístico mostró diferencias significativas entre los estímulos visuales y sonoros medidos con el MTR, siendo menor el TR ante el estímulo visual que ante el sonoro, tanto para los atletas con discapacidad auditiva como para los que no la presentaron (TR visual, 0.195 s ± 0.018 vs 0.197 s ± 0.022, p≤0.05; TR sonoro 0.230 s ± 0.016 vs 0.237 s ± 0.045, p≤0.05). Teniendo en cuenta los resultados según población objeto de estudio y situación experimental, se registraron diferencias significativas entre ambas poblaciones, VDA y VsDA, siendo más rápidos los VDA que VsDA en la situación experimental con el estímulo visual en el suelo (EVsuelo, 0.191 ±0.025 vs 0.210 ±0.025, p≤0.05, respectivamente) y los VsDA en la situación experimental con el estímulo auditivo (EA, 0.396 ±0.045 vs 0.174 ±0.021, p≤0.05), aunque sin diferencias entre ambos grupos en la situación experimental con el estímulo visual a 5m de los tacos de salida. Es de destacar que en el TR no hubo diferencias significativas entre EA para VsDA y EVsuelo para VDA. El ANOVA simple registró diferencias significativas en todas las situaciones experimentales dentro de cada grupo y para todas las variables, por lo que estadísticamente, las situaciones experimentales fueron diferentes entre sí. En relación al de ANOVA medidas repetidas, la prueba de esfericidad se mostró adecuada, existiendo diferencias significativas en las varianzas de los pares de medias: el valor de F indicó que existieron diferencias entre las diferentes situaciones experimentales en cuanto a TR, incluso cuando éstas se relacionaban con el factor discapacidad (factor interacción, p≤0,05). Por ello, queda patente que las situaciones son distintas entre sí, también teniendo en cuenta la discapacidad. El η2 (eta al cuadrado, tamaño del efecto, para la interacción) indica que el 91.7% de la variación se deben a las condiciones del estudio, y no al error (indicador de la generalización de los resultados del estudio). Por otro lado, la evaluación del dispositivo luminoso fue positiva en relación a la iluminación, comodidad de uso, ubicación, color, tamaño, adecuación del dispositivo y del equipamiento necesario para adaptar al sistema de salida. La totalidad de los atletas afirman rotundamente que el dispositivo luminoso favorecería la adaptación al sistema de salida atlética para permitir una competición inclusiva. Asimismo concluyen que el dispositivo luminoso favorecería el rendimiento o mejora de marca en la competición. La discusión de este estudio presenta justificación de las diferencias demostradas que el tipo de estímulo y su colocación son clave en el TR de esta prueba, por lo que podríamos argumentar la necesidad de contar con dispositivos luminosos para VDA a la hora de competir con VsDA en una misma prueba, inclusiva. El presente trabajo de investigación ha demostrado, aplicando el método científico, que el uso de estos dispositivos, en las condiciones técnicas y experimentales indicadas, permite el uso por parte del VDA, usando su mejor TR visual posible, que se muestra similar (ns) al TR auditivo de VsDA, lo que indica que, para competiciones inclusivas, la salida usando el semáforo (para VDA) y la salida habitual (estímulo sonoro) para VsDA, puede ser una solución equitativa en base a la evidencia demostrada en este estudio. De esta manera, y como referencia, indicar que la media de los TR de los velocistas en la final de los 100 m.l. en los Juegos Olímpicos de Londres 2012 fue de 0.162 ±0.015. De esta manera, creemos que estos parámetros sirven de referencia a técnicos deportivos, atletas y futuros trabajos de investigación. Las aplicaciones de este trabajo permitirán modificaciones y reflexiones en forma de apoyo al entrenamiento y la competición para el entrenador, o juez de salida en la competición que, creemos, es necesaria para proporcionar a este colectivo una atención adecuada en las salidas, especialmente en situaciones inclusivas de práctica. ABSTRACT This research aims to study of reaction time (RT) in sprinters with and without hearing impairment from the Sports Science perspective. The approach of this study came asking whether there were differences in the visual and auditory RT applied to sprinters with and without hearing impairment, thinking about the future development of inclusive competition between the two groups. Therefore, this study attempts to resolve the difficulties commonly founded by sprinters with hearing impairments during competitions. A priori, sprinters with hearing impairment would compete in a disadvantage situation as a result of the use of a staring signal not suitable for them (from the blocks, they have to look to the judge´s pistol or the movement of an opponent). The document is divided into three parts. In the first part of the review of relevant theoretical framework and justification of the study is presented. The second part focuses on the research objectives, material and method, where results, discussion and conclusions of the study, as well as the limitations of this study and future research are presented. The third part contains references and the fourth, annexes. In the first part, we present the theoretical framework consisting of five chapters, organizing the state of the art of RT, determined by the characteristics of the task and other factors that influence the RT as object of our study. Then we present the main structural and functional aspects of the nervous system associated with visual and auditory RT. After that, sport for people with hearing disabilities is presented, investigating its peculiarities and eligibility criteria is that group within the deaf sport. Finally, we discuss the theoretical foundation of the study of start speed in athletics as a key aspect that will guide our research, especially the determining parameters in placing the starting blocks for athletes with and without hearing impairment, the starting position and the actual placement of stimuli in such a situation. The second part of the research aims to study the values of simple manual visual RT, RT start from blocks and travel times up to 10m and 20m of sprinters with and without hearing impairment, and to analyze possible differences in RT as position and type of light stimulus with respect to both groups of athletes. The third objective of the study is to assess the pertinence of the lighting device developed and used in the study, in a qualitatively way by athletes themselves. Data collection for this study was carried out between February and May 2014, in the Athletics module at the High Performance Centre Joaquin Blume (Madrid) with the two study groups: 9 sprinters with hearing impairments(VDA, reaching 60% of the population in Spain, according to the number of licenses for athletics at FEDS: sprint, 100 and 200 m.l., at the time of the study), and another 13 sprinters without disability (VsDA) who voluntarily presented themselves, with same inclusion criteria for both groups. For measuring and data collection materials such as recording sheet, gauge reaction time (MTR), starting blocks, ReacTime®, luminous device connected to the starting blocks, photocells, computer and software ReacTime, and video camera were used. The methodology used in this study was correlational, analyzing the results of simple manual RT according sensory pathway (visual and auditory) between the two groups (VsDA and VDA). Also auditory and visual RT was studied depending the placement of the start light signal (on the ground and 5 meters, visual pathway) and athletic start gun signal (auditory pathway, conventional situation) and travel time up to 10m (t10m) and 20m (t20m) for both groups of sprinters. Finally, we developed and carried out an evaluation questionnaire for VDA athletes in order to determine the degree of satisfaction after completing the series of experiments with lighting device and adapted to start systems in athletic speed. In order to test the feasibility of the methodology described and tested in the context of real analysis of the experimental protocol, a pilot study in order to know the possible differences visual RT from the starting blocks in sprinters with hearing impairments was performed, to said output using a visual stimulus coordinated by a lighting device with sound output signal (Soto-Rey Perez-Tejero, Rojo-González y Álvarez-Ortiz, 2015). For the statistical procedures, in order to analyze the distribution of the data and their normality, Kolmogorov-Smirnov test was applied, this test yielded normal results for all variables analyzed during EA, EVsuelo and EV5m experimental situations. Parametric statistics were used in this research. As descriptive measures, the maximum, minimum, mean and standard deviation were calculated. In relation to experimental situations, to study possible differences in the variables studied in each group sprinters (intragroup) in the experimental situation 1 (MTR), a Student t test was used for independent samples. Under the experimental situations 2, 3 and 4, to know the differences between the two groups of sprinters in every situation, the T test for independent samples was used, while a simple ANOVA (with post hoc Bonferroni) was used to analyze differences for each group (VDA and VsDA) by experimental situation. Likewise, a repeated measures ANOVA, where the type of stimulus (experimental situation) was variable intra-group and participants sprinters group (VDA and VsDA) the variable between-group, was performed to assess each situation for RT, t10m and t20m, and also interactions between variables. For the statistical treatment SPSS 18.0 (Chicago, IL, USA) was used. Significance levels were set for  ≤0.05, indicating the value of p in each case. One of the most important aspects of this work is the measurement of RT in sprinters with and without hearing impairment in different situations, with different instrumentation and different experimental situations. This involved the development of a research design that responded to the needs raised by the study aims and the development of specific instrumentation (Rojo-Lacal, Soto-Rey Perez-Tejero and Rojo-Gonzalez, 2014; Soto-Rey et al., 2015) and different experimental situations to reproduce the conditions of practical and real competition VsDA and VDA in athletic sprints, and more specifically, at the start. Statistical analysis showed significant differences between the visual and sound stimuli measured by the MTR, with lower RT to the visual stimulus that for sound, both for athletes with hearing disabilities and for those without (visual RT, 0.195 s ± 0.018 s vs 0.197 ± 0.022, p≤0.05; sound RT 0.230 s ± 0.016 vs 0.237 s ± 0.045, p≤0.05). Considering the results according to study population and experimental situation, significant differences between the two populations, VDA and VsDA were found, being faster the VDA than VsDA in the experimental situation with the visual stimulus on the floor (EVsuelo, recorded 0.191 s ± 0.025 vs 0.210 s ± 0.025, p≤0.05, respectively) and VsDA in the experimental situation with the auditory stimulus (EA, 0.396 s ± 0.045 vs 0.174 s ± 0.021, p≤0.05), but no difference between groups in the experimental situation with the 5m visual stimulus to the starting blocks. It is noteworthy that no significant differences in EA and EVsuelo between VsDA to VDA, respectively, for RT. Simple ANOVA showed significant differences in all experimental situations within each group and for all variables, so statistically, the experimental situations were different. Regarding the repeated measures ANOVA, the sphericity test showed adequate, and there were significant differences in the variances of the pairs of means: the value of F indicated that there were differences between the different experimental situations regarding RT, even when they were related to the disability factor (factor interaction, p≤0.05). Therefore, it is clear that the situations were different from each other, also taking into account impairment. The η2 (eta squared, effect size, for interaction) indicates that 91.7% of the variation is due to the conditions of the study, not by error (as indicator of the generalization potential of the study results). On the other hand, evaluation of the light signal was positively related to lighting, ease of use, location, color, size, alignment device and equipment necessary to adapt the start system. All the athletes claim strongly in favor of the lighting device adaptation system to enable athletic competition inclusive. Also they concluded that light device would enhance performance or would decrease their RT during the competition. The discussion of this study justify the type of stimulus and the start light positioning as key to the RT performance, so that we could argue the need for lighting devices for VDA when competing against VsDA the same competition, inclusive. This research has demonstrated, applying the scientific method, that the use of these devices, techniques and given experimental conditions, allows the use of the VDA, using his best visual RT, shown similar (ns) auditory RT of VsDA, indicating that for inclusive competitions, the start signal using the light (for VDA) and the usual start (sound stimulus) to VsDA can be an equitable solution based on the evidence shown in this study. Thus, and as a reference, indicate that the average of the RT sprinters in the 100 m. final at the 2012 Summer Olympic Games was 0.162 s ± 0.015. Thus, we believe that these parameters become a reference to sports coaches, athletes and future research. Applications of this work will allow modifications and reflections in the form of support for training and competition for the coach, or judge, as we believe is necessary to provide adequate attention to VDA in speed starts, especially in inclusive practice situations.

Scalable software architecture for on-line multi-camera video processing

In this paper we present a scalable software architecture for on-line multi-camera video processing, that guarantees a good trade off between computational power, scalability and flexibility. The software system is modular and its main blocks are the Processing Units (PUs), and the Central Unit. The Central Unit works as a supervisor of the running PUs and each PU manages the acquisition phase and the processing phase. Furthermore, an approach to easily parallelize the desired processing application has been presented. In this paper, as case study, we apply the proposed software architecture to a multi-camera system in order to efficiently manage multiple 2D object detection modules in a real-time scenario. System performance has been evaluated under different load conditions such as number of cameras and image sizes. The results show that the software architecture scales well with the number of camera and can easily works with different image formats respecting the real time constraints. Moreover, the parallelization approach can be used in order to speed up the processing tasks with a low level of overhead

Video analysis based vehicle detection and tracking using an MCMC sampling framework

This article presents a probabilistic method for vehicle detection and tracking through the analysis of monocular images obtained from a vehicle-mounted camera. The method is designed to address the main shortcomings of traditional particle filtering approaches, namely Bayesian methods based on importance sampling, for use in traffic environments. These methods do not scale well when the dimensionality of the feature space grows, which creates significant limitations when tracking multiple objects. Alternatively, the proposed method is based on a Markov chain Monte Carlo (MCMC) approach, which allows efficient sampling of the feature space. The method involves important contributions in both the motion and the observation models of the tracker. Indeed, as opposed to particle filter-based tracking methods in the literature, which typically resort to observation models based on appearance or template matching, in this study a likelihood model that combines appearance analysis with information from motion parallax is introduced. Regarding the motion model, a new interaction treatment is defined based on Markov random fields (MRF) that allows for the handling of possible inter-dependencies in vehicle trajectories. As for vehicle detection, the method relies on a supervised classification stage using support vector machines (SVM). The contribution in this field is twofold. First, a new descriptor based on the analysis of gradient orientations in concentric rectangles is dened. This descriptor involves a much smaller feature space compared to traditional descriptors, which are too costly for real-time applications. Second, a new vehicle image database is generated to train the SVM and made public. The proposed vehicle detection and tracking method is proven to outperform existing methods and to successfully handle challenging situations in the test sequences.

Adaptive Multi-Camera System for Real Time Object Detection

In this paper we present an adaptive multi-camera system for real time object detection able to efficiently adjust the computational requirements of video processing blocks to the available processing power and the activity of the scene. The system is based on a two level adaptation strategy that works at local and at global level. Object detection is based on a Gaussian mixtures model background subtraction algorithm. Results show that the system can efficiently adapt the algorithm parameters without a significant loss in the detection accuracy.

Mapping wide row crops with video sequences acquired from a tractor moving at treatment speed

This paper presents a mapping method for wide row crop fields. The resulting map shows the crop rows and weeds present in the inter-row spacing. Because field videos are acquired with a camera mounted on top of an agricultural vehicle, a method for image sequence stabilization was needed and consequently designed and developed. The proposed stabilization method uses the centers of some crop rows in the image sequence as features to be tracked, which compensates for the lateral movement (sway) of the camera and leaves the pitch unchanged. A region of interest is selected using the tracked features, and an inverse perspective technique transforms the selected region into a bird’s-eye view that is centered on the image and that enables map generation. The algorithm developed has been tested on several video sequences of different fields recorded at different times and under different lighting conditions, with good initial results. Indeed, lateral displacements of up to 66% of the inter-row spacing were suppressed through the stabilization process, and crop rows in the resulting maps appear straight

EVA: Laparoscopic instrument tracking based on endoscopic video analysis for psychomotor skills assessment

INTRODUCTION: The EVA (Endoscopic Video Analysis) tracking system a new tracking system for extracting motions of laparoscopic instruments based on non-obtrusive video tracking was developed. The feasibility of using EVA in laparoscopic settings has been tested in a box trainer setup. METHODS: EVA makes use of an algorithm that employs information of the laparoscopic instrument's shaft edges in the image, the instrument's insertion point, and the camera's optical centre to track the 3D position of the instrument tip. A validation study of EVA comprised a comparison of the measurements achieved with EVA and the TrEndo tracking system. To this end, 42 participants (16 novices, 22 residents, and 4 experts) were asked to perform a peg transfer task in a box trainer. Ten motion-based metrics were used to assess their performance. RESULTS: Construct validation of the EVA has been obtained for seven motion-based metrics. Concurrent validation revealed that there is a strong correlation between the results obtained by EVA and the TrEndo for metrics such as path length (p=0,97), average speed (p=0,94) or economy of volume (p=0,85), proving the viability of EVA. CONCLUSIONS: EVA has been successfully used in the training setup showing potential of endoscopic video analysis to assess laparoscopic psychomotor skills. The results encourage further implementation of video tracking in training setups and in image guided surgery.

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.

Adaptive spatio-temporal filter for low-cost camera depth maps

In this paper we present an adaptive spatio-temporal filter that aims to improve low-cost depth camera accuracy and stability over time. The proposed system is composed by three blocks that are used to build a reliable depth map of static scenes. An adaptive joint-bilateral filter is used to obtain consistent depth maps by jointly considering depth and video information and by adapting its parameters to different levels of estimated noise. Kalman filters are used to reduce the temporal random fluctuations of the measurements. Finally an interpolation algorithm is used to obtain consistent depth maps in the regions where the depth information is not available. Results show that this approach allows to considerably improve the depth maps quality by considering spatio-temporal information and by adapting its parameters to different levels of noise.

NAMA3DS1-COSPAD1: Subjective video quality assessment database on coding conditions introducing freely available high quality 3D stereoscopic sequences

Research in stereoscopic 3D coding, transmission and subjective assessment methodology depends largely on the availability of source content that can be used in cross-lab evaluations. While several studies have already been presented using proprietary content, comparisons between the studies are difficult since discrepant contents are used. Therefore in this paper, a freely available dataset of high quality Full-HD stereoscopic sequences shot with a semiprofessional 3D camera is introduced in detail. The content was designed to be suited for usage in a wide variety of applications, including high quality studies. A set of depth maps was calculated from the stereoscopic pair. As an application example, a subjective assessment has been performed using coding and spatial degradations. The Absolute Category Rating with Hidden Reference method was used. The observers were instructed to vote on video quality only. Results of this experiment are also freely available and will be presented in this paper as a first step towards objective video quality measurement for 3DTV.

Efficient hybrid monocular-stereo approach to on-board, video-based traffic sign detection and tracking

In this paper we propose an innovative method for the automatic detection and tracking of road traffic signs using an onboard stereo camera. It involves a combination of monocular and stereo analysis strategies to increase the reliability of the detections such that it can boost the performance of any traffic sign recognition scheme. Firstly, an adaptive color and appearance based detection is applied at single camera level to generate a set of traffic sign hypotheses. In turn, stereo information allows for sparse 3D reconstruction of potential traffic signs through a SURF-based matching strategy. Namely, the plane that best fits the cloud of 3D points traced back from feature matches is estimated using a RANSAC based approach to improve robustness to outliers. Temporal consistency of the 3D information is ensured through a Kalman-based tracking stage. This also allows for the generation of a predicted 3D traffic sign model, which is in turn used to enhance the previously mentioned color-based detector through a feedback loop, thus improving detection accuracy. The proposed solution has been tested with real sequences under several illumination conditions and in both urban areas and highways, achieving very high detection rates in challenging environments, including rapid motion and significant perspective distortion