XL Jornadas de Automática: libro de actas (Ferrol, 4-6 de septiembre de 2019)最新文献

{"title":"Mejoras del simulador de dispersión de gases GADEN para desarrollos de robótica olfativa","authors":"P. Ojeda, J. Monroy, J. Gonzalez-Jimenez","doi":"10.17979/SPUDC.9788497497169.552","DOIUrl":"https://doi.org/10.17979/SPUDC.9788497497169.552","url":null,"abstract":"espanolDentro de las disciplinas cientificas, las herramientas de simulacion juegan un papel fundamental durante el proceso de diseno y desarrollo de nuevas soluciones, permitiendo reducir los tiempos de desarrollo y posibilitando un estudio detallado del efecto de multiples parametros. En este trabajo nos centramos en GADEN, un novedoso simulador de dispersion de gases para aplicaciones roboticas, proponiendo un conjunto de mejoras con el objetivo de facilitar su uso y mejorar su rendimiento computacional. Ademas de una descripcion detallada de los cambios realizados, se incluye un estudio cuantitativo del efecto de los mismos sobre el rendimiento de la simulacion. EnglishWithin scientific disciplines, simulation tools play a fundamental role during the process of designing and developing new solutions, reducing development times and enabling detailed studies of the effect of multiple parameters. In this work we focus on GADEN, a novel gas dispersion simulator for robotic applications, proposing a set of improvements with the aim to facilitate its use and improve its computational performance. In addition to a detailed description of the changes introduced, a quantitative study of their effect on the performance of the simulation is included.","PeriodicalId":189601,"journal":{"name":"XL Jornadas de Automática: libro de actas (Ferrol, 4-6 de septiembre de 2019)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127145412","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Experiencias educativas basadas en el sistema Marpabiobot","authors":"Gustavo Adolfo Casañ Núñez, José Vicente Martí Avilés, Raúl Marín Prades, D. Fornas, P. Valero","doi":"10.17979/SPUDC.9788497497169.679","DOIUrl":"https://doi.org/10.17979/SPUDC.9788497497169.679","url":null,"abstract":"espanolEn este articulo se presenta un robot modular y de bajo coste, MARPABIOBOT (Modular Arduino ROS Printable Android Robot), que ya ha sido puesto a prueba con exito como herramienta educativa en varios niveles educativos (colegio, instituto y universidad). Al ser hardware y software libre, basado en componentes de bajo coste y facil accesibilidad, las posibilidades de aprendizaje que ofrece destacan sobre las de otros sistemas roboticos que estan mas orientados al aprendizaje de uno de los aspectos de la robotica (generalmente la programacion) o limitan mucho la profundidad a la que se puede llegar al emplearlos. EnglishIn this paper MARPABIOBOT, a modular low cost robot which has already been tested as a teaching tool at several educational levels (school, high school and university) is presented. As it is free hardware and software, based in low cost and easy to find and use components, the possibilities it offers stand out among other robotic systems that are usually oriented towards only one aspect of robotics (generally programming) or they are limited in the depth they allow the students to arrive.","PeriodicalId":189601,"journal":{"name":"XL Jornadas de Automática: libro de actas (Ferrol, 4-6 de septiembre de 2019)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129454672","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Modelos empíricos del campo solar en plantas termosolares de concentración. Aplicación a la planificación","authors":"E. Cojocaru, J. M. Caro, M. Vázquez, Manuel Emilio Gegúndez Arias","doi":"10.17979/SPUDC.9788497497169.466","DOIUrl":"https://doi.org/10.17979/SPUDC.9788497497169.466","url":null,"abstract":"espanolUno de los bloques fundamentales de una planta termosolar de concentracion es el campo solar. En este bloque, la energia del recurso solar se captura y concentra sobre un fluido para su posterior utilizacion como energia termica. La estimacion de la potencia termica disponible en el campo solar a partir de valores del recurso solar es una informacion de gran utilidad en diversas aplicaciones. Esta estimacion se puede conseguir utilizando un modelo del campo solar disenado en base a primeros principios. Sin embargo la construccion de un modelo de este tipo puede ser complejo y requerir la participacion de un experto con un conocimiento en profundidad del campo solar a modelar. En este trabajo se propone como alternativa la utilizacion de modelos empiricos del campo solar. En este caso, el modelo se obtiene a partir de un conjunto de medidas realizadas en el campo solar. Se proponen dos tipos de modelos empiricos: parametrico y orientado a datos. Con el fin de estudiar la aplicabilidad de los modelos propuestos se ha considerado su utilizacion en el problema de la generacion optima auto-planificada en una planta CSP que participa en un mercado electrico a un dia. En un contexto de simulacion y con el objeto de comparar diferentes opciones, se ha realizado un estudio economico donde se evaluan varias estrategias de planificacion en una planta basada en colectores cilindro-parabolicos de 50 MW con almacenamiento termico. Las estrategias de planificacion se diferencian unicamente en el modelo del campo solar utilizado. Los resultados muestran que las estrategias que utilizan los modelos empiricos del campo solar proporcionan resultados competitivos y que por tanto, se pueden utilizar como una alternativa viable a los basados en primeros principios. La utilizacion de modelos empiricos simplifica significativamente el diseno del planificador de produccion. EnglishAn important block of a concentrated solar thermal plant is the solar field. In this block, the solar energy is concentrated as thermal energy in a fluid. An estimation of the available thermal power based on the available solar resource is a useful information in several applications. This estimation can be obtained using a solar field model based on first-principles. However, to build a model of this kind, can be complex and requires a human expert with in depth knowledge of the solar filed to be modeled. This work proposes an alternative, to use empirical models of the solar field. In this case, the model is obtained using a set of measurements from the solar field. Two kind of empirical models are proposed: parametric and data-driven models. In order to study the applicability of the proposed models, the optimal self-scheduling generation problem in a concentrated solar thermal plant is considered. Several scheduling strategies with different solar field models are compared in a simulation context. The simulations show that the strategies with empirical models of the solar field prov","PeriodicalId":189601,"journal":{"name":"XL Jornadas de Automática: libro de actas (Ferrol, 4-6 de septiembre de 2019)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133639193","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Experiencia de aprendizaje basado en proyectos con evaluación competitiva-colaborativa para Regulación Automática","authors":"Luís Orihuela","doi":"10.17979/SPUDC.9788497497169.324","DOIUrl":"https://doi.org/10.17979/SPUDC.9788497497169.324","url":null,"abstract":"espanolEste articulo presenta una experiencia de aprendizaje basado en proyecto en una asignatura de Regulacion Automatica de segundo curso de grado. Todos los estudiantes tienen como objetivo el control de una unidad de transporte. Dicho sistema mecanico, que se les proporciona descrito mediante Simscape, tiene una serie de parametros dependientes del DNI del alumno. Se detallan todas las fases del proyecto y la metodologia que se sigue en las sesiones. Se pone especial enfasis en la evaluacion del proyecto, pues se ha introducido como novedad un sistema de evaluacion competitivo-colaborativo, que aumente la motivacion y disminuya la copia entre los estudiantes. Tal y como se extrae de las encuestas realizadas, la experiencia de los estudiantes ha sido positiva comparada con datos del curso anterior. EnglishThis paper presents an experience of project-based learning in a course of Automatic Control, for second-year students of a Bachelor’s degree. The students’goal is the control of a transport unit. This mechanical system, which is given to them described with Simscape, contains a set of parameters that depends on the identification number of each student. The paper presents the details of all the phases of the project, as well as the teaching methodology used in each session. Special emphasis is put on the assessment, and a novel competitive-collaborative assessment has been introduced, looking for an increment in motivation and reducing the plagiarism between students. As it is deduced from the questionnaires, the experience of the students has been rather positive compared with the answers of the previous year.","PeriodicalId":189601,"journal":{"name":"XL Jornadas de Automática: libro de actas (Ferrol, 4-6 de septiembre de 2019)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134455281","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integración End-to-End a través del modelo del producto 4.0","authors":"I. Sarachaga, A. Burgos, Nagore Iriondo, M. L. Alvarez, Marga Marcos","doi":"10.17979/SPUDC.9788497497169.155","DOIUrl":"https://doi.org/10.17979/SPUDC.9788497497169.155","url":null,"abstract":"Digitization is a clear need in the industrial environment for all companies seeking to move towards Industry 4.0. This paper presents a proposal for the digitization of the first phase of the product lifecycle corresponding to the design and manufacture in the company environment, which allows integration with suppliers and customers. This approach adopts the standards proposed in the RAMI 4.0 model and the I4.0 component model. The technological solution used in the prototype uses web services with API REST and distributed XML databases. This prototype has been used in a case study to show the interoperability of applications throughout the product lifecycle. Specifically, it shows the exchange of information between the scheduler and the product model.","PeriodicalId":189601,"journal":{"name":"XL Jornadas de Automática: libro de actas (Ferrol, 4-6 de septiembre de 2019)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124386133","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Uso de técnicas de machine learning para realizar mapping en robótica móvil","authors":"Sergio Cebollada, V. Román, L. Payá, María Flores Tenza, L. M. Jiménez, Óscar Reinoso","doi":"10.17979/SPUDC.9788497497169.686","DOIUrl":"https://doi.org/10.17979/SPUDC.9788497497169.686","url":null,"abstract":"espanolEl trabajo presentado consiste en un estudio de diversos clasificadores basados en machine learning como herramienta para llevar a cabo la tarea de mapeo y localizacion en robotica movil. En concreto, estos clasificadores son utilizados para solventar la tarea de localizacion \"gruesa\", la cual forma parte de los procesos a realizar para resolver la localizacion jerarquica. El proceso de localizacion llevado a cabo por el robot consistira en (1) capturar una imagen desde una posicion desconocida, (2) calcular su correspondiente descriptor de apariencia global, (3) introducir dicha informacion al clasificador y obtener la estancia en la cual se encuentra el robot en ese instante. Tras esto, (5) el robot realizara el problema de image retrieval con toda la informacion visual de entrenamiento contenida en la estancia seleccionada (localizacion - na). Este trabajo evalua el uso de tres clasificadores (Na ve Bayes, SVM y clasificador basado en red neuronal) los cuales se entrenan con tres posibles descriptores de apariencia global (HOG, gist y un descriptor obtenido a partir de una CNN). Los experimentos se llevan a cabo mediante el uso de un dataset que contiene imagenes omnidireccionales capturadas en entornos de interior y que presenta cambios dinamicos (personas andando, cambios de mobiliario, etc.). Los resultados obtenidos demuestran que el metodo propuesto es una alternativa eficiente para realizar la tarea de localizacion jerarquica en cuanto error de localizacion y tiempo de computo. EnglishThis work introduces a study regarding the use of several classi ers based on machine learning tools to carry out the mapping and localization task in mobile robotics. These classi ers are used to solve the rough localization, which is part of the hierachical localization process. Therefore, the localization tackled by the robot consists in (1) obtaining an image from an unknown position, (2) calculating its related global appearance descriptor, (3) puting this information into the classifer to estimate the current room. Afterwards, (5) the robot carries out the image retrieval problem with all the visual information provided by the training dataset contained in the selected room ( ne localization step). This work evaluates the use of three types of classi ers (Na ve Bayes, SVM and a classi er based on neural networks) which are trained with three possible global appearance descriptors (HOG, gist and a descriptor calculated from a CNN). The experiments are carried out through the use of a dataset which contains omnidirectional images captured indoor under dynamic changes (people walking, furniture changes, etc.). The results obtained show that this method proposed is an e cient alternative to tackle the hierarchical localization regarding the localization error and the computing time.","PeriodicalId":189601,"journal":{"name":"XL Jornadas de Automática: libro de actas (Ferrol, 4-6 de septiembre de 2019)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129497002","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Real-time optimisation for a heat-recovery section with equipment degradation","authors":"Maria P. Marcos, J. L. Pitarch, C. Prada","doi":"10.17979/SPUDC.9788497497169.513","DOIUrl":"https://doi.org/10.17979/SPUDC.9788497497169.513","url":null,"abstract":"This work aims to optimise the operation of an industrial heat-recovery section in a fibre-production factory. The section is formed by a network of heat exchangers able to be supplied with different hot sources. The goal is minimising the resource utilisation in real time (the sources usage) while satisfying a set of operational constrains. Hence, problems of economically optimal hot-sources allocation to heat exchangers arise. The problem is formulated and solved via mixed-integer non-linear programming. Furthermore, concerns about the practical implementation and the degradation of the equipment due to the fouling effect are also taken into account in the optimisation. In this way, the decision-support tool not only provides the optimal allocation, but also suggestions on which heat exchangers are potentially beneficial to be clean.","PeriodicalId":189601,"journal":{"name":"XL Jornadas de Automática: libro de actas (Ferrol, 4-6 de septiembre de 2019)","volume":"135 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127391687","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Identificación y conteo de aceitunas en imágenes digitales tomadas en el olivar mediante morfología matemática y redes neuronales convolucionales","authors":"Arturo Aquino Martín, Juan Manuel Ponce, Borja Millán, Diego Tejada Guzmán, José Manuel Andújar Márquez","doi":"10.17979/SPUDC.9788497497169.818","DOIUrl":"https://doi.org/10.17979/SPUDC.9788497497169.818","url":null,"abstract":"espanolLa estimacion precoz y precisa de la produccion es un objetivo muy codiciado en la agricultura moderna. En el caso de la olivicultura, ello toma una especial relevancia debido al alto valor economico que alcanza su produccion. Este articulo presenta una metodologia enfocada a lograr dicho objetivo. Concretamente, se propone un algoritmo de vision artificial capaz de detectar las aceitunas visibles en una imagen digital de un arbol de olivo, tomada directamente en campo, de noche y con iluminacion artificial. En primera instancia, esta imagen es preprocesada mediante tecnicas de morfologia matematica y filtrado estadistico para, a partir de ella, obtener un conjunto de subimagenes con alta probabilidad de contener una aceituna. Este preprocesamiento reduce el espacio potencial de busqueda en una magnitud de 103. A continuacion, estas subimagenes son clasificadas por una red neuronal convolucional como ‘aceituna’ o ‘descarte’. De un total de 304.483 subimagenes, extraidas de 21 imagenes, la red clasifico correctamente el 98,23%, y arrojo un coeficiente de determinacion R2 igual a 0,9875, al enfrentar el numero de aceitunas detectadas con el obtenido manualmente. Esta precision alcanzada indica que el algoritmo desarrollado constituye un paso certero en la implementacion de un futuro sistema de estimacion de la produccion de cultivos de olivo. EnglishEarly and accurate yield estimation is a very valued objective for modern agriculture. In the case of oliviculture, it is especially relevant due to the high economic value of its production. This paper presents a methodology aimed at achieving that end. Concretely, it comprises an artificial vision algorithm able to detect those olives that are visible in a digital image of an olive tree, captured directly in the field, at night-time and with artificial illumination. First, the image is preprocessed by means of mathematical morphology techniques and statistical filtering to, from this output, generate a subset of images with high probability of containing an olive. Thus, this preprocessing reduces the search space in a magnitude of 103. Next, these subimages are classified by a convolutional neural network as ‘olive’ or ‘discarded’. From a total of 304,483 subimages, extracted from 21 images, the net correctly classified 98.23% of cases, and gave a coefficient of determination R2 of 0.9875 when facing the number of detected olives to the real one. This achieved accuracy indicates that the found algorithm constitutes a solid step towards the implementation of a future system for early yield estimation of olive orchards","PeriodicalId":189601,"journal":{"name":"XL Jornadas de Automática: libro de actas (Ferrol, 4-6 de septiembre de 2019)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132847574","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Interfaz para un optimizador que gestiona la producción de electricidad en una fábrica azucarera","authors":"S. Hernández, Cristian Pablos de la Fuente, Luis Felipe Acebes Arconada","doi":"10.17979/SPUDC.9788497497169.506","DOIUrl":"https://doi.org/10.17979/SPUDC.9788497497169.506","url":null,"abstract":"espanolLa optimizacion de la operacion de procesos industriales, se erige como una base fundamental de la nueva revolucion industrial. Sin embargo, su implementacion en el dia a dia de las empresas, muchas veces es lastrada debido a la necesidad de conocimientos de programacion por parte del usuario final, y lo poco intuitivos que son los entornos desde los cuales se puede ejecutar. En este articulo, se presenta una propuesta para la interaccion y manejo de un algoritmo desarrollado en Python, que trata de optimizar la operacion de una planta azucarera simulada que participa en el mercado diario electrico espanol. Para ello, se ha desarrollado una Interfaz Hombre Maquina, que actua como enlace entre optimizacion y usuario, y que ha sido implementada mediante el software industrial Wonderware y el estandar de comunicaciones OPC UA. Como resultado, el operario es capaz de lanzar optimizaciones con facilidad, e interpretar sus resultados sin necesitar conocimiento alguno de programacion. EnglishThe optimization of the operation of industrial processes, stands as a fundamental basis of the new industrial revolution. However, its implementation in the industry daily work is often limited due to the operator’s lack of programming knowledge, and the counter-intuitive environments where the optimization is programmed and executed. In this article, we present a proposal for the interaction and management of an algorithm developed in Python, which seeks to optimize the operation of a simulated sugar plant that participates in the Spanish electricity daily market. For this purpose, a Human Machine Interface has been developed, which works as a link between the optimization and the final user. It has been implemented using the industrial software Wonderware and the communication standard OPC UA. As a result, the operator is able to run optimizations easily, and interpret their results without the need of any programming knowledge. This is key in order to push the use of optimization in the industry.","PeriodicalId":189601,"journal":{"name":"XL Jornadas de Automática: libro de actas (Ferrol, 4-6 de septiembre de 2019)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129750549","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Asistencia al aparcamiento basado en una cámara de tiempo de vuelo","authors":"Myriam Elizabeth Vaca Recalde, Luis Paarup Peláez, Enrique D. Marti Munoz, Ray Lattarulo, Xavier Udaeta","doi":"10.17979/SPUDC.9788497497169.810","DOIUrl":"https://doi.org/10.17979/SPUDC.9788497497169.810","url":null,"abstract":"espanolEn este articulo se propone un asistente de aparcamiento basado en la reconstruccion de objetos alrededor del vehiculo, usando informacion obtenida de una camara de Tiempo de Vuelo (ToF, del ingles Time-to-Flight). El metodo propuesto se centra en la deteccion de las matriculas de los vehiculos de alrededor, para estimar su posicion y determinar espacios libres de aparcamiento. Para ello, se fusiona una imagen 2D de intensidad de luz recibida, y una nube de puntos 3D creada a partir de la informacion de profundidad. Esta fusion permite relacional cada pixel de la imagen con una posicion 3D, por lo que se obtiene una referencia 3D del entorno facilitando al conductor la maniobra de aparcamiento que esta realizando. El algoritmo propuesto mejora la deteccion de los vehiculos resolviendo dos de los principales problemas de trabajar con camaras: 1) obtencion de sombras y reflejos en las imagenes debido al brillo (principalmente en estacionamientos al aire libre), lo que dificulta su proceso para detectar objetos; y 2) la deteccion limitada de objetos de baja reflexion, como los coches oscuros. El sistema es evaluado a traves de una plataforma Renault Twizy en condiciones reales. EnglishThis paper proposes a parking assistant base don the reconstruction of objects around the vehicle, using 2D and 3D data obtained from a Time-to-Flight camera (ToF). The proposed method is based on the fusion of the data obtained from the intensity image and the point cloud. It is mainly on the detection of the vehicle’s plate to estimate their position and determine free parking lots. This fusion allows to link each pixel of the image with a 3D position, so it gets a 3D reference of the environment and a clear vision during the parking maneuver. In addition, this methodology improves the vehicles detection solving two of the relevant problems found in cameras: 1) obtaining shadows and reflections in the images considering brightness (mainly in outdoor parking lots), which hinders the process to detect objects; and 2) limited detection of low reflection objects, such as dark cars. The system is evaluated in a Renault Twizy platform in real conditions.","PeriodicalId":189601,"journal":{"name":"XL Jornadas de Automática: libro de actas (Ferrol, 4-6 de septiembre de 2019)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127678233","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}