Proyectos en empresas: la experiencia de Ingeniería Informática Empresarial

Esta comunicación tiene por objetivo exponer la experiencia a la fecha de la participación de las empresas en el proceso de formación -bajo un enfoque de desarrollo de competencias- de los Ingenieros en Informática Empresarial de la Universidad de Talca (Chile). En primer lugar se presenta la carrera y el contexto en el que se inserta, así como los principios que guiaron la construcción de su plan de estudios, entre los cuales destaca su orientación hacia la innovación y la enseñanza dual, lo que implica la activa participación de las empresas en el proceso de formación. Esto último implica la aplicación de una metodología de enseñanza dominada por el aprendizaje basado en problemas, lo que conlleva necesariamente a una fuerte vinculación con empresas. Posteriormente se presentan los resultados de esta experiencia desde la perspectiva de los alumnos y de las empresas que permiten identificar las fortalezas, debilidades, oportunidades y amenazas detectadas. Partir de allí se desprenden algunas acciones a seguir con miras a superar las debilidades encontradas

Desenvolupament d’un sistema de visió estereoscòpica per a la reconstrucció tridimensional d’objectes

El projecte consisteix en analitzar, dissenyar i desenvolupar un sistema estèreo binocular (format per dues càmeres) sobre un suport que ofereixi la mobilitat i portabilitat necessària per utilitzar-lo de forma independent, és a dir, sense necessitat de connexió a un ordinador, ja que normalment, els sistemes de visió per computador solen incorporar un ordinador amb un frame grabber (placa de captura d’imatges). Per a dur a terme el sistema estèreo més adient, s’analitzaran els requeriments necessaris, s’estudiaran diferents alternatives, i finalment, es desenvoluparà i es demostrarà el funcionament del sistema en qüestió

Integració d’un visualitzador de volums en una plataforma de reconstrucció de mapes de fibres del cervell

Estudi, disseny i implementació d’un algorisme de visualització de volums i integrar-lo en la plataforma DTIWeb de visualització i processament de dades de DTI. La plataforma DTIWeb és una plataforma desenvolupada conjuntament entre el Laboratori de Gràfics i Imatge de la Universitat de Girona i d’Institut de Diagnòstic per la imatge de l’Hospital Josep Trueta de Girona. Aquesta plataforma integra els mètodes bàsics de reconstrucció de fibres del cervell. La principal limitació de la plataforma és que no suporta la visualització de models 3D. Aquest fet limita el seu us en la pràctica clínica habitual ja que es fa difícil la interpretació dels mapes de connectivitat que genera

Modelatge basat en exemples de carrers d’una ciutat

L’objectiu d’aquest projecte és el desenvolupament d’una eina de generació de xarxes de carrers a partir d’exemples. L’eina ha de permetre generar una xarxa de carrers nova que sigui semblant a l’existent en un mapa vectorial donat. A més, també es pretén unir aquesta aplicació amb l’urbanEngine per tal de poder generar vistes en 3D sobre aquestes xarxes de carrers, a més d’ampliar les opcions de l’urbanEngine a l’hora de crear ciutats

Modelatge procedural de ciutats

L’objectiu d’aquest projecte és el desenvolupament d’una eina pel modelatge procedural de ciutats i xarxes de carrers. El modelatge de carrers és, per si sol, un bon tema on aplicar-hi la programació procedural. Les ciutats solen comptar amb patrons que es van repetint al llarg del territori. El fet de “repetir” una tasca suggereix sempre l’aplicació d’algun tipus de procediment per tal de simplificar i reduir la feina de l’usuari a l’hora de desenvolupar aquesta tasca. Shan utilitzat bàsicament tres eines diferents: Un modelador 3D, un llenguatge d’scripting i un llenguatge flexible per a definir els edificis

Plan de orientación y acogida para un nuevo título de grado acorde al EEES en la Facultad de Informática de la Universidad Politécnica de Madrid

El alumno percibe una gran diferencia entre la educación secundaria y la educación universitaria al comenzar sus estudios de grado. Los programas de orientación que ayudan a afianzar la integración social y académica de los alumnos de nuevo ingreso contribuyen a evitar el abandono de los estudios iniciados en un centro universitario. La Facultad de Informática de la Universidad Politécnica de Madrid (FI-UPM) cuenta con cuatro años de experiencia en la implantación de un programa de mentoría para la orientación y acogida de alumnos de nuevo ingreso, contribuyendo, junto a otras medidas, a una disminución notable de la tasa de abandono. Este bagaje ha permitido la definición de un Plan de Orientación y Acogida para el nuevo título acorde con el Espacio Europeo de Educación Superior (EEES), que incluye tres acciones de carácter complementario. En primer lugar, el Proyecto de Inicio para Alumnos de Nuevo Ingreso, el cual combina los aspectos de orientación y acogida con la realización de un proyecto en equipo en los primeros cuatro días del curso que permite la evaluación de las competencias de trabajo en equipo y presentación oral. En segundo lugar, el Plan de Acción Tutorial tiene como objetivo orientar al alumno a lo largo de toda la carrera universitaria, en especial en lo referente a la matriculación, para aumentar la eficiencia del alumno en los créditos superados frente a los matriculados. Como tercera acción, el Proyecto Mentor se complementa con las dos anteriores al proporcionar una orientación entre iguales, la cual tiene que acomodarse a las nuevas condiciones en las que se desarrollan los planes de estudio acordes al EEES

Laser stripe peak detector for 3D scanners: a FIR filter approach

The accuracy of a 3D reconstruction using laser scanners is significantly determined by the detection of the laser stripe. Since the energy pattern of such a stripe corresponds to a Gaussian profile, it makes sense to detect the point of maximum light intensity (or peak) by computing the zero-crossing point of the first derivative of such Gaussian profile. However, because noise is present in every physical process, such as electronic image formation, it is not sensitive to perform the derivative of the image of the stripe in almost any situation, unless a previous filtering stage is done. Considering that stripe scanning is an inherently row-parallel process, every row of a given image must be processed independently in order to compute its corresponding peak position in the row. This paper reports on the use of digital filtering techniques in order to cope with the scanning of different surfaces with different optical properties and different noise levels, leading to the proposal of a more accurate numerical peak detector, even at very low signal-to-noise ratios

Recovering Euclidean deformable models from stereo-motion

In this paper we present a novel structure from motion (SfM) approach able to infer 3D deformable models from uncalibrated stereo images. Using a stereo setup dramatically improves the 3D model estimation when the observed 3D shape is mostly deforming without undergoing strong rigid motion. Our approach first calibrates the stereo system automatically and then computes a single metric rigid structure for each frame. Afterwards, these 3D shapes are aligned to a reference view using a RANSAC method in order to compute the mean shape of the object and to select the subset of points on the object which have remained rigid throughout the sequence without deforming. The selected rigid points are then used to compute frame-wise shape registration and to extract the motion parameters robustly from frame to frame. Finally, all this information is used in a global optimization stage with bundle adjustment which allows to refine the frame-wise initial solution and also to recover the non-rigid 3D model. We show results on synthetic and real data that prove the performance of the proposed method even when there is no rigid motion in the original sequence

Surface registration from range image fusion

The registration of full 3-D models is an important task in computer vision. Range finders only reconstruct a partial view of the object. Many authors have proposed several techniques to register 3D surfaces from multiple views in which there are basically two aspects to consider. First, poor registration in which some sort of correspondences are established. Second, accurate registration in order to obtain a better solution. A survey of the most common techniques is presented and includes experimental results of some of them

Online Robust 3D Mapping Using Structure from Motion Cues

This paper presents a complete solution for creating accurate 3D textured models from monocular video sequences. The methods are developed within the framework of sequential structure from motion, where a 3D model of the environment is maintained and updated as new visual information becomes available. The camera position is recovered by directly associating the 3D scene model with local image observations. Compared to standard structure from motion techniques, this approach decreases the error accumulation while increasing the robustness to scene occlusions and feature association failures. The obtained 3D information is used to generate high quality, composite visual maps of the scene (mosaics). The visual maps are used to create texture-mapped, realistic views of the scene

Omnidirectional Depth Computation from a Single Image

Omnidirectional cameras offer a much wider field of view than the perspective ones and alleviate the problems due to occlusions. However, both types of cameras suffer from the lack of depth perception. A practical method for obtaining depth in computer vision is to project a known structured light pattern on the scene avoiding the problems and costs involved by stereo vision. This paper is focused on the idea of combining omnidirectional vision and structured light with the aim to provide 3D information about the scene. The resulting sensor is formed by a single catadioptric camera and an omnidirectional light projector. It is also discussed how this sensor can be used in robot navigation applications

Accuracy estimation of a new omnidirectional 3D vision sensor

We present a computer vision system that associates omnidirectional vision with structured light with the aim of obtaining depth information for a 360 degrees field of view. The approach proposed in this article combines an omnidirectional camera with a panoramic laser projector. The article shows how the sensor is modelled and its accuracy is proved by means of experimental results. The proposed sensor provides useful information for robot navigation applications, pipe inspection, 3D scene modelling etc

Calibration of a Structured Light-Based Stereo Catadioptric Sensor

Catadioptric sensors are combinations of mirrors and lenses made in order to obtain a wide field of view. In this paper we propose a new sensor that has omnidirectional viewing ability and it also provides depth information about the nearby surrounding. The sensor is based on a conventional camera coupled with a laser emitter and two hyperbolic mirrors. Mathematical formulation and precise specifications of the intrinsic and extrinsic parameters of the sensor are discussed. Our approach overcomes limitations of the existing omni-directional sensors and eventually leads to reduced costs of production

A new optimised De Bruijn coding strategy for structured light patterns

Coded structured light is an optical technique based on active stereovision that obtains the shape of objects. One shot techniques are based on projecting a unique light pattern with an LCD projector so that grabbing an image with a camera, a large number of correspondences can be obtained. Then, a 3D reconstruction of the illuminated object can be recovered by means of triangulation. The most used strategy to encode one-shot patterns is based on De Bruijn sequences. In This work a new way to design patterns using this type of sequences is presented. The new coding strategy minimises the number of required colours and maximises both the resolution and the accuracy

Overview of coded light projection techniques for automatic 3D profiling

Obtaining automatic 3D profile of objects is one of the most important issues in computer vision. With this information, a large number of applications become feasible: from visual inspection of industrial parts to 3D reconstruction of the environment for mobile robots. In order to achieve 3D data, range finders can be used. Coded structured light approach is one of the most widely used techniques to retrieve 3D information of an unknown surface. An overview of the existing techniques as well as a new classification of patterns for structured light sensors is presented. This kind of systems belong to the group of active triangulation method, which are based on projecting a light pattern and imaging the illuminated scene from one or more points of view. Since the patterns are coded, correspondences between points of the image(s) and points of the projected pattern can be easily found. Once correspondences are found, a classical triangulation strategy between camera(s) and projector device leads to the reconstruction of the surface. Advantages and constraints of the different patterns are discussed