Emiliano Pérez

Improved Method for Object Recognition in Complex Scenes by Fusioning 3-D Information and RFID Technology

This work analyzes a new method for object recognition in complex scenes combining vision-based techniques applied to the 3-D data obtained using range sensors and object identification coming from radio frequency tags (radio frequency identification (RFID) technology). Three-dimensional vision-based algorithms for object recognition have many restrictions in practical applications, i.e., uncertainty, incapability for real-time tasks, etc., but they work well for pose determination once the object is recognized. On the other hand, RFID technology allows us to detect the presence of specific objects in a scene, but it cannot provide their localization, at least not with the accuracy required in applications such as ours. In this paper, we present a new and powerful recognition method obtained by fusing both techniques. The phases of the method are described, and abundant experimentation results are included. An in-depth performance analysis has been carried out to demonstrate the recognition improvements achieved by the algorithm when RFID assistance is considered. It helps to confirm the robustness of this fusion approach and prove its effectiveness. A final discussion is included, concerning what should be the most adequate size of the object database for optimal algorithm exploitation.

Fusion of 3D Vision Techniques and RFID Technology for Object Recognition in Complex Scenes

This work presents a new method for object recognition in complex scenes combining vision-based techniques applied to the 3D data obtained using range sensors, and object identification coming from Radio Frequency tags (RFID technology). Vision based algorithms for 3D recognition have many restrictions in practical applications: uncertainty, incapability for real time tasks; but they work well for pose determination once the object is recognized. On the other hand, RFID technology allows detecting the presence of specific objects in a scene but it cannot provide their localization. In this paper, we show the powerful recognition tool obtained by fusioning both techniques. The phases of the proposed procedure are described and an in depth experimental demonstration is included. A performance analysis of the method is made by comparing the recognition algorithm with and without the RFID phase. Obtained results, concerning to success rate increasing and computational cost reduction, confirm the robustness of this fusion approach and prove its effectiveness.

A Robust Method for Filling Holes in 3D Meshes Based on Image Restoration

In this work a method for filling holes in 3D meshes based on a 2D image restoration algorithm is expounded. Since 3D data must be converted to a suitable input format, a 3D to 2D transformation is executed by projecting the 3D surface onto a grid. The storage of the depth information in every grid provides the 2D image which the restoration algorithms is applied in. Finally, an inverse transformation 2D to 3D is performed and the new produced data added to the damaged mesh. To test the method, artificial holes have been generated on a set of 3D surfaces. The distances between 3D original surfaces (before damaging it) and 3D repaired ones have been measured and a comparison with a commercial software has been established. Furthermore, the relation between holes areas and success rates has been also studied. This method has been applied to the sculptures of the collection from the National Museum of Roman Art in Spain with good results.

Reconocimiento de Objetos de Forma Libre a Partir de los Datos de Rango de una Vista Parcial Usando Cono Curvaturas Ponderadas

Este trabajo se ha desarrollado gracias a la financiacion del Ministerio de Educacion y Ciencia, a traves de los proyectos de la CICYT DPI2005-03769 y DPI2006-14794-C02.

A comparison of hole-filling methods in 3D

Abstract This paper presents a review of the most relevant current techniques that deal with hole-filling in 3D models. Contrary to earlier reports, which approach mesh repairing in a sparse and global manner, the objective of this review is twofold. First, a specific and comprehensive review of hole-filling techniques (as a relevant part in the field of mesh repairing) is carried out. We present a brief summary of each technique with attention paid to its algorithmic essence, main contributions and limitations. Second, a solid comparison between 34 methods is established. To do this, we define 19 possible meaningful features and properties that can be found in a generic hole-filling process. Then, we use these features to assess the virtues and deficiencies of the method and to build comparative tables. The purpose of this review is to make a comparative hole-filling state-of-the-art available to researchers, showing pros and cons in a common framework.

Touring the Forum Adiectum of Augusta Emerita in a virtual reality experience

The current advances of Information and Communication Technologies (ICTs) have created new spaces for the recreational participation, mainly on virtual spaces, which can be considered as one of the main drivers of the cultural and creative production. This paper describes the experience in developing and testing an interactive 3D virtual environment for the Aeneas group in the Forum Adiectum. 3D models obtained from different sources can be included in this virtual world after a proper adaptation. We aim to demonstrate that this way of showing Cultural Heritage can motivate and facilitate people’s learning o our past rather than traditional media.

A framework for the analysis of parabolic trough collectors using 3D data from laser scanners

This paper presents an original method for the analysis of geometrical and physical properties of parabolic solar trough collectors that belong to operating solar thermal power plants. The method is applied in operating plants, which is a novelty with respect to the majority of the methods proposed so far, used only in the mirrors design phase. Laser scanners have turned out to be an ideal tool for acquiring the surface of parabolic mirrors on field. The aim of our proposal is the comparison of the sensed 3D data with a theoretical parabolic surface. All the phases needed for the achievement of this objective constitute a general framework that has been detailed throughout this paper. The proposed framework has been applied to the analysis of real surfaces of parabolic solar trough collectors acquired in an operating solar thermal plant. The results obtained demonstrate its validity and robustness.

Fractional disturbance observer for vibration suppression of a beam-cart system

In this paper, vibration suppression of a flexible beam on a moving cart is investigated based on fractional order disturbance observers (FODOB). Linear models to describe the position of the beam-cart system and the single-mode vibration of the beam are firstly derived. Likewise, a fractional order model is also identified for such a vibration, which is considered as a disturbance of the cart. The proposed control strategy consists of a proportional-derivative (PD) controller with noise filter to control the position of the cart, and a FDOB to compensate the coupling torque between the flexible beam and the cart. Simulation results are given to show the effectiveness of the proposed strategy to attenuate the vibration of the beam.

Heritage pieces integration in autonomous augmented reality systems: key problems and solutions

Nowadays virtual reality users and professionals demand a growing quality and a higher degree of realism in development and applications. Among these technologies augmented reality systems stand out due to their complexity and possibilities, having open current problems from the digitalization process to the accurate insertion of digital information in the reality. This paper is addressed to present solutions to key problems that arise in these environments which the 3D Computer Vision and Robotics (UCLM) group has been working on over the last two years. The final objective is to extend and complete the real visual information perceived by the user superimposing three-dimensional information synthesized with a high degree of realism. Our research is focused on two aspects that converge towards the same objective. The first objective is to carry out a reverse engineering process on valuable heritage pieces with the aim of obtaining complete and realistic models. This is a field where current technology itself is not capable of yielding a complete and satisfactory answer. Here we present solutions to two of the most important issues which many researchers continue working on: automatic filling holes in 3D meshes and color integration in the geometrical model through view fusion techniques. The second objective concerns the problem of the insertion of virtual models in the image captured by one or more cameras. Current display as well as positioning devices solves most of the AR problems in controlled environments. Nevertheless, a more interesting matter, on which notable research efforts are being carried out, are focused on the positioning aspects in external and non controlled environments. In this paper, we describe an efficient solution with low computational cost that allows us to carry out autonomous augmented reality sessions in free environments.