• Arm and hand gesture recognition through online learning 

    Pluma Duran, Oscar (Universitat Politècnica de Catalunya, 2014-06)
    Trabajo final de grado
    Acceso abierto
    Realizado en/con:  Institut national des sciences appliquées de Lyon
    [ANGLÈS] The aim of this project is to develop a system capable to move a robot by recognizing the gestures performed by a user. The system has been already implemented by the LIRIS laboratory, and the objective has been ...
  • A sensor data fusion system based on k-nearest neighbor pattern classification for structural health monitoring applications 

    Vitola Oyaga, Jaime; Pozo Montero, Francesc; Tibaduiza Burgos, Diego Alexander; Anaya Vejar, Maribel (2017-02-21)
    Artículo
    Acceso abierto
    Civil and military structures are susceptible and vulnerable to damage due to the environmental and operational conditions. Therefore, the implementation of technology to provide robust solutions in damage identification ...
  • A two-step approach for estimating pedestrian demand in a congested network 

    Rojas Lombarte, Eduard (Universitat Politècnica de Catalunya, 2014-07-25)
    Trabajo final de grado
    Acceso abierto
    Realizado en/con:  École polytechnique fédérale de Lausanne
    [ANGLÈS] In the framework of PedFlux, a long-term research project jointly carried out by the Swiss Federal Railways (SBB) and EPFL, pedestrian ow patterns arising in complex train stations are investigated. For this ...
  • Automatic extraction of semantic metadata from optical biopsy images 

    Ballester Ripoll, Rafael (Universitat Politècnica de Catalunya, 2012-01-20)
    Proyecto/Trabajo final de carrera
    Acceso restringido por acuerdo de confidencialidad
  • Bag of Delay-Vectors for human action recognition 

    Andreu Villagrasa, Aitor David (Universitat Politècnica de Catalunya, 2012-10)
    Proyecto/Trabajo final de carrera
    Acceso abierto
    [ANGLÈS] The main objective of this project is to present a functional framework to recognize human actions. We use time-series to describe the human actions and we apply the Time-Delay Embeddings method to reconstruct the ...
  • BoVDW: Bag-of-Visual-and-Depth-Words for gesture recognition 

    Hernandez Vela, Antonio; Bautista, Miguel Angel; Perez-Sala, Xavier; Ponce, Víctor; Baró, Xavier; Pujol, Oriol; Angulo Bahón, Cecilio; Escalera, Sergio (2012)
    Texto en actas de congreso
    Acceso restringido por política de la editorial
    We present a Bag-of-Visual-and-Depth-Words (BoVDW) model for gesture recognition, an extension of the Bag-of-Visual-Words (BoVW) model, that benefits from the multimodal fusion of visual and depth features. State-of-the-art ...
  • Captura de moviments a partir d'un núvol de punts RGBD 

    Jubert Hermoso, Miquel (Universitat Politècnica de Catalunya, 2017-06-19)
    Trabajo final de grado
    Acceso abierto
    Aquest treball de fi de grau ha estat orientat com un projecte d’investigació. Per tant, l’interès no es troba únicament en el resultat final, part de la gràcia es troba en el procés de presa de decisions. L’estructura ...
  • Categorizing object-actions relations from semantic scene graphs 

    Aksoy, Eren Erdal; Abramov, Alexey; Wörgötter, Florentin; Dellen, Babette (2010)
    Texto en actas de congreso
    Acceso restringido por política de la editorial
    In this work we introduce a novel approach for detecting spatiotemporal object-action relations, leading to both, action recognition and object categorization. Semantic scene graphs are extracted from image sequences and ...
  • Characterization of textile grasping experiments 

    Alenyà Ribas, Guillem; Ramisa Ayats, Arnau; Moreno-Noguer, Francesc; Torras, Carme (2012)
    Texto en actas de congreso
    Acceso abierto
    Grasping highly deformable objects, like textiles, is an emerging area of research that involves both percep- tion and manipulation abilities. As new techniques appear, it becomes essential to design strategies to compare ...
  • Click'n'Cut: crowdsourced interactive segmentation with object candidates 

    Carlier, Axel; Charvillat, Vincent; Salvador Aguilera, Amaia; Giró Nieto, Xavier; Marques, Ogé (ACM, 2014)
    Comunicación de congreso
    Acceso abierto
    This paper introduces Click’n’Cut, a novel web tool for inter- active object segmentation designed for crowdsourcing tasks. Click’n’Cut combines bounding boxes and clicks generated by workers to obtain accurate object ...
  • Combining depth with appearance images for object detection using online learning 

    Vaquero Gómez, Víctor (Universitat Politècnica de Catalunya, 2014-06)
    Projecte Final de Màster Oficial
    Acceso restringido por decisión del autor
    This Master's Thesis presents a new developed algorithm that merges Appearance and Depth Images in order to perform the detection of objects in scenes. This new algorithm uses the approach of the Online Learning Random ...
  • Compact form of the pseudo-inverse matrix in the approximation of a star graph using the conductance electrical model (CEM) 

    Igelmo Ganzo, Manuel; Sanfeliu Cortés, Alberto (2012)
    Texto en actas de congreso
    Acceso restringido por política de la editorial
    The Conductance Electrical Model (CEM) translate a graph into a circuit. After applying the model, in many cases, it is necessary to approximate the circuit obtained by a star circuit and this requires the calculation ...
  • Comparative analysis for detecting objects under cast shadows in video images 

    Scandaliaris, Jorge; Villamizar Vergel, Michael Alejandro; Sanfeliu Cortés, Alberto (2010)
    Texto en actas de congreso
    Acceso abierto
  • Comparison of methods for the number recognition of sport players 

    Àlvarez Criach, Gerard (Universitat Politècnica de Catalunya, 2010-09-08)
    Proyecto/Trabajo final de carrera
    Acceso abierto
    Realizado en/con:  Université Catholique de Louvain
    In a system of detection and recognition of players on a sport- el, the process of identifying numbers from a binary image is the last step. The identi cation is possible using the numbers of players jerseys that are ...
  • Complementing kernel-based visualization of protein sequences with their phylogenetic tree 

    Cárdenas, Martha Ivón; Vellido Alcacena, Alfredo; Olier, Iván; Rovira, Xavier; Giraldo, Jesús (Springer, 2012)
    Capítulo de libro
    Acceso restringido por política de la editorial
  • Computing the barycenter graph by means of the graph edit distance 

    Bardaji Goikoetxea, Itziar; Ferrer Sumsi, Miquel; Sanfeliu Cortés, Alberto (2010)
    Texto en actas de congreso
    Acceso abierto
    The barycenter graph has been shown as an alternative to obtain the representative of a given set of graphs. In this paper we propose an extension of the original algorithm which makes use of the graph edit distance in ...
  • Constrained random sampling and gap filling technique for near-regular texture synthesis 

    López Recas, Diego (Universitat Politècnica de Catalunya / Technische Universität Berlin. Fakultät Elektrotechnik und Informatik, 2011-07-28)
    Proyecto/Trabajo final de carrera
    Acceso abierto
    Realizado en/con:  Technische Universität Berlin
    This thesis addresses the synthesis of near-regular textures, i.e. textures that consist of a regular global structure plus subtle yet very characteristic stochastic irregularities, from a small exemplar image. Such textures ...
  • Damage localization using pattern recognition techniques and statistical dissimilarity analysis 

    Rodríguez Lozada, Harold S.; Tibaduiza Burgos, Diego Alexander; Pozo Montero, Francesc; León Medina, Jersson Xavier (Destech, 2019)
    Texto en actas de congreso
    Acceso abierto
    The increasing expansion of standards and regulations aimed to guarantee the safe operation of different types of structures and materials ---which are extensively used in buildings, airplanes, transformers, machinery, ...
  • Deep Learning For Sequential Pattern Recognition 

    Safari, Pooyan (Universitat Politècnica de Catalunya / Technische Universität München, 2013-12-18)
    Projecte Final de Màster Oficial
    Acceso abierto
    Realizado en/con:  Technische Universität München
    In recent years, deep learning has opened a new research line in pattern recognition tasks. It has been hypothesized that this kind of learning would capture more abstract patterns concealed in data. It is motivated by the ...
  • Deep learning superresolution 

    Mazagatos Pérez, Santiago (Universitat Politècnica de Catalunya, 2019-04-24)
    Projecte Final de Màster Oficial
    Acceso abierto
    [...] In this work the author makes use of state-of-the-art Super-Resolution methods and denoising methods to try and create a comprehensive solution for all use cases related to digital art restoration.