Ara es mostren els items 1-20 de 151

  • 2D Grammar Extension of the CMP Mathematical Formulae On-line Recognition System 

    Gallardo Pérez, Eva (Universitat Politècnica de Catalunya, 2009-01-21)
    Projecte/Treball Final de Carrera
    Accés obert
    In the last years, the recognition of handwritten mathematical formulae has recieved an increasing amount of attention in pattern recognition research. However, the diversity of approaches to the problem and the lack of ...
  • 3D human action recognition in multiple view scenarios 

    Canton Ferrer, Cristian; Casas Pla, Josep Ramon; Pardàs Feliu, Montse; Sargin, M E; Tekalp, A M (Universitat Politècnica de Catalunya (UPC), 2006)
    Text en actes de congrés
    Accés obert
    This paper presents a novel view-independent approach to the recognition of human gestures of several people in low resolution sequences from multiple calibrated cameras. In contraposition with other multi-ocular ...
  • 3D modelling of leaves from color and ToF data for robotized plant measuring 

    Alenyà Ribas, Guillem; Dellen, Babette; Torras, Carme (2011)
    Text en actes de congrés
    Accés restringit per política de l'editorial
    Supervision of long-lasting extensive botanic experiments is a promising robotic application that some recent technological advances have made feasible. Plant modelling for this application has strong demands, particularly ...
  • 3D reconstruction and recognition of objects using a kinect camera 

    Luján Rossell, Alba (Universitat Politècnica de Catalunya, 2016-09)
    Treball Final de Grau
    Accés obert
    Realitzat a/amb:  Technische Universität München
    This project is based on the recent advances of 3D depth cameras, one being the Microsoft Kinect sensors. Nowadays, this technology enables to create really accurate 3D figures and scenes simplifying difficult tasks in ...
  • 3d semantic representation of actions from effcient stereo-image-sequence segmentation on GPUs 

    Alexey, Abramov; Aksoy, Eren Erdal; Dörr, Johannes; Wörgötter, Florentin; Pauwels, Karl; Dellen, Babette (2010)
    Text en actes de congrés
    Accés obert
    A novel real-time framework for model-free stereo-video segmentation and stereo-segment tracking is presented, combining real-time optical flow and stereo with image segmentation running separately on two GPUs. The ...
  • Accurate human body tracking from multiple RGBZ sensors 

    Carruesco Llorens, Álex (Universitat Politècnica de Catalunya, 2014-06-26)
    Treball Final de Grau
    Accés obert
    [CATALÀ] En aquest projecte s'ha desenvolupat un software que permet calibrar càmeres Kinect i reconèixer gestos amb múltiples Kinect a partir de la informació de profunditat. El software s'ha dissenyat per a que pugui ...
  • A comparison between two representatives of a set of graphs: median vs barycenter graph 

    Bardaji Goikoetxea, Itziar; Ferrer Sumsi, Miquel; Sanfeliu Cortés, Alberto (Springer Verlag, 2010)
    Text en actes de congrés
    Accés obert
    In this paper we consider two existing methods to generate a representative of a given set of graphs, that satisfy the following two conditions. On the one hand, that they are applicable to graphs with any kind of labels ...
  • Active Appearance Models for People Recognition with a RGB-D Sensor 

    Trejo Ramírez, Karla Andrea (Universitat Politècnica de Catalunya, 2014-06)
    Projecte Final de Màster Oficial
    Accés restringit per decisió de l'autor
    Active Appearance Models (AAMs) is a computer vision procedure for statistical matching of object shape and appearance between images. The present work will analyze how AAMs can be employed with RGB-Depth technology, so ...
  • A deep analysis on age estimation 

    Huerta Casado, Iván; Fernandez Tena, Carles; Segura, Carlos; Hernando Pericás, Francisco Javier; Prati, Andrea (2015-12-15)
    Article
    Accés obert
    The automatic estimation of age from face images is increasingly gaining attention, as it facilitates applications including advanced video surveillance, demographic statistics collection, customer profiling, or search ...
  • A generic framework for median graph computation based on a recursive embedding approach 

    Ferrer Sumsi, Miquel; Karatzas, D; Valveny, Ernest; Bardaji Goikoetxea, Itziar; Bunke, Horst (2011)
    Article
    Accés obert
    The median graph has been shown to be a good choice to obtain a representative of a set of graphs. However, its computation is a complex problem. Recently, graph embedding into vector spaces has been proposed to obtain ...
  • A local algorithm for the computation of image velocity via constructive interference of global Fourier components 

    Dellen, Babette; Wörgötter, Florentin (2011)
    Article
    Accés obert
    A novel Fourier-based technique for local motion detection from image sequences is proposed. In this method, the instantaneous velocities of local image points are inferred directly from the global 3D Fourier components ...
  • A new algorithm to compute the distance between multi-dimensional histograms 

    Serratosa Casanelles, Francesc; Sanromà Güell, Gerard; Sanfeliu Cortés, Alberto (Springer Verlag, 2007)
    Capítol de llibre
    Accés obert
    The aim of this paper is to present a new algorithm to compute the distance between ndimensional histograms. There are some domains such as pattern recognition or image retrieval that use the distance between histograms ...
  • A new graph matching method for point-set correspondence using the EM algorithm and Softassign 

    Sanromà Güell, Gerard; Alquézar Mancho, René; Serratosa Casanelles, Francesc (2012)
    Article
    Accés restringit per política de l'editorial
    Finding correspondences between two point-sets is a common step in many vision applications (e.g., image matching or shape retrieval). We present a graph matching method to solve the point-set correspondence problem, which ...
  • A new relational geometric feature for human action recognition 

    Vinagre Ruiz, Manuel; Aranda López, Juan; Casals Gelpi, Alicia (Springer, 2015-01)
    Article
    Accés restringit per política de l'editorial
    Pose-based features have demonstrated to outperform low-levelappearance features in human action recognition. New RGB-D cameras provide locations of human joints with which geometric correspondences can be easily calculated. ...
  • Application of graph embedding to solve graph matching problems 

    Valveny, Ernest; Ferrer Sumsi, Miquel (2008)
    Text en actes de congrés
    Accés restringit per política de l'editorial
    Graphs have very interesting properties for object representation in pattern recognition. However, graph matching algorithms are usually computationally complex. In addition, graphs are harder to manipulate and operate ...
  • Approximate nearest neighbour search with the fukunaga & narendra algorithm 

    Si, Peng (Universitat Politècnica de Catalunya, 2011-09-05)
    Projecte Final de Màster Oficial
    Accés obert
    English: Nearest neighbour search is the one of the most simple and used technique in Pattern Recognition due to its simplicity and its good behaviour.. Many fast NN search algorithm have been developed during last years. ...
  • Aprenentatge de la llengua de signes catalana amb Kinect 

    Górriz, Marc (Universitat Politècnica de Catalunya, 2012)
    Projecte/Treball Final de Carrera
    Accés obert
    S’ha desenvolupat una aplicació per a facilitar l’aprenentatge de l’abecedari de la Llengua de signes catalana mitjançant una sèrie d’activitats de lletrejar paraules. El projecte fa ús del dispositiu Kinect per tal de ...
  • A recursive embedding approach to median graph computation 

    Ferrer Sumsi, Miquel; Valveny, Ernest; Bunke, Horst (Springer Verlag, 2009-06-12)
    Capítol de llibre
    Accés obert
    The median graph has been shown to be a good choice to infer a representative of a set of graphs. It has been successfully applied to graph-based classification and clustering. Nevertheless, its computation is extremely ...
  • Arm and hand gesture recognition through online learning 

    Pluma Duran, Oscar (Universitat Politècnica de Catalunya, 2014-06)
    Treball Final de Grau
    Accés obert
    [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 survey on model based approaches for 2D and 3D visual human pose recovery 

    Perez Sala, Xavier; Escalera, Sergio; Angulo Bahón, Cecilio; Gonzàlez, Jordi (2014-03-03)
    Article
    Accés obert
    Human Pose Recovery has been studied in the field of Computer Vision for the last 40 years. Several approaches have been reported, and significant improvements have been obtained in both data representation and model design. ...