Now showing items 1-20 of 27

  • 3D hierarchical optimization for multi-view depth map coding 

    Maceira, Marc; Varas, David; Morros Rubió, Josep Ramon; Ruiz Hidalgo, Javier; Marqués Acosta, Fernando (2017-11-28)
    Article
    Open Access
    Depth data has a widespread use since the popularity of high resolution 3D sensors. In multi-view sequences, depth information is used to supplement the color data of each view. This article proposes a joint encoding of ...
  • Assessment of crowdsourcing and gamification loss in user-assisted object segmentation 

    Carlier, Axel; Salvador Aguilera, Amaia; Cabezas, Ferran; Giró Nieto, Xavier; Charvillat, Vincent; Marques, Oge (2015-09-12)
    Article
    Open Access
    There has been a growing interest in applying human computation – particularly crowdsourcing techniques – to assist in the solution of multimedia, image processing, and computer vision problems which are still too difficult ...
  • Binary partition tree as a polarimetric SAR data representation in the space-time domain 

    Alonso González, Alberto; López Martínez, Carlos; Salembier Clairon, Philippe Jean (IEEE, 2011)
    Conference lecture
    Restricted access - publisher's policy
    The aim of this paper is to present a Polarimetric Synthetic Aperture Radar data processing technique on the space-time domain. This approach is based on a Binary Partition Tree (BPT), which is a region-based and multi-scale ...
  • Cage active contours: Extension to color spaces and application to image morphing 

    Carandell Saladich, Jeroni (Universitat Politècnica de Catalunya, 2015-10-23)
    Master thesis
    Open Access
    The main purpose of this master thesis is to enhance the performance of Cage Active Contours (CAC) in the context of color image object segmentation as well as provide a theoretical framework on which to justify the potential ...
  • Co-filtering human interaction and object segmentation 

    Cabezas Castellvi, Ferran Albert (Universitat Politècnica de Catalunya, 2015-02-17)
    Bachelor thesis
    Open Access
    Covenantee:  Institut national polytechnique de Toulouse
    [ANGLÈS] For so many years the problem of object segmentation have been present in image processing field. Click'n'Cut, an already existing web tool for interactive object segmentation, helps us to obtain segmentations of ...
  • Cost-effective active learning for melanoma segmentation 

    Górriz, Marc; Giró Nieto, Xavier; Carlier, Axel; Faure, Emmanuel (2017)
    Conference lecture
    Open Access
    We propose a novel Active Learning framework capable to train effectively a convolutional neural network for semantic segmentation of medical imaging, with a limited amount of training labeled data. Our contribution is a ...
  • Detection-aided liver lesion segmentation using deep learning 

    Bellver, Míriam; Maninis, Kevis-Kokitsi; Pont Tuset, Jordi; Giró Nieto, Xavier; Torres Viñals, Jordi; Van Gool, Luc (2017)
    Conference lecture
    Open Access
    A fully automatic technique for segmenting the liver and localizing its unhealthy tissues is a convenient tool in order to diagnose hepatic diseases and assess the response to the according treatments. In this work we ...
  • Disparity Estimation using a Color Segmentation 

    Wang, Xin (Universitat Politècnica de Catalunya, 2009-09)
    Master thesis
    Open Access
    This thesis work is mainly motivated to solve the stereo correspondence problem. As solving the correspondence problem could result a precise disparity map allowing the interpolation of intermediate views in 3DTV, the ...
  • Distributed partitioning algorithm with application to video-surveillance 

    Paloma Garcia, Inés; Saiz, Carlos (Universitat Politècnica de Catalunya / Università degli Studi di Padova, 2014)
    Bachelor thesis
    Open Access
    How many times have we wanted to control an area and the video-surveillance system does not have the appropriate properties? Nowadays, the video-surveillance has become a responsibility by the necessity to patrol a ...
  • Head pose estimation from 2D/3D images 

    Guàrdia Santesmases, Robert (Universitat Politècnica de Catalunya / Université de Liège, 2014)
    Master thesis (pre-Bologna period)
    Open Access
    The purpose of the current work is to develop, test and compare different methods for the detection of the angles of the head. To achieve good head estimation this project has been divided in two stages. In the first ...
  • Hierarchical object detection with deep reinforcement learning 

    Bellver, Míriam; Giró Nieto, Xavier; Marqués Acosta, Fernando; Torres, Jordi (2016)
    Conference lecture
    Open Access
    We present a method for performing hierarchical object detection in images guided by a deep reinforcement learning agent. The key idea is to focus on those parts of the image that contain richer information and zoom on ...
  • Hierarchical stack filtering: a bitplane-based algorithm for massively parallel processors 

    Frías Velazquez, Andres; Morros Rubió, Josep Ramon; García Molina, Mario; Philips, Wilfried (2017-03-15)
    Article
    Open Access
    With the development of novel parallel architectures for image processing, the implementation of well-known image operators needs to be reformulated to take advantage of the so-called massive parallelism. In this work, we ...
  • Image Segmentation using Dictionary Learning 

    Sarasúa Cañedo-Arguelles, Ignacio (Universitat Politècnica de Catalunya, 2014-12-22)
    Master thesis (pre-Bologna period)
    Open Access
    Covenantee:  Technische Universität München
    [ANGLÈS] In image segmentation, we are often interested in capturing certain characteristics of objects of interests, and perform the classification based on criteria such as mean intensity, gradient magnitude, and responses ...
  • Implementació i millores de l'algorisme de Texture Bombing 

    Élez-Villarroel Garcia, Miguel Ángel (Universitat Politècnica de Catalunya, 2016-04-26)
    Bachelor thesis
    Open Access
    Texture bombing és una tècnica molt bona però com tantes altres també té les seves debilitats, tals com la falta de diversitat o la falta de mipmapping. En aquest projecte s'implementa la solució al primer problema, la ...
  • Improving object segmentation by using EEG signals and rapid serial visual presentation 

    Mohedano, Eva; Healy, Graham; McGuinness, Kevin; Giró Nieto, Xavier; O'Connor, Noel; Smeaton, Alan F. (2015-07-31)
    Article
    Open Access
    This paper extends our previous work on the potential of EEG-based brain computer interfaces to segment salient objects in images. The proposed system analyzes the Event Related Potentials (ERP) generated by the rapid ...
  • Is a “happy dog” more “happy” than “dog”? - Adjective and Noun Contributions for Adjective-Noun Pair prediction 

    Fernàndez, Dèlia; Campos Camúñez, Victor; Jou, Brendan; Giró Nieto, Xavier; Chang, Shih-Fu (2016)
    Conference lecture
    Open Access
  • Leishmaniasis parasite segmentation and classification using deep learning 

    Górriz, Marc; Aparicio, Albert; Raventós, Berta; Vilaplana Besler, Verónica; Sayrol Clols, Elisa; López Codina, Daniel (Springer, 2018)
    Conference lecture
    Restricted access - publisher's policy
    Leishmaniasis is considered a neglected disease that causes thousands of deaths annually in some tropical and subtropical countries. There are various techniques to diagnose leishmaniasis of which manual microscopy is ...
  • Multiresolution co-clustering for uncalibrated multiview segmentation 

    Ventura, Carles; Varas, David; Vilaplana Besler, Verónica; Giró Nieto, Xavier; Marqués Acosta, Fernando (2019-05-04)
    Article
    Restricted access - publisher's policy
    We propose a technique for coherently co-clustering uncalibrated views of a scene with a contour-based representation. Our work extends the previous framework, an iterative algorithm for segmenting sequences with small ...
  • On-line human activity recognition by monitoring the interaction with the objects in a known environment 

    Ajenjo Escolano, Enrique Javier (Universitat Politècnica de Catalunya, 2016-01)
    Master thesis
    Open Access
    Until now, the robots environment was characterized for being parametrized. This means, that all tasks must be defined and the robot only needs to repeat the programed action continually. Furthermore, the robot and the ...
  • Research of robot trajectory control by optical method 

    Pérez Sanmartín, Alejandro (Universitat Politècnica de Catalunya / Vilnius Gediminas Technical University, 2017-07)
    Master thesis
    Open Access
    The thesis is part of a larger ongoing research project of the Department of Mechatronics and Robotics of VGTU. The goal of that project is to develop software for KUKA YouBot and contribute to the study of advanced ...