Enviaments recents

  • BASS: boundary-aware superpixel segmentation 

    Rubio Romano, Antonio; Yu, Longlong; Simó Serra, Edgar; Moreno-Noguer, Francesc (IEEE Press, 2016)
    Text en actes de congrés
    Accés obert
    We propose a new superpixel algorithm based on exploiting the boundary information of an image, as objects in images can generally be described by their boundaries. Our proposed approach initially estimates the boundaries ...
  • Semantic segmentation priors for object discovery 

    Martín García, Germán; Husain, Syed Farzad; Schulz, Hannes; Frintrop, Simone; Torras, Carme; Behnke, Sven (IEEE Press, 2016)
    Text en actes de congrés
    Accés obert
    Reliable object discovery in realistic indoor scenes is a necessity for many computer vision and service robot applications. In these scenes, semantic segmentation methods have made huge advances in recent years. Such ...
  • Recovering pose and 3D deformable shape from multi-instance image ensembles 

    Agudo Martínez, Antonio; Moreno-Noguer, Francesc (Springer, 2017)
    Text en actes de congrés
    Accés obert
    In recent years, there has been a growing interest on tackling the Non-Rigid Structure from Motion problem (NRSfM), where the shape of a deformable object and the pose of a moving camera are simultaneously estimated from ...
  • Structured prediction with output embeddings for semantic image annotation 

    Quattoni, Ariadna Julieta; Ramisa Ayats, Arnau; Madhyastha, Pranava S.; Simo Serra, Edgar; Moreno-Noguer, Francesc (2016)
    Text en actes de congrés
    Accés obert
    We address the task of annotating images with semantic tuples. Solving this problem requires an algorithm able to deal with hundreds of classes for each argument of the tuple. In such contexts, data sparsity becomes a key ...
  • Personalization framework for adaptive robotic feeding assistance 

    Canal Camprodon, Gerard; Alenyà Ribas, Guillem; Torras, Carme (2016)
    Text en actes de congrés
    Accés obert
    The deployment of robots at home must involve robots with pre-defined skills and the capability of personalizing their behavior by non-expert users. A framework to tackle this personalization is presented and applied to ...
  • User evaluation of an interactive learning framework for single-arm and dual-arm robots 

    Jevtic, Aleksandar; Colomé Figueras, Adrià; Alenyà Ribas, Guillem; Torras, Carme (Springer, 2016)
    Text en actes de congrés
    Accés obert
    Social robots are expected to adapt to their users and, like their human counterparts, learn from the interaction. In our previous work, we proposed an interactive learning framework that enables a user to intervene and ...
  • Robot-aided cloth classification using depth information and CNNs 

    Gabas Nova, Antonio; Corona Puyane, Enric; Alenyà Ribas, Guillem; Torras, Carme (2016)
    Text en actes de congrés
    Accés obert
    We present a system to deal with the problem of classifying garments from a pile of clothes. This system uses a robot arm to extract a garment and show it to a depth camera. Using only depth images of a partial view of the ...
  • Tracking of microtubules in anisotropic volumes of neural tissue 

    Buhmann, JULIA M.; Gerhard, Stephan; Cook, Matthew; Funke, Jan (2016)
    Text en actes de congrés
    Accés restringit per política de l'editorial
    For both the automatic and manual reconstruction of neural circuits from electron microscopy (EM) images, the detection and identification of intracellular structures provide useful cues. This is particularly true for ...
  • Confluència de ciència i ficció en la robòtica actual 

    Torras, Carme (Edicions Talaiots, 2015)
    Comunicació de congrés
    Accés obert
    Els robots industrials i els hominoides de la ciència-ficció, tan diferents fins ara, comencen a confluir gràcies al ràpid desenvolupament de la robòtica assistencial i de serveis. S’estan dissenyant robots que puguin ...
  • Accurate and linear time pose estimation from points and lines 

    Vakhitov, A.; Funke, Jan; Moreno-Noguer, Francesc (2016)
    Text en actes de congrés
    Accés obert
    The Perspective-n-Point (PnP) problem seeks to estimate the pose of a calibrated camera from n 3Dto-2D point correspondences. There are situations, though, where PnP solutions are prone to fail because feature point ...

Mostra'n més