Ara es mostren els items 1-20 de 59

    • 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 point cloud segmentation using a fully connected conditional random field 

      Lin, Xiao; Casas Pla, Josep Ramon; Pardàs Feliu, Montse (Institute of Electrical and Electronics Engineers (IEEE), 2017)
      Comunicació de congrés
      Accés restringit per política de l'editorial
      Traditional image segmentation methods working with low level image features are usually difficult to adapt to higher level tasks, such as object recognition and scene understanding. Object segmentation emerges as a new ...
    • 3D point cloud video segmentation based on interaction analysis 

      Lin, Xiao; Casas Pla, Josep Ramon; Pardàs Feliu, Montse (Springer, 2016-11-24)
      Capítol de llibre
      Accés obert
      Given the widespread availability of point cloud data from consumer depth sensors, 3D segmentation becomes a promising building block for high level applications such as scene understanding and interaction analysis. It ...
    • 3D point cloud video segmentation based on interaction analysis 

      Lin, Xiao; Casas Pla, Josep Ramon; Pardàs Feliu, Montse (Springer, 2016)
      Comunicació de congrés
      Accés obert
      Given the widespread availability of point cloud data from consumer depth sensors, 3D segmentation becomes a promising building block for high level applications such as scene understanding and interaction analysis. It ...
    • 3D point cloud video segmentation oriented to the analysis of interactions 

      Lin, Xiao; Casas Pla, Josep Ramon; Pardàs Feliu, Montse (Institute of Electrical and Electronics Engineers (IEEE), 2016)
      Comunicació de congrés
      Accés obert
      Given the widespread availability of point cloud data from consumer depth sensors, 3D point cloud segmentation becomes a promising building block for high level applications such as scene understanding and interaction ...
    • 3D shape from multi-camera views by error projection minimization 

      Haro, Gloria; Pardàs Feliu, Montse (2010)
      Text en actes de congrés
      Accés obert
      Traditional shape from silhouette methods compute the 3D shape as the intersection of the back-projected silhouettes in the 3D space, the so called visual hull. However, silhouettes that have been obtained with background ...
    • A new approach to active contours for tracking 

      Pardàs Feliu, Montse; Sayrol Clols, Elisa (Institute of Electrical and Electronics Engineers (IEEE), 2000)
      Text en actes de congrés
      Accés obert
      This paper addresses the application of active contours or snakes for robust tracking of contours. Conventional snake approaches to tracking initialize the current frame snake with the snake obtained in the previous frame ...
    • A real-time body tracking system for smart rooms 

      Alcoverro Vidal, Marcel; López Méndez, Adolfo; Casas Pla, Josep Ramon; Pardàs Feliu, Montse (2011)
      Text en actes de congrés
      Accés restringit per política de l'editorial
      We present a real-time human body tracking system for a single user in a Smart Room scenario. In this paper we propose a novel system that involves a silhouette-based cost function using variable windows, a hierarchical ...
    • A segmentation-based coding system allowing manipulation of objects (sesame) 

      Marqués Acosta, Fernando; Salembier Clairon, Philippe Jean; Pardàs Feliu, Montse; Marcotegui Iturmendi, Beatriz (IEEE, 1996)
      Text en actes de congrés
      Accés obert
      We present a coding scheme that achieves, for each image in the sequence, the best segmentation in terms of rate-distortion theory. It is obtained from a set of initial regions and a set of available coding techniques. The ...
    • Active mesh coding and rate-distortion theory 

      Salembier Clairon, Philippe Jean; Martí Navarro, Eva; Pardàs Feliu, Montse (Institute of Electrical and Electronics Engineers (IEEE), 1996)
      Comunicació de congrés
      Accés obert
      This paper presents a video coding scheme for very low bit rate applications. The coding approach relies on active meshes and can be viewed as a particular case of region-based coding. The active mesh is used to efficiently ...
    • Approximate partitioning of observations in hierarchical particle filter body tracking 

      López Méndez, Adolfo; Alcoverro Vidal, Marcel; Pardàs Feliu, Montse; Casas Pla, Josep Ramon (2011)
      Text en actes de congrés
      Accés restringit per política de l'editorial
      This paper presents a model-based hierarchical particle filtering algorithm to estimate the pose and anthropometric parameters of humans in multi-view environments. Our method incorporates a novel likelihood measurement ...
    • Audiovisual head orientation estimation with particle filtering in multisensor scenarios 

      Canton Ferrer, Cristian; Segura Perales, Carlos; Casas Pla, Josep Ramon; Pardàs Feliu, Montse; Hernando Pericás, Francisco Javier (2008-01)
      Article
      Accés obert
      This article presents a multimodal approach to head pose estimation of individuals in environments equipped with multiple cameras and microphones, such as SmartRooms or automatic video conferencing. Determining the individuals ...
    • Bayesian foreground segmentation and tracking using pixel-wise background model and region-based foreground model 

      Gallego Vila, Jaime; Pardàs Feliu, Montse; Haro, Gloria (IEEE Press. Institute of Electrical and Electronics Engineers, 2009)
      Text en actes de congrés
      Accés obert
      In this paper we present a segmentation system for monocular video sequences with static camera that aims at foreground/ background separation and tracking. We propose to combine a simple pixel-wise model for the background ...
    • Connected Operators on 3D data for human body analysis 

      Alcoverro Vidal, Marcel; López Méndez, Adolfo; Pardàs Feliu, Montse; Casas Pla, Josep Ramon (2011)
      Text en actes de congrés
      Accés restringit per política de l'editorial
      This paper presents a novel method for filtering and extraction of human body features from 3D data, either from multi-view images or range sensors. The proposed algorithm consists in processing the geodesic distances on ...
    • Context-unsupervised adversarial network for video sensors 

      Canet Tarrés, Gemma; Pardàs Feliu, Montse (Multidisciplinary Digital Publishing Institute (MDPI), 2022-04-21)
      Article
      Accés obert
      Foreground object segmentation is a crucial first step for surveillance systems based on networks of video sensors. This problem in the context of dynamic scenes has been widely explored in the last two decades, but it ...
    • Depth estimation and semantic segmentation from a single RGB image using a hybrid convolutional neural network 

      Lin, Xiao; Sánchez Escobedo, Dalila; Casas Pla, Josep Ramon; Pardàs Feliu, Montse (Multidisciplinary Digital Publishing Institute (MDPI), 2019-04-15)
      Article
      Accés obert
      Semantic segmentation and depth estimation are two important tasks in computer vision, and many methods have been developed to tackle them. Commonly these two tasks are addressed independently, but recently the idea of ...
    • Elaboració de materials transversals per a l'aprenentatge actiu de les matèries de processat d'imatge i vídeo pels graus de sistemes audiovisuals i de telecomunicacions 

      Vilaplana Besler, Verónica; Casas Pla, Josep Ramon; Gasull Llampallas, Antoni; Marqués Acosta, Fernando; Morros Rubió, Josep Ramon; Pardàs Feliu, Montse; Ruiz Hidalgo, Javier; Salembier Clairon, Philippe Jean (Universitat Politècnica de Catalunya. Institut de Ciències de l'Educació, 2013-02-08)
      Text en actes de congrés / Comunicació de congrés
      Accés obert
      La finalitat del projecte ha estat promoure la col·laboració i coordinació entre les diverses assignatures de processat d'imatge i vídeo impartides per professors del Departament de TSC, als graus de telecomunicacions ...
    • Examen Final 

      Gasull Llampallas, Antoni; Pardàs Feliu, Montse (Universitat Politècnica de Catalunya, 2016-06-01)
      Examen
      Accés restringit a la comunitat UPC
    • Examen Final 

      Salembier Clairon, Philippe Jean; Pardàs Feliu, Montse (Universitat Politècnica de Catalunya, 2017-01-09)
      Examen
      Accés restringit a la comunitat UPC
    • Extraction and tracking of the eyelids 

      Pardàs Feliu, Montse (Institute of Electrical and Electronics Engineers (IEEE), 2000)
      Text en actes de congrés
      Accés obert
      Facial analysis is used in a number of applications like face recognition systems, human-computer interaction through head movements or facial expressions, or model based coding. In all these applications a very precise ...