• Detection-aided medical image segmentation using deep learning 

      Bellver Bueno, Míriam (Universitat Politècnica de Catalunya, 2017-08-14)
      Projecte Final de Màster Oficial
      Accés obert
      Realitzat a/amb:   Eidgenössische Technische Hochschule Zürich
      A fully automatic technique for segmenting the liver and localizing its unhealthy tissues is a convenient tool in order to diagnose hepatic diseases and also to assess the response to the according treatments. In this ...
    • Image-Based Query by Example Using MPEG-7 Visual Descriptors 

      Ventura Royo, Carles (Escola Tècnica Superior de Telecomunicació de Barcelona, 2010)
      Projecte/Treball Final de Carrera
      Accés obert
      This project presents the design and implementation of a Content-Based Image Retrieval (CBIR) system where queries are formulated by visual examples through a graphical interface. Visual descriptors and similarity measures ...
    • Pin-hole camera calibration in football scenes based on the Hough transform 

      Espinosa Fricke, Pedro-Christian (Universitat Politècnica de Catalunya, 2010-05-10)
      Projecte/Treball Final de Carrera
      Accés obert
      This work deals with camera calibration in general views of football match broadcast sequences. In this context, to calibrate a camera, which is determining the camera real-world location and where it is pointing at, is ...
    • Video Object Segmentation by Tracking Structured Key Points and Contours 

      Caelles Prat, Sergi (Universitat Politècnica de Catalunya, 2016-08)
      Projecte Final de Màster Oficial
      Accés obert
      Realitzat a/amb:   Eidgenössische Technische Hochschule Zürich
      In this thesis, we tackle the problem of video object segmentation where we have to classify every pixel of every frame in a video sequence into background and foreground classes. Our algorithms fall in the semi-supervised ...
    • Visibility estimation of advertising panels in football sequences 

      Varas González, David (Universitat Politècnica de Catalunya, 2009-09-06)
      Projecte/Treball Final de Carrera
      Accés obert
      In this work, we propose a robust classification system that estimates the advertising panels visibility in real time. For each frame of the sequence, a set of descriptors is extracted to characterize a specific part of ...