El GPI fa recerca en Processament d'Imatge i Vídeo per representació, codificació, indexació i anàlisi del contingut visual. L'expertesa del grup en Morfologia i segmentació ha estat la base de contribucions als estàndards ISO MPEG-4 i MPEG-7. La recerca en anàlisi d'imatge l'ha permès participar en projectes europeus des de 1992 als programes RACE (Morpheco, coord.), ACTS (MAVT, MoMuSys, Vidas), IST (Diceman, Hypermedia, INTERFACE, ADViSOR, MASCOT, FAETHON), xarxes d'excel·lència (SCHEMA, SIMILAR, MUSCLE), i projectes integrats FP6 (CHIL) i FP7 (FASCINATE).

http://futur.upc.edu/GPI

El Grupo de Procesado de Imagen y Vídeo investiga técnicas de tratamiento de imagen y vídeo en los campos de compresión, análisis, indexación, representación e interfaces multimodales. El Grupo se ha especializado en herramientas básicas de filtrado no lineal y morfología matemática, segmentación, seguimiento de objetos, detección y reconocimiento de caras, análisis de emociones y modelitzación de la actividad humana, que han sido la base de aplicaciones de codificación basada en el contenido, representación de vídeo mediante índices y tablas de contenido, y contribuciones a estándares internacionales como MPEG4 y MPEG7. El Grupo también desarrolla aplicaciones biomédicas, de teledetección y marcado.

http://futur.upc.edu/GPI

The research of the Image and Video Processing Group focuses on the areas of compression, analysis, indexing, representation and multimodal interfaces. The group specialises in basic tools for nonlinear filtering, mathematical morphology, segmentation, object tracking, face detection and recognition, emotion analysis and modelling of human activity, which have been the basis of applications related to content-based video coding, video indexing and the creation of tables of content and contributions to international standardisation processes such as MPEG-4 and MPEG-7. The group also develops biomedical, remote-sensing and watermarking applications.

http://futur.upc.edu/GPI

The research of the Image and Video Processing Group focuses on the areas of compression, analysis, indexing, representation and multimodal interfaces. The group specialises in basic tools for nonlinear filtering, mathematical morphology, segmentation, object tracking, face detection and recognition, emotion analysis and modelling of human activity, which have been the basis of applications related to content-based video coding, video indexing and the creation of tables of content and contributions to international standardisation processes such as MPEG-4 and MPEG-7. The group also develops biomedical, remote-sensing and watermarking applications.

http://futur.upc.edu/GPI

Enviaments recents

  • Region-based video coding using mathematical morphology 

    Salembier Clairon, Philippe Jean; Torres Urgell, Lluís; Meyer, F; Gu, C (1995-06)
    Article
    Accés obert
    This paper presents a region-based coding algorithm for video sequences. The coding approach involves a time-recursive segmentation relying on the pixels homogeneity, a region-based motion estimation, and motion compensated ...
  • Image restoracion using the w-slice method 

    Sayrol Clols, Elisa; Chrysostomos, Nikias; Gasull Llampallas, Antoni (1995-08)
    Article
    Accés obert
    We propose the use of higher order statistics (HOS)-based methods to address the problem of image restoration. The restoration strategy is based on the fact that the phase information of the original image and its HOS are ...
  • Coding of details in very low bit-rate video systems 

    Casas Pla, Josep Ramon; Torres Urgell, Lluís (1994-06)
    Article
    Accés obert
    In this paper, the importance of including small image features at the initial levels of a progressive second generation video coding scheme is presented. It is shown that a number of meaningful small features called details ...
  • Hierarchical morphological segmentation for image sequence coding 

    Salembier Clairon, Philippe Jean; Pardàs Feliu, Montse (1994-09)
    Article
    Accés obert
    This paper deals with a hierarchical morphological segmentation algorithm for image sequence coding. Mathematical morphology is very attractive for this purpose because it efficiently deals with geometrical features such ...
  • Bags of local convolutional features for scalable instance search 

    Mohedano, Eva; Salvador Aguilera, Amaia; McGuinness, Kevin; Marqués Acosta, Fernando; O'Connor, Noel; Giró Nieto, Xavier (Association for Computing Machinery (ACM), 2016)
    Comunicació de congrés
    Accés obert
    This work proposes a simple instance retrieval pipeline based on encoding the convolutional features of CNN using the bag of words aggregation scheme (BoW). Assigning each local array of activations in a convolutional layer ...
  • LTA 2016: The First Workshop on Lifelogging Tools and Applications 

    Gurrin, Cathal; Giró Nieto, Xavier; Radeva, Petia; Dimicolli, Mariella; Johansen, Havard D.; Joho, Hideo; Singh, Vivek K. (Association for Computing Machinery (ACM), 2016)
    Text en actes de congrés
    Accés restringit per política de l'editorial
    The organisation of personal data is receiving increasing research attention due to the challenges we face in gathering, enriching, searching, and visualising such data. Given the increasing ease with which personal data ...
  • Multiresolution hierarchy co-clustering for semantic segmentation in sequences with small variations 

    Varas González, David; Alfaro Vendrell, Mónica; Marqués Acosta, Fernando (Institute of Electrical and Electronics Engineers (IEEE), 2015)
    Text en actes de congrés
    Accés restringit per política de l'editorial
    This paper presents a co-clustering technique that, given a collection of images and their hierarchies, clusters nodes from these hierarchies to obtain a coherent multiresolution representation of the image collection. We ...
  • Where is my phone?: personal object retrieval from egocentric images 

    Reyes, Cristian; Mohedano, Eva; McGuinness, Kevin; O'Connor, Noel; Giró Nieto, Xavier (Association for Computing Machinery (ACM), 2016)
    Comunicació de congrés
    Accés restringit per política de l'editorial
    This work presents a retrieval pipeline and evaluation scheme for the problem of finding the last appearance of personal objects in a large dataset of images captured from a wearable camera. Each personal object is modelled ...
  • Supervised evaluation of image segmentation and object proposal techniques 

    Pont Tuset, Jordi; Marqués Acosta, Fernando (2016-07-01)
    Article
    Accés obert
    This paper tackles the supervised evaluation of image segmentation and object proposal algorithms. It surveys, structures, and deduplicates the measures used to compare both segmentation results and object proposals with ...
  • Aplicación del algoritmo de Kalman al estudio de la ritmicidad ultradiana en el comportamiento expontáneo de sujetos humanos aislados 

    Carol Vilanova, Antonio; Gasull Llampallas, Antoni; Lagunas Hernandez, Miguel A. (E.T.S.I.I.T, 1981)
    Text en actes de congrés
    Accés obert
    Este trabajo explora la posible existencia de ritmos ultradianos (período comprendido entre 30 minutos y 20 horas) en el comportamiento espontáneo vigil del hombre, analizando espectralmente las señales con el filtra ...

Mostra'n més