To access the full text documents, please follow this link:

Improving spatial codification in semantic segmentation
Ventura Royo, Carles; Giró Nieto, Xavier; Vilaplana Besler, Verónica
Universitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions; Universitat Politècnica de Catalunya. GPI - Grup de Processament d'Imatge i Vídeo
This paper explores novel approaches for improving the spatial codification for the pooling of local descriptors to solve the semantic segmentation problem. We propose to partition the image into three regions for each object to be described: Figure, Border and Ground. This partition aims at minimizing the influence of the image context on the object description and vice versa by introducing an intermediate zone around the object contour. Furthermore, we also propose a richer visual descriptor of the object by applying a Spatial Pyramid over the Figure region. Two novel Spatial Pyramid configurations are explored: Cartesian-based and crown-based Spatial Pyramids. We test these approaches with state-of-the-art techniques and show that they improve the Figure-Ground based pooling in the Pascal VOC 2011 and 2012 semantic segmentation challenges.
Peer Reviewed
Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la imatge i del senyal vídeo
Pattern recognition systems
Image processing--Digital techniques
Imatges -- Processament -- Tècniques digitals
Reconeixement de formes (Informàtica)

Show full item record

Related documents

Other documents of the same author

Ventura Royo, Carles; Giró Nieto, Xavier; Vilaplana Besler, Verónica; Giribet, Daniel; Carasusan, Eusebio
Ventura Royo, Carles; Vilaplana Besler, Verónica; Giró Nieto, Xavier; Marqués Acosta, Fernando
Ventura Royo, Carles; Martos Asensio, Manuel; Giró Nieto, Xavier; Vilaplana Besler, Verónica; Marqués Acosta, Fernando
Ventura Royo, Carles; Tella-Amo, Marcel; Giró Nieto, Xavier