Digital.CSIC > Ciencia y Tecnologías Físicas > Instituto de Investigación en Inteligencia Artificial (IIIA) > (IIIA) Libros y partes de libros >

Open Access item Real-Time Object Segmentation Using a Bag of Features Approach

Authors:Aldavert, David
Ramisa, Arnau
Lopez de Mantaras, Ramon
Toledo, Ricardo
Issue Date:2010
Abstract:In this paper, we propose an object segmentation framework, based on the popular bag of features (BoF), which can process several images per second while achieving a good segmentation accuracy assigning an object category to every pixel of the image. We propose an efficient color descriptor to complement the information obtained by a typical gradient-based local descriptor. Results show that color proves to be a useful cue to increase the segmentation accuracy, specially in large homogeneous regions. Then, we extend the Hierarchical K-Means codebook using the recently proposed Vector of Locally Aggregated Descriptors method. Finally, we show that the BoF method can be easily parallelized since it is applied locally, thus the time necessary to process an image is further reduced. The performance of the proposed method is evaluated in the standard PASCAL 2007 Segmentation Challenge object segmentation dataset.
Identifiers:isbn: 9781607506423
Appears in Collections:(IIIA) Libros y partes de libros

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.