TY  - CONF
AU  - David Aldavert
AU  - Arnau Ramisa
AU  - Ramon Lopez de Mantaras
AU  - Ricardo Toledo
A2  - CCIA
ED  - In R.Alquezar, A.Moreno
PY  - 2010//
TI  - Real-time Object Segmentation using a Bag of Features Approach
BT  - 13th International Conference of the Catalan Association for Artificial Intelligence
SP  - 321–329
VL  - 220
PB  - IOS Press Amsterdam,
KW  - Object Segmentation
KW  - Bag Of Features
KW  - Feature Quantization
KW  - Densely sampled descriptors
N2  - 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.
SN  - 9781607506423
UR  - http://hdl.handle.net/10261/60904
N1  - ADAS
ID  - David Aldavert2010
ER  -