%0 Journal Article
%T Segmentation of RGB-D Indoor scenes by Stacking Random Forests and Conditional Random Fields
%A Mikkel Thogersen
%A Sergio Escalera
%A Jordi Gonzalez
%A Thomas B. Moeslund
%J Pattern Recognition Letters
%D 2016
%V 80
%F Mikkel Thogersen2016
%O HuPBA; ISE;MILAB; 600.098; 600.119
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=2843), last updated on Fri, 19 Feb 2021 09:58:40 +0100
%X This paper proposes a technique for RGB-D scene segmentation using Multi-classMulti-scale Stacked Sequential Learning (MMSSL) paradigm. Following recent trends in state-of-the-art, a base classifier uses an initial SLIC segmentation to obtain superpixels which provide a diminution of data while retaining object boundaries. A series of color and depth features are extracted from the superpixels, and are used in a Conditional Random Field (CRF) to predict superpixel labels. Furthermore, a Random Forest (RF) classifier using random offset features is also used as an input to the CRF, acting as an initial prediction. As a stacked classifier, another Random Forest is used acting on a spatial multi-scale decomposition of the CRF confidence map to correct the erroneous labels assigned by the previous classifier. The model is tested on the popular NYU-v2 dataset.The approach shows that simple multi-modal features with the power of the MMSSLparadigm can achieve better performance than state of the art results on the same dataset.
%U https://doi.org/10.1016/j.patrec.2016.06.024
%P 208–215