TY  - JOUR
AU  - Antonio Hernandez
AU  - Nadezhda Zlateva
AU  - Alexander Marinov
AU  - Miguel Reyes
AU  - Petia Radeva
AU  - Dimo Dimov
AU  - Sergio Escalera
PY  - 2012//
TI  - Human Limb Segmentation in Depth Maps based on Spatio-Temporal Graph Cuts Optimization
T2  - JAISE
JO  - Journal of Ambient Intelligence and Smart Environments
SP  - 535
EP  - 546
VL  - 4
IS  - 6
KW  - Multi-modal vision processing
KW  - Random Forest
KW  - Graph-cuts
KW  - multi-label segmentation
KW  - human body segmentation
N2  - We present a framework for object segmentation using depth maps based on Random Forest and Graph-cuts theory, and apply it to the segmentation of human limbs. First, from a set of random depth features, Random Forest is used to infer a set of label probabilities for each data sample. This vector of probabilities is used as unary term in α−β swap Graph-cuts algorithm. Moreover, depth values of spatio-temporal neighboring data points are used as boundary potentials. Results on a new multi-label human depth data set show high performance in terms of segmentation overlapping of the novel methodology compared to classical approaches.
SN  - 1876-1364
L1  - http://refbase.cvc.uab.es/files/HZM2012a.pdf
UR  - http://dx.doi.org/10.3233/AIS-2012-0176
N1  - MILAB;HuPBA
ID  - Antonio Hernandez2012
ER  -