PT Journal
AU Antonio Hernandez
   Nadezhda Zlateva
   Alexander Marinov
   Miguel Reyes
   Petia Radeva
   Dimo Dimov
   Sergio Escalera
TI Human Limb Segmentation in Depth Maps based on Spatio-Temporal Graph Cuts Optimization
SO Journal of Ambient Intelligence and Smart Environments
JI JAISE
PY 2012
BP 535
EP 546
VL 4
IS 6
DI 10.3233/AIS-2012-0176
DE Multi-modal vision processing; Random Forest; Graph-cuts; multi-label segmentation; human body segmentation
AB 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.
ER