Affiliations: Computer Vision Center, Edifici O, Campus UAB, 08193 Bellaterra (Cerdanyola), Barcelona, Spain. E-mail: {ahernandez,mreyes,petia,sescalera}@cvc.uab.cat | Dept. of Applied Mathematics and Analysis, Universitat de Barcelona, Gran Via 585, 08007 Barcelona, Spain | Inst. of Information and Communication Technologies, BAS, Acad. G. Bonchev St., Block 2, Sofia 1113, Bulgaria. E-mail: {zlateva,amarinov,dtdim}@iinf.bas.bg
Note: [] Corresponding author.
Abstract: 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.
Keywords: Multi-modal vision processing, Random Forest, Graph-cuts, multi-label segmentation, human body segmentation
