TY  - JOUR
AU  - Antonio Hernandez
AU  - Miguel Angel Bautista
AU  - Xavier Perez Sala
AU  - Victor Ponce
AU  - Sergio Escalera
AU  - Xavier Baro
AU  - Oriol Pujol
AU  - Cecilio Angulo
PY  - 2014//
TI  - Probability-based Dynamic Time Warping and Bag-of-Visual-and-Depth-Words for Human Gesture Recognition in RGB-D
T2  - PRL
JO  - Pattern Recognition Letters
SP  - 112
EP  - 121
VL  - 50
IS  - 1
KW  - RGB-D
KW  - Bag-of-Words
KW  - Dynamic Time Warping
KW  - Human Gesture Recognition
N2  - PATREC5825We present a methodology to address the problem of human gesture segmentation and recognition in video and depth image sequences. A Bag-of-Visual-and-Depth-Words (BoVDW) model is introduced as an extension of the Bag-of-Visual-Words (BoVW) model. State-of-the-art RGB and depth features, including a newly proposed depth descriptor, are analysed and combined in a late fusion form. The method is integrated in a Human Gesture Recognition pipeline, together with a novel probability-based Dynamic Time Warping (PDTW) algorithm which is used to perform prior segmentation of idle gestures. The proposed DTW variant uses samples of the same gesture category to build a Gaussian Mixture Model driven probabilistic model of that gesture class. Results of the whole Human Gesture Recognition pipeline in a public data set show better performance in comparison to both standard BoVW model and DTW approach.
L1  - http://refbase.cvc.uab.es/files/HBP2014.pdf
UR  - http://dx.doi.org/10.1016/j.patrec.2013.09.009
N1  - HuPBA;MV; 605.203
ID  - Antonio Hernandez2014
ER  -