TY  - JOUR
AU  - Cristina Palmero
AU  - Albert Clapes
AU  - Chris Bahnsen
AU  - Andreas Møgelmose
AU  - Thomas B. Moeslund
AU  - Sergio Escalera
PY  - 2016//
TI  - Multi-modal RGB-Depth-Thermal Human Body Segmentation
T2  - IJCV
JO  - International Journal of Computer Vision
SP  - 217
EP  - 239
VL  - 118
IS  - 2
PB  - Springer US
KW  - Human body segmentation
KW  - RGB
KW  - Depth Thermal
N2  - This work addresses the problem of human body segmentation from multi-modal visual cues as a first stage of automatic human behavior analysis. We propose a novel RGB–depth–thermal dataset along with a multi-modal segmentation baseline. The several modalities are registered using a calibration device and a registration algorithm. Our baseline extracts regions of interest using background subtraction, defines a partitioning of the foreground regions into cells, computes a set of image features on those cells using different state-of-the-art feature extractions, and models the distribution of the descriptors per cell using probabilistic models. A supervised learning algorithm then fuses the output likelihoods over cells in a stacked feature vector representation. The baseline, using Gaussian mixture models for the probabilistic modeling and Random Forest for the stacked learning, is superior to other state-of-the-art methods, obtaining an overlap above 75 % on the novel dataset when compared to the manually annotated ground-truth of human segmentations.
L1  - http://refbase.cvc.uab.es/files/PCB2016.pdf
UR  - http://dx.doi.org/10.1007/s11263-016-0901-x
N1  - HuPBA;MILAB;
ID  - Cristina Palmero2016
ER  -