TY - JOUR
T1 - Multi-part body segmentation based on depth maps for soft biometry analysis
AU - Madadi, Meysam
AU - Escalera, Sergio
AU - Gonzàlez, Jordi
AU - Roca, F. Xavier
AU - Lumbreras, Felipe
N1 - Publisher Copyright:
© 2015 Elsevier B.V. All rights reserved.
PY - 2015/4/15
Y1 - 2015/4/15
N2 - This paper presents a novel method extracting biometric measures using depth sensors. Given a multi-part labeled training data, a new subject is aligned to the best model of the dataset, and soft biometrics such as lengths or circumference sizes of limbs and body are computed. The process is performed by training relevant pose clusters, defining a representative model, and fitting a 3D shape context descriptor within an iterative matching procedure. We show robust measures by applying orthogonal plates to body hull. We test our approach in a novel full-body RGB-Depth data set, showing accurate estimation of soft biometrics and better segmentation accuracy in comparison with random forest approach without requiring large training data.
AB - This paper presents a novel method extracting biometric measures using depth sensors. Given a multi-part labeled training data, a new subject is aligned to the best model of the dataset, and soft biometrics such as lengths or circumference sizes of limbs and body are computed. The process is performed by training relevant pose clusters, defining a representative model, and fitting a 3D shape context descriptor within an iterative matching procedure. We show robust measures by applying orthogonal plates to body hull. We test our approach in a novel full-body RGB-Depth data set, showing accurate estimation of soft biometrics and better segmentation accuracy in comparison with random forest approach without requiring large training data.
KW - 3D point cloud alignment
KW - 3D shape context
KW - Depth maps
KW - Human body segmentation
KW - Soft biometry analysis
UR - http://www.scopus.com/inward/record.url?scp=84923259643&partnerID=8YFLogxK
U2 - 10.1016/j.patrec.2015.01.012
DO - 10.1016/j.patrec.2015.01.012
M3 - Journal article
AN - SCOPUS:84923259643
SN - 0167-8655
VL - 56
SP - 14
EP - 21
JO - Pattern Recognition Letters
JF - Pattern Recognition Letters
ER -