Submitted manuscript, 1.67 MB, PDF document
Research output: Contribution to Journal/Magazine › Journal article › peer-review
Research output: Contribution to Journal/Magazine › Journal article › peer-review
}
TY - JOUR
T1 - Articulated Human Body Parts Detection Based on Cluster Background Subtraction and Foreground Matching
AU - Bhaskar, Harish
AU - Mihaylova, Lyudmila
AU - Maskell, S.
PY - 2013/1/16
Y1 - 2013/1/16
N2 - Detecting people or other articulated objects and localizing their body parts is a challenging computer vision problem as their movement is unpredictable under circumstances of partial and full occlusions. In this paper, a framework for human body parts tracking in video sequences using a self-adaptive clus- ter background subtraction (CBS) scheme is proposed based on a Gaussian mixture model (GMM) and foreground matching with rectangular pictorial structures. The efficiency of the designed human body parts tracking frame- work is illustrated over various real-world video sequences.
AB - Detecting people or other articulated objects and localizing their body parts is a challenging computer vision problem as their movement is unpredictable under circumstances of partial and full occlusions. In this paper, a framework for human body parts tracking in video sequences using a self-adaptive clus- ter background subtraction (CBS) scheme is proposed based on a Gaussian mixture model (GMM) and foreground matching with rectangular pictorial structures. The efficiency of the designed human body parts tracking frame- work is illustrated over various real-world video sequences.
KW - target tracking
KW - background subtraction
KW - optimisation
KW - genetic algorithms
KW - pictorial structures
KW - articulated objects
U2 - 10.1016/j.neucom.2011.12.039
DO - 10.1016/j.neucom.2011.12.039
M3 - Journal article
VL - 100
SP - 58
EP - 73
JO - Neurocomputing
JF - Neurocomputing
SN - 0925-2312
IS - 1
ER -