Research

Research Interest

My broad areas of research interest are computer vision, statistical methods to machine learning, and image/signal processing.

My current research activity is focused on reconstructing the motion of an articulated human from a multi-view video footage. I rely on optimization and filtering tools to this end.

Google Scholar link.

Publications

P. Kaliamoorthi, R. Kakarala, "Probabilistic state space decomposition for human motion capture", Asian Conference on Computer Vision (ACCV 2014), Springer, LNCS. [PDF][VIDEO][SRC]

P. Kaliamoorthi, R. Kakarala, "Directional chamfer matching in 2.5 dimensions", IEEE Signal Processing Letters, December, 2013. [PDF]

P. Kaliamoorthi, R. Kakarala, "A robust integrated approach to segmentation and tracking", PSIVT, Springer, LNCS, October 2013. [PDF]

R. Kakarala, P. Kaliamoorthi*, V. Premachandran*, "Three-dimensional bilateral symmetry plane estimation in the phase domain'', IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2013. [PDF] (* equal contribution)

P. Kaliamoorthi, R. Kakarala, "Parametric annealing: a stochastic search method for human pose tracking", Pattern Recognition, Elsevier, May 2013. [PDF][SRC]

P. Kaliamoorthi, R. Kakarala, "Human pose tracking by parametric annealing", CVPR Workshop on Human Activity Understanding from 3D Data (HAU3D), June 2012. [PDF][PPT][SRC]

R. Kakarala, P. Kaliamoorthi, W. Li, "Viewpoint invariants from three-dimensional data: the role of reflection in human activity understanding", CVPR Workshop on Human Activity Understanding from 3D Data (HAU3D), June 2011. [PDF]

Patents

Nam-jae Jeon, Prabhu Kaliamoorthi, "Electronic apparatus and booting method of the same", US 20100306520

Prabhu Kaliamoorthi, "Portable apparatus, a host device for setting a shortcut function and a method thereof, specially for combining plural functions into one shortcut function according to a users intention", KR 1020070016176