Gianfranco Doretto / Publications

Online Geometric Human Interaction Segmentation and Recognition

Siyahjani, F., Motiian, S., Bharthavarapu, H., Sharlemin, S., and Doretto, G.
Online Geometric Human Interaction Segmentation and Recognition
In icme, July 2014.

Download

PDF (1.3MB )  

Abstract

We address the problem of online temporal segmentation and recognition of human interactions in video sequences. The complexity of the high-dimensional data variability representing interactions is handled by combining kernel methods with linear models, giving rise to kernel regression and kernel state space models. By exploiting the geometry of linear operators in Hilbert space, we show how the concept of parity space, defined for linear models, generalizes to the kernellized extensions. This provides a powerful and flexible framework for online temporal segmentation and recognition. We extensively evaluate the approach on a publicly available dataset, and on a new challenging human interactions dataset that we have collected. The results show that the approach holds the promise to become an effective building block for the analysis in real-time of human behavior.

BibTeX

@InProceedings{siyahjaniMBSD14icme,
  Title                    = {Online Geometric Human Interaction Segmentation and Recognition},
  Author                   = {Siyahjani, F. and Motiian, S. and Bharthavarapu, H. and Sharlemin, S. and Doretto, G.},
  Booktitle                = icme,
  Year                     = {2014},
  Month                    = jul,
  Abstract                 = {We address the problem of online temporal segmentation and recognition of human interactions in video sequences. The complexity of the high-dimensional data variability representing interactions is handled by combining kernel methods with linear models, giving rise to kernel regression and kernel state space models. By exploiting the geometry of linear operators in Hilbert space, we show how the concept of parity space, defined for linear models, generalizes to the kernellized extensions. This provides a powerful and flexible framework for online temporal segmentation and recognition. We extensively evaluate the approach on a publicly available dataset, and on a new challenging human interactions dataset that we have collected. The results show that the approach holds the promise to become an effective building block for the analysis in real-time of human behavior.},
  Bib2html_pubtype         = {Refereed Conferences},
  Bib2html_rescat          = {Interaction Recognition, Video Surveillance},
  File                     = {siyahjaniMBSD14icme.pdf:doretto/conference/siyahjaniMBSD14icme.pdf:PDF},
  Owner                    = {doretto},
  Timestamp                = {2014.05.21}
}