A model change detection approach to dynamic scene modeling

Kim, S. J., Doretto, G., Rittscher, J., Tu, P., Krahnstoever, N., and Pollefeys, M.
A model change detection approach to dynamic scene modeling
In Proceedings of IEEE International Conference on Video and Signal Based Surveillance, pp. 490–495, September 2009.
Oral Presentation

Download

PDF (922.5kB )  

Abstract

In this work we propose a dynamic scene model to provide information about the presence of salient motion in the scene, and that could be used for focusing the attention of a pan/tilt/zoom camera, or for background modeling purposes. Rather than proposing a set of saliency detectors, we define what we mean by salient motion, and propose a precise model for it. Detecting salient motion becomes equivalent to detecting a model change. We derive optimal online procedures to solve this problem, which enable a very fast implementation. Promising results show that our model can effectively detect salient motion even in severely cluttered scenes, and while a camera is panning and tilting.

BibTeX

@InProceedings{kimDRTKP09avss,
  Title                    = {A model change detection approach to dynamic scene modeling},
  Author                   = {Kim, S. J. and Doretto, G. and Rittscher, J. and Tu, P. and Krahnstoever, N. and Pollefeys, M.},
  Booktitle                = avss,
  Year                     = {2009},
  Month                    = sep,
  Pages                    = {490--495},
  Abstract                 = {In this work we propose a dynamic scene model to provide information about the presence of salient motion in the scene, and that could be used for focusing the attention of a pan/tilt/zoom camera, or for background modeling purposes. Rather than proposing a set of saliency detectors, we define what we mean by salient motion, and propose a precise model for it. Detecting salient motion becomes equivalent to detecting a model change. We derive optimal online procedures to solve this problem, which enable a very fast implementation. Promising results show that our model can effectively detect salient motion even in severely cluttered scenes, and while a camera is panning and tilting.},
  Bib2html_pubtype         = {Refereed Conferences},
  Bib2html_rescat          = {Video Surveillance, Dynamic Textures, Visual Motion Detection},
  File                     = {kimDRTKP09avss.pdf:doretto\\conference\\kimDRTKP09avss.pdf:PDF},
  Keywords                 = {dynamic scene modeling, PTZ camera, focus-ofattention, background modeling, sequential generalized likelihood ratio, model change detection, linear dynamical systems, dynamic textures},
  Owner                    = {doretto},
  Timestamp                = {2009.09.28},
  Wwwnote                  = {<span class="wwwnote">Oral Presentation</span>}
}