A model change detection approach to dynamic scene modeling

—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. Keywords-dynamic scene modeling, PTZ camera, focus-ofattention, background modeling, sequential generalized likelihood ratio, model change detection, linear dynamical systems, dynamic textures.

• Type: Conference
• Year: 2009
• Where: AVSS
• Authors: Seon Joo Kim, Gianfranco Doretto, Jens Rittscher, Peter H. Tu, Nils Krahnstoever, Marc Pollefeys
• Keywords: AVSS 2009, Model, Model Change, Salient Motion, Signal Processing