ocean (2.7M)Aggregated Dynamic Background Modeling
Standard practices in background modeling learn a separate model for every pixel in the image. However, in dynamic scenes the connection between an observation and the place where it was observed is much less important and is usually random. For example, a wave observed in an ocean scene could easily have been observed at another place in the image. Moreover, during a limited learning period, we cannot expect to observe at every pixel all the possible background behaviors. We therefore develop in this paper a background model in which observations are decoupled from the place in the image where they were observed. A single non-parametric model is used to describe the dynamic region of the scene, aggregating the observations from the whole region. Using high-order features, we demonstrate the feasibility of our approach on challenging ocean scenes using only grayscale information.
Paper
Amit Adam, Ilan Shimshoni and Ehud Rivlin, Aggregated Dynamic Background Modeling (pdf). IEEE International Conference on Image Processing (ICIP), October 2006
Copyright note:
Copyright 2006 IEEE. Published in the 2006 International Conference on Image Processing (ICIP 2006), scheduled for October 8-11, 2006 in Atlanta, Georgia, USA. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works, must be obtained from the IEEE. Contact: Manager, Copyrights and Permissions / IEEE Service Center / 445 Hoes Lane / P.O. Box 1331 / Piscataway, NJ 08855-1331, USA. Telephone: +1-908-562-3966.
Example Videos
The following videos show the foreground detection masks obtained when using our model. We have used only gray-scale intensity co-occurrence information (in contrast with other works which use color and optical flow for example). No post-processing was employed on the obtained masks.
