Features

The characteristics of the features are the following ones (Features Website) (532 papers):

• Feature size (45 papers)

• Feature type (410 papers)

• Feature strategies (65 papers)

• Feature selection (9 papers)

• Feature reliability (4 papers)

• Feature relevance (2 papers)

Fair Use Policy

This web site presents a survey on robust features for background/foreground separation. If you use information from this web site for publication, please cite the following papers:

C. Silva, T. Bouwmans, C. Frelicot, 'An eXtended Center-Symmetric Local Binary Pattern for Background Modeling and Subtraction in Videos", VISAPP 2015, Berlin, Germany, March  2015.

C. Silva, T.  Bouwmans, C. Frelicot, "Online Weighted One-Class Ensemble for Feature Selection in Background/Foreground Separation", International Conference on  Pattern Recognition, ICPR 2016, December 2016.

C. Pacheco, T. Bouwmans, C. Frelicot,"Superpixel-based online wagging one-class ensemble for feature selection in foreground/background separation", Pattern Recognition Letters, 2017. 

T. Bouwmans, C. Silva, C. Marghes, M. Zitouni, H. Bhaskar, C. Frelicot, “On the Role and the Importance of Features for Background Modeling and Foreground Detection”, Computer Science Review, Volume 28, pages 26-91, May 2018.