Background subtraction in highly dynamic scenes
- 1 June 2008
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 1-6
Abstract
A new algorithm is proposed for background subtraction in highly dynamic scenes. Background subtraction is equated to the dual problem of saliency detection: background points are those considered not salient by suitable comparison of object and background appearance and dynamics. Drawing inspiration from biological vision, saliency is defined locally, using center-surround computations that measure local feature contrast. A discriminant formulation is adopted, where the saliency of a location is the discriminant power of a set of features with respect to the binary classification problem which opposes center to surround. To account for both motion and appearance, and achieve robustness to highly dynamic backgrounds, these features are spatiotemporal patches, which are modeled as dynamic textures. The resulting background subtraction algorithm is fully unsupervised, requires no training stage to learn background parameters, and depends only on the relative disparity of motion between the center and surround regions. This makes it insensitive to camera motion. The algorithm is tested on challenging video sequences, and shown to outperform various state-of-the-art techniques for background subtraction.Keywords
This publication has 17 references indexed in Scilit:
- Bayesian modeling of dynamic scenes for object detectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2005
- A Principled Approach to Detecting Surprising Events in Video2005
- On incremental and robust subspace learningPattern Recognition, 2004
- Motion detection with nonstationary backgroundMachine Vision and Applications, 2003
- Statistics of natural images and models2003
- Background modeling and subtraction of dynamic scenes2003
- Detecting salient motion by accumulating directionally-consistent flowIEEE Transactions on Pattern Analysis and Machine Intelligence, 2000
- Motion tracking with an active cameraIEEE Transactions on Pattern Analysis and Machine Intelligence, 1994
- N4SID: Subspace algorithms for the identification of combined deterministic-stochastic systemsAutomatica, 1994
- AN APPROACH TO TIME SERIES SMOOTHING AND FORECASTING USING THE EM ALGORITHMJournal of Time Series Analysis, 1982