We present a background subtraction method that uses multiple cues to detect objects robustly in adverse conditions. The algorithm consists of three distinct levels, i.e., pixel level, region level and frame level. At the pixel level, statistical models of gradients and color are separately used to classify each pixel as belonging to background or foreground. In the region level, foreground pixels obtained from the color based subtraction are grouped into regions and gradient based subtraction is then used to make inferences about the validity of these regions. Pixel based models are updated based on decisions made at the region level. Finally, frame level analysis is performed to detect global illumination changes. Our method provides the solution to some of the common problems that are not addressed by most background subtraction algorithms, such as fast illumination changes, repositioning of static background objects, and initialization of background model with moving objects present in the scene.
A hierarchical approach to robust background subtraction using color and gradient information
2002-01-01
346148 byte
Conference paper
Electronic Resource
English
A Hierarchical Approach to Robust Background Subtraction Using Color and Gradient Information
British Library Conference Proceedings | 2002
|Trans Tech Publications | 2014
|Background subtraction model based on color and depth cues
British Library Online Contents | 2014
|A novel background subtraction method based on color invariants
British Library Online Contents | 2013
|Background Subtraction Using Markov Thresholds
IEEE | 2005
|