Fast and effective background subtraction based on eLBP
Lingfeng Wang, Chunhong Pan · 2010
Background subtraction is an important component of many com-puter vision systems. In this paper, we present a fast and efficient texture-based method for background subtraction in a video se-quence. At first, a novel LBP (Local Binary Pattern) operator called eLBP is applied to extract the local description of each pixel. Then, the kernel of background subtraction is performed based on two principle phases, i.e. the background building phase and the fore-ground detection phase. In the former phase, the probability that a pixel belongs to foreground is calculated based on the difference between the current eLBP and the adaptive mean eLBP. In the later phase, a thresholding operator is applied on the probability to determine whether a pixel can be classified as foreground, and the adaptive mean eLBP is updated by a user-settable learning rate. Finally, our approach is evaluated against several video sequences compared with the traditional MoG model. Experiments show that our method is suitable for various scenes and is appealing with respect to robustness.