An efficient pattern-less background modeling based on scale invariant local states

A robust and efficient background modeling algorithm is crucial to the success of most of the intelligent video surveillance systems. Compared with intensity-based approaches, texture-based background modeling approaches have shown to be more robust against dynamic backgrounds and illumination changes, which are common in real life videos. However, many of the existing texture-based methods are too computationally expensive, which renders them useless in real-time applications. In this paper, a novel efficient texture-based background modeling algorithm is presented. Scale invariant local states (SILS) are introduced as pixel features for modeling a background pixel, and a pattern-less probabilistic measurement (PLPM) is derived to estimate the probability of a pixel being background from its SILS. An adaptive background modeling framework is also introduced for learning and representing a multi-modal background model. Experimental results show that the proposed method can run nearly 3 times faster than existing state-of-the-art texture-based method, without sacrificing the output quality. This allows more time for a real-time surveillance system to carry out other computationally intensive analysis on the detected foreground objects.