A novel framework for background subtraction and foreground detection

In this paper, we propose a novel image background subtraction framework based on KDE. Firstly a new data structure called Mino Vector (MV) is designed for each pixel; we define dynamic nature (DN) for pixels of a scene and rank them in terms of DN for getting quantized results named dynamic rank (DR). Then, the varying KDE is adopted and implemented which significantly improves the estimation accuracy. Unlike using a global threshold in literature, we adaptively set a threshold for each pixel according to its DR. Inspired by the popular computer game Tetris, we present a Tetris update scheme (TUS) to update the background model in which the bottom row will be cleared, so do noises when the update condition is met. In experiments, we evaluate our framework on a well-known video dataset, CDnet 2012. Our results indicate that our framework achieves competitive results when compared with the state-of-the-art methods.