基于模糊逻辑的码本视频背景建模方法

his paper introduces a combined codebook model for foreground-background segmentation. The improvement is two-fold. First, to cope with changing global lumination, we develop the conventional codebook with confidence functions. Similarities of both brightness and normalized color-vector are integrated confidence-weightedly to form overall similarity. A designed codeword-update progress also contributes to the stable performance. Then, inspired by fuzzy logic, a background membership function is constructed from former segmentations. It measures how reliable it is to take a certain similarity value as background. The threshold to separate foreground form background is for background membership function, rather than the overall similarity itself. As each video owns a unique background membership function, the method is able to adjust itself with the statistical properties of given video. A thorough evaluation is performed on the Wallflower dataset. Qualitative and quantitative results and comparisons with other approaches justify the model.(10 Points, Times New Roman)