基于模糊逻辑的码本视频背景建模方法.pdf

中国科技论文在线 A Combined Fuzzy Logic-based Codebook for Foreground-background Segmentation ** 5 CUI Yuanyuan, MEN Aidong (School of information and communication engineering, Beijing University of Posts and Telecommunications, Beijing 100876) Abstract: This paper introduces a combined codebook model for foreground-background segmentation. The improvement is two-fold. First, to cope with changing global lumination, we 10 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 15 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) 20 Key words: image processing; background modeling; fuzzy logic