Analysis of Volume Local Binary Patterns for Video based Smoke Detection

A video based smoke detection method using dynamic texture feature extraction with volume local binary patterns is studied. Dynamic texture features were extracted from blocks and irregular motion regions, respectively. Different operators were used to extract dynamic texture for smoke detection to study their characteristics. The results show that dynamic texture is a reliable clue for video based smoke detection. Irregular motion regions based method reduces adverse impacts of block size and motion area ratio threshold. It is generally conducive to reducing the false alarm rate by increasing the dimension of the feature vector. Additionally, it is found that the feature computing time is not directly related to the vector dimension, which is important for the realization of real-time detection.