Research on the Design of the Categorization System for Moving Information in Video Stream and Its Implementation

The moving objects are what attract most attention in the video surveillance system, and also the key part for study. Currently, the video surveillance system relies much on the subjective initiative of the observers while having the real-time surveillance. In this study, applying the mixture Gaussian model algorithm, the profile image of the moving objects in the picture got from the video surveillance is obtained, and then denoised so as to extract the feature vector of the image. Further, utilizing the already trained neural network, the feature vectors are categorized to elevate the intelligence of the surveillance system and to implement the automatic categorization on the moving objects. It is proved to be effective through the simulation test.