Paper Title
Semantic Content Extraction In Video Surveillance System

Abstract
Recent increase in the use of video-based applications has revealed the need for extracting the content in videos. The video data in row format is not useful that much because it requires a human being to moderate surveillance system continuously. So we require the automated system which moderate the surveillance system and give us information about only important events happening in the premises. There are 3 layers of video data 1) low level data (raw data) 2) Middle level data (content information) 3) High level Data (event information). The raw data contains the low level features of video like number of frames, length, pixel no. etc which not so important to user. The content information consist the information about the object and occurrences of that object in video. The event information consist the relation between the objects in temporal and spatial manner. We extract the event information in the form of semantic content, which consist of relation between objects. Keywords- Pattern Recognition and Feature Content Extraction, Fuzziness