AN INTELLIGENT EVENT DETECTION AND ALARM BASED SURVEILLANCE ALGORITHM FOR VIDEO SUMMARIZATION

摘要

Video Summarization is currently the most researched area of Computer Vision. Researchers nowadays are trying to propose more intelligent and efficient solutions for problems related to summarization. The proposed system is an effort towards the objective of proposing an intelligent and efficient algorithm designed in order to summarize the video, based upon the detection of a human being carrying a specific object, captured by a video camera. Security cameras are widely used for security purposes and to detect any illegal movement inside or outside the campus. These cameras are backbone of modern security infrastructure in any critical or security sensitive organization e.g defense sector, education sector, hospitals etc. The system being developed actually captures each frame from the video, then it processes the frame, it retains the frames of its interest, otherwise discards the frame, hence the resultant video is very short and it only contains those frames in which a human being is carrying an object of our interest, i-e a Laptop, Projector and a PC in our case. The system also generate an alarm in the form of a beep whenever it captures a frame in which there is a person carrying a specific object which is basically an alert to prompt security officials about an illegal movement in the surroundings.