Human Motion Detection with a Triggered Alarm in University of Benin Computer Engineering Laboratory Using Frame Difference

Abstract

Human motion detection with a triggered alarm system plays an important role in University of Benin Computer Engineering Laboratory by intelligently gathering information of unauthorized personnel from malicious activities. Traditional video surveillance takes a huge amount of storage space and hence limits the duration of video that can be stored. In addition, the traditional video surveillance is time-consuming for a human to review the stored video. All these disadvantages limit the effectiveness of traditional video surveillance. This paper presents an algorithm using Matrix Laboratory (MATLAB) software for detecting human motion from a static background scene based on frame difference and subsequent generation of an alarm condition as soon as the human motion is detected. The experiment shows that the method is robust to noise and can detect the human body under both simple and complex circumstance with good performance and efficiency. The overall efficiency of the work was found to be 63.64 percent.