Lavanya M P
Abstract: In todays competitive generation; the security concerns have grown rapidly. The latest technology used for security concerns is motion detection system. Motion detection is broadly used in many computer vision tasks like pose estimation; human tracking and face recognition. It is a basic part for many computer vision tasks. By using this technologies; it is possible to monitor and capture every motion by inch and second of the area of interest. As motion detection system is real time and it is implemented widely; system is used to detect any motion in a real time video and once motion has been detected in the real time; the warning system will activate by means of an alarm and capture the real time video. The methods employed to detect the motion are background subtraction method and frame difference method. The purposed method makes background image using 4 previous consecutive frames. This method detects the motion via a standard webcam in real-time YUY2_640x480 resolution.Experimental results showed that the proposed method is more robust in nature as it can avoid the noise in motion detection due to camera flicker and useful to reduce the number of false positive alarms.
Keywords: Background subtraction method, frame difference, motion detection, consecutive frames, threshold comparison method