An improved method for visual surveillance using background subtraction technique

Moving object detection is an important research area in computer vision. It deals with detecting instances of moving objects of various classes (such as humans, animals, buildings, or vehicles) in digital images and frame sequences for increasing needs of security and surveillance in public or private areas. In this work, proposed improvement enhances the existing model by using some image processing techniques in order to improve detection quality and compared against existing model using metrics like error analysis, precision, recall, f-measure and accuracy. In the existing work, robust estimators were used in order to model an efficient background and then a fast test was used to classify foreground pixel. There were problem of noisy pixels (false detection) due to environmental changes like waving tree leaves, rippling water and lighting effects. The, proposed improvement overcomes the problem of false detection and enhances the detection quality.