Background Subtraction Methods for Motion Detection in Video Surveillance Systems
Boris Nikolov, Nikolay Kostov, Nikolay Velikov · Journal of marine Technology and Environment · 2010
A main activity of many computer vision systems is foreground object detection. Motion is used in a video sequence to identify target objects. Many background subtraction methods have been proposed to identify motion that belongs to a moving object. Each has advantages and disadvantages when applied under different conditions. This paper proposes an overview of 5 background subtraction methods. One of the features that was found was that the more complex methods, such as Kernel Density Estimate and mixture of Gaussians, achieve more high precision and recall when applied to practice. Lower precision and recall resulted from the more basic methods. However, the more basic methods are less expensive in computational costs.