Simultaneous background/foreground segmentation and contour smoothing with level set based partial differential equation for intelligent surveillance systems over network

Abstract

In this paper, we propose for intelligent surveillance systems over the network, an automatic motion detection computer vision technique that uses a level set based energy functional, the minimisation of which results in simultaneous background modelling, foreground segmentation, and contour smoothing. The simultaneous dealing of background modelling and foreground segmentation has the effect that the two processes constrain each other positively, such that a good estimate of the background can be obtained with a small number of frames, and a temporal change in the scene is reflected quickly in the construction of the background image.