Moving objects detection based on thresholding operations for video surveillance systems

Motion detection based on background subtraction approaches require a background model generation before extracting the moving objects. This extraction consists to subtract the static scene from the current image. The result of subtraction will be segmented in order to represent the moving object by a binary image using a threshold. In this paper a new background subtraction approach is presented. Firstly, each gray-level image of the sequence will be decomposed on two components, structure and texture/noise by applying the Osher and Vese algorithm. The structure component of each image will be taken to generate the background model. The background model development uses a threshold in order to decide if a pixel belongs to the background or to the foreground. The absolute difference is used to subtracting the background before compute the binary image of the moving objects using a proposed threshold selection operation. The experimental results demonstrate that our approach is effective and accurate moving objects detection comparing with the results of two existing methods.