A Moving Target Detection Method Based on Improved Frame DifferenceBackground Modeling

摘要

Background modeling is the key technology for moving target detection implemented with the background differencemethod. The conventional background modeling methods cost large amount of calculation time, in order to improvethe speed and precision of the model, this paper presents an improved Frame Difference Background Modeling. Theframe difference background modeling was initialized by Selective Averaging method, on the basis of this, Moving objectsis detected by background difference method. This kind of modeling method separated the moving targets and gotthe average of the background area, reduced the influence of moving target to background. The experimental results showthat the method needs less prior video sequences and the background of the extracted is more accurately, the effect of themoving target detection is better.