A Moving Object Detection Algorithm Based on Multiple Judgments

The traditional background subtraction method is more sensitive to light and shows poor anti-interference performance.A moving object detection algorithm based on multiple judgments is proposed.The Local Binary Pattern(LBP)algorithm is considered to put texture information into the background model,combining color and texture information and an improved background subtraction method proposed.In addition,a new method is proposed combining the inter-frame difference method with improved background subtraction method in this paper.The method made use of dual-threshed to detect moving targets and make multiple judgments.It not only used the change of pixel gray value to detect moving targets,but also took advantage of the number of changed pixels to detect moving targets interested in.The algorithm uses people and vehicles as moving targets to be detected through mat lab.The experiment showed that the algorithm was able to detect the moving target accurately and can resist interferences which were brought about by the slow sand slight movements in the scene with better robustness.