A video target detection algorithm based on pixels texture correlation background model

Abstract

This paper describes a screen target detection algorithm which is based on the background of Pixel texture information to judge models. The model is based on Bayesian statistical model frame, using histogram to get background reference, and lead in texture information of pixels to determine the results of the test optimization. It can quickly and accurately generate reference background, accumulating less noise during the period of updating background, and keeping longtime stability. Experimental results show that compared with the Bayesian statistical model, the screen target detection algorithm which is based on the background of Pixel texture information to judge models has greatly improved in accuracy and reduced in error rate.