Moving object detection in dynamic background

Abstract

The application of RPCA model in moving object detection can accurately extract the moving foreground, but the effect of the model is not ideal under complex dynamic background conditions. Based on this, this paper proposes an improved RPCA model based on rank–1 regulation and 3D-TV. The improved model uses regulation term to describe the low rank of video background, 3D-TV to constrain the spatiotemporal continuity of moving objects, and F-norm to eliminate the dynamic interference in video background. The experimental results show that the improved model proposed in this paper can effectively deal with the complex dynamic background and obtain a complete foreground object.