Deep Background Modeling Using Fully Convolutional Network

Abstract

Background modeling plays an important role for video surveillance, object tracking, and object counting. In this paper, we propose a novel deep background modeling approach utilizing fully convolutional network. In the network block constructing the deep background model, three atrous convolution branches with different dilate are used to extract spatial information from different neighborhoods of pixels, which breaks the limitation that extracting spatial information of the pixel from fixed pixel neighborhood. Furthermore, we sample multiple frames from original sequential images with increasing interval, in order to capture more temporal information and reduce the computation. Compared with classical background modeling approaches, our approach outperforms the state-of-art approaches both in indoor and outdoor scenes.