Scene background estimation based on temporal median filter with Gaussian filtering
Wei Liu, Yuanzheng Cai, Miaohui Zhang, Hui Li, He-Jin Gu · 2016
Background estimation can be regarded as a problem to construct the background from a series of video frames including moving objects in the scene. Scene background estimation is the essential prerequisite, or at least can be helpful for many applications such as video surveillance, video segmentation, and privacy protection for videos. To perform this task, in this paper we propose a robust framework for scene background modelling based on temporal median filter with Gaussian filtering. Specifically, each background pixel is firstly modeled with a probability density function (PDF) learned over a series of video sequence. Then, pixels in video sequence with low probabilities are filtered, taken as foreground moving objects or noises. Finally, a temporal median filter is employed on video sequence, with pixels left. The performance of our framework is evaluated visually and numerically using different metrics on the scene background modeling contest 2016(SBMnet 2016). Results on the SBMnet dataset indicate that the proposed scheme can improve performance, in comparison with the classic temporal median filter to some extend, for background motion and clutter.