Dynamic Background Subtraction by Generative Neural Networks
This addresses the problem of handling stochastic movements in backgrounds for applications like video surveillance, though it appears incremental as it builds on existing generative approaches.
The paper tackles dynamic background subtraction in computer vision by proposing DBSGen, a method using two generative neural networks for motion removal and background generation, which outperforms most state-of-the-art methods on dynamic background sequences.
Background subtraction is a significant task in computer vision and an essential step for many real world applications. One of the challenges for background subtraction methods is dynamic background, which constitute stochastic movements in some parts of the background. In this paper, we have proposed a new background subtraction method, called DBSGen, which uses two generative neural networks, one for dynamic motion removal and another for background generation. At the end, the foreground moving objects are obtained by a pixel-wise distance threshold based on a dynamic entropy map. The proposed method has a unified framework that can be optimized in an end-to-end and unsupervised fashion. The performance of the method is evaluated over dynamic background sequences and it outperforms most of state-of-the-art methods. Our code is publicly available at https://github.com/FatemeBahri/DBSGen.