Learning dynamic background for weakly supervised moving object detection

作者：

Highlights：

• A novel video decomposition framework, additionally modeling the dynamic clutter explicitly.

• A unified tensor-based framework to capture the appearance and motion information simultaneously for three components.

• A self-supervised strategy to learn the dynamic clutter well by considering the video sequence itself as a dataset.

• Bridge the gap between discriminative prior and the low-rank MAP framework.

摘要

•A novel video decomposition framework, additionally modeling the dynamic clutter explicitly.•A unified tensor-based framework to capture the appearance and motion information simultaneously for three components.•A self-supervised strategy to learn the dynamic clutter well by considering the video sequence itself as a dataset.•Bridge the gap between discriminative prior and the low-rank MAP framework.

论文关键词：Moving object detection,Dynamic background,Data-driven discriminative prior,Low-rank framework

论文评审过程：Received 17 December 2021, Revised 26 February 2022, Accepted 28 February 2022, Available online 8 March 2022, Version of Record 15 March 2022.

论文官网地址：https://doi.org/10.1016/j.imavis.2022.104425