# Video Compressive Sensing for Stationary Scene with Lightweight ROI Detection
_by Yang Jian (Hosei Univ Tokyo, Japan) - 2022.11.10_

###### tags: `VAADER` `Seminar`


## Video
{%youtube p6PhBHwIV1E %}

## Abstract
By exploiting the potential of deep learning, video compressive sensing (CS) has achieved tremendous improvement recently. Due to the video CS is mainly served for the fixed scenes in real life. In this paper, we propose a novel video compressive sensing for those stationary scenes (VCSSS). A lightweight region-of-interest (ROI) detection method is utilized in our framework without introducing any additional neural networks and parameters. Subsequently, only the detected ROIs are sampled and transmitted except the frame that is regarded as the background. The final reconstructed sequence would be attained by combining the ROIs and the background. Compared to the state-of-the-art counterparts, extensive experimental results have demonstrated that our proposed methods achieve superior performance while tackling more complex sequences.