Denoising-based Turbo Message Passing for Compressed Video Background Subtraction

TL;DR

This paper introduces a denoising-based turbo message passing algorithm for efficient compressed video background subtraction, capable of handling both offline and online data with improved accuracy at lower compression rates.

Contribution

The paper develops a novel DTMP algorithm that leverages structural properties of video data within a turbo message passing framework, extending it to online processing with optical flow and sliding window techniques.

Findings

DTMP outperforms existing algorithms at lower compression rates.

It achieves lower mean squared error in background subtraction.

Provides better visual quality in both offline and online scenarios.

Abstract

In this paper, we consider the compressed video background subtraction problem that separates the background and foreground of a video from its compressed measurements. The background of a video usually lies in a low dimensional space and the foreground is usually sparse. More importantly, each video frame is a natural image that has textural patterns. By exploiting these properties, we develop a message passing algorithm termed offline denoising-based turbo message passing (DTMP). We show that these structural properties can be efficiently handled by the existing denoising techniques under the turbo message passing framework. We further extend the DTMP algorithm to the online scenario where the video data is collected in an online manner. The extension is based on the similarity/continuity between adjacent video frames. We adopt the optical flow method to refine the estimation of the foreground. We also adopt the sliding window based background estimation to reduce complexity. By exploiting the Gaussianity of messages, we develop the state evolution to characterize the per-iteration performance of offline and online DTMP. Comparing to the existing algorithms, DTMP can work at much lower compression rates, and can subtract the background successfully with a lower mean squared error and better visual quality for both offline and online compressed video background subtraction.