Denoising-based Turbo Message Passing for Compressed Video Background Subtraction
This work provides a more efficient and accurate method for compressed video background subtraction, which is beneficial for applications requiring video analysis with limited data or computational resources.
This paper addresses compressed video background subtraction, aiming to separate background and foreground from compressed video measurements. The proposed Denoising-based Turbo Message Passing (DTMP) algorithm successfully performs background subtraction at much lower compression rates, achieving lower mean squared error and better visual quality compared to existing algorithms for both offline and online scenarios.
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.