CANDID: Robust Change Dynamics and Deterministic Update Policy for Dynamic Background Subtraction

TL;DR

CANDID introduces an adaptive, deterministic approach for background subtraction in videos, effectively handling dynamic backgrounds and extreme weather, outperforming existing methods in challenging scenarios.

Contribution

The paper presents a novel adaptive and deterministic background subtraction method that dynamically updates parameters based on change detection, improving robustness in complex environments.

Findings

Outperforms state-of-the-art methods in dynamic backgrounds

Effective under extreme weather conditions

Provides both qualitative and quantitative improvements

Abstract

Background subtraction in video provides the preliminary information which is essential for many computer vision applications. In this paper, we propose a sequence of approaches named CANDID to handle the change detection problem in challenging video scenarios. The CANDID adaptively initializes the pixel-level distance threshold and update rate. These parameters are updated by computing the change dynamics at a location. Further, the background model is maintained by formulating a deterministic update policy. The performance of the proposed method is evaluated over various challenging scenarios such as dynamic background and extreme weather conditions. The qualitative and quantitative measures of the proposed method outperform the existing state-of-the-art approaches.