Adaptive Prior Scene-Object SLAM for Dynamic Environments

TL;DR

This paper introduces an adaptive SLAM framework that assesses scene reliability and refines camera pose to improve localization accuracy in dynamic environments with moving objects and abrupt viewpoint changes.

Contribution

It presents a novel reliability assessment method and a pose refinement strategy that together enhance SLAM robustness in dynamic scenes.

Findings

Significant improvement in localization accuracy on TUM RGB-D datasets.

Enhanced robustness of SLAM system in dynamic environments.

Effective mitigation of localization drift caused by moving objects.

Abstract

Visual Simultaneous Localization and Mapping (SLAM) plays a vital role in real-time localization for autonomous systems. However, traditional SLAM methods, which assume a static environment, often suffer from significant localization drift in dynamic scenarios. While recent advancements have improved SLAM performance in such environments, these systems still struggle with localization drift, particularly due to abrupt viewpoint changes and poorly characterized moving objects. In this paper, we propose a novel scene-object-based reliability assessment framework that comprehensively evaluates SLAM stability through both current frame quality metrics and scene changes relative to reliable reference frames. Furthermore, to tackle the lack of error correction mechanisms in existing systems when pose estimation becomes unreliable, we employ a pose refinement strategy that leverages information from reliable frames to optimize camera pose estimation, effectively mitigating the adverse effects of dynamic interference. Extensive experiments on the TUM RGB-D datasets demonstrate that our approach achieves substantial improvements in localization accuracy and system robustness under challenging dynamic scenarios.