Amos-SLAM: An Anti-Dynamics Two-Stage RGB-D SLAM Approach

The traditional simultaneous localization and mapping (SLAM) systems rely on the assumption of a static environment and fail to accurately estimate the system's location when dynamic objects are present in the background. While learning-based dynamic SLAM systems have difficulties in handling unknown moving objects, geometry-based methods have limited success in addressing the residual effects of unidentified dynamic objects on location estimation. To address these issues, we propose an anti-dynamics two-stage RGB-D SLAM approach. In the first stage, we identify potential motion regions for both known and unknown dynamic objects and rapidly generate pose estimates through optical flow tracking and model generation techniques. In the second stage, dynamic features within each frame are eliminated through dynamic assessment. For unidentified dynamic objects, we propose an approach involving superpixel extraction and geometric clustering to delineate potential motion regions based on color and geometric cues within the image. We conducted extensive experiments using public datasets and real-world scenarios, which demonstrated that our method surpasses current state-of-the-art (SOTA) dynamic SLAM techniques on public datasets. Our method's robustness was also confirmed through experiments in real scenes featuring objects moving at varying speeds.