Det-SLAM: A semantic visual SLAM for highly dynamic scenes using Detectron2

TL;DR

Det-SLAM integrates semantic segmentation with visual SLAM to effectively handle highly dynamic scenes, improving robustness and accuracy in indoor environments with moving objects.

Contribution

This paper introduces Det-SLAM, a novel system combining ORB-SLAM3 and Detectron2 for dynamic scene understanding using depth and semantic segmentation.

Findings

Det-SLAM outperforms previous dynamic SLAM systems in resilience.

It reduces camera pose estimation errors in dynamic indoor scenarios.

The system effectively identifies and removes dynamic objects using semantic segmentation.

Abstract

According to experts, Simultaneous Localization and Mapping (SLAM) is an intrinsic part of autonomous robotic systems. Several SLAM systems with impressive performance have been invented and used during the last several decades. However, there are still unresolved issues, such as how to deal with moving objects in dynamic situations. Classic SLAM systems depend on the assumption of a static environment, which becomes unworkable in highly dynamic situations. Several methods have been presented to tackle this issue in recent years, but each has its limitations. This research combines the visual SLAM systems ORB-SLAM3 and Detectron2 to present the Det-SLAM system, which employs depth information and semantic segmentation to identify and eradicate dynamic spots to accomplish semantic SLAM for dynamic situations. Evaluation of public TUM datasets indicates that Det-SLAM is more resilient than previous dynamic SLAM systems and can lower the estimated error of camera posture in dynamic indoor scenarios.