D2SLAM: Semantic visual SLAM based on the Depth-related influence on object interactions for Dynamic environments

TL;DR

This paper introduces D2SLAM, a semantic visual SLAM method that leverages depth information to better handle dynamic environments, improving localization accuracy by modeling object interactions and scene dynamics.

Contribution

The novel integration of depth data with semantic and geometric modules enhances dynamic scene understanding and SLAM accuracy in unknown, changing environments.

Findings

Outperforms state-of-the-art on TUM-RGBD dataset

Improves localization accuracy in dynamic environments

Effectively models object interactions using depth information

Abstract

Considering the scene's dynamics is the most effective solution to obtain an accurate perception of unknown environments for real vSLAM applications. Most existing methods attempt to address the non-rigid scene assumption by combining geometric and semantic approaches to determine dynamic elements that lack generalization and scene awareness. We propose a novel approach that overcomes these limitations by using scene-depth information to improve the accuracy of the localization from geometric and semantic modules. In addition, we use depth information to determine an area of influence of dynamic objects through an Object Interaction Module that estimates the state of both non-matched and non-segmented key points. The obtained results on TUM-RGBD dataset clearly demonstrate that the proposed method outperforms the state-of-the-art.