S3LAM: Structured Scene SLAM

TL;DR

S3LAM introduces a semantic SLAM system that leverages object and structure segmentation to enhance localization accuracy and scene understanding by integrating semantic clusters and geometrical priors into the SLAM process.

Contribution

It presents a novel semantic SLAM system based on ORB-SLAM2 with a new clustering approach and modified bundle adjustment for improved accuracy and scene comprehension.

Findings

Improves camera pose estimation over state-of-the-art methods

Creates semantic maps with object and structure clusters

Enhances scene understanding through geometrical priors

Abstract

We propose a new SLAM system that uses the semantic segmentation of objects and structures in the scene. Semantic information is relevant as it contains high level information which may make SLAM more accurate and robust. Our contribution is twofold: i) A new SLAM system based on ORB-SLAM2 that creates a semantic map made of clusters of points corresponding to objects instances and structures in the scene. ii) A modification of the classical Bundle Adjustment formulation to constrain each cluster using geometrical priors, which improves both camera localization and reconstruction and enables a better understanding of the scene. We evaluate our approach on sequences from several public datasets and show that it improves camera pose estimation with respect to state of the art.