Direction-Aware Semi-Dense SLAM

TL;DR

This paper introduces a novel direction-aware semi-dense SLAM system that integrates scene understanding with real-time camera tracking, enhancing accuracy and efficiency through a joint probabilistic model.

Contribution

It is the first to combine direction-aware scene segmentation with semi-dense SLAM, using a Bayesian nonparametric prior and CRF for improved localization and mapping.

Findings

Enhanced SLAM accuracy over previous methods

Improved tracking efficiency through scene-guided observation

State-of-the-art performance demonstrated

Abstract

To aide simultaneous localization and mapping (SLAM), future perception systems will incorporate forms of scene understanding. In a step towards fully integrated probabilistic geometric scene understanding, localization and mapping we propose the first direction-aware semi-dense SLAM system. It jointly infers the directional Stata Center World (SCW) segmentation and a surfel-based semi-dense map while performing real-time camera tracking. The joint SCW map model connects a scene-wide Bayesian nonparametric Dirichlet Process von-Mises-Fisher mixture model (DP-vMF) prior on surfel orientations with the local surfel locations via a conditional random field (CRF). Camera tracking leverages the SCW segmentation to improve efficiency via guided observation selection. Results demonstrate improved SLAM accuracy and tracking efficiency at state of the art performance.