Object-Augmented RGB-D SLAM for Wide-Disparity Relocalisation

TL;DR

This paper introduces an object-augmented RGB-D SLAM system that improves relocalisation accuracy across wide viewpoints by leveraging object detection, pose estimation, and probabilistic matching, outperforming traditional appearance-based methods.

Contribution

The novel system integrates object detection and pose estimation with probabilistic mapping and matching to enhance relocalisation in RGB-D SLAM, especially under wide viewpoint variations.

Findings

High success rates in relocalisation across different viewpoints

Significant outperforming of appearance-based methods

Effective object map construction and matching

Abstract

We propose a novel object-augmented RGB-D SLAM system that is capable of constructing a consistent object map and performing relocalisation based on centroids of objects in the map. The approach aims to overcome the view dependence of appearance-based relocalisation methods using point features or images. During the map construction, we use a pre-trained neural network to detect objects and estimate 6D poses from RGB-D data. An incremental probabilistic model is used to aggregate estimates over time to create the object map. Then in relocalisation, we use the same network to extract objects-of-interest in the `lost' frames. Pairwise geometric matching finds correspondences between map and frame objects, and probabilistic absolute orientation followed by application of iterative closest point to dense depth maps and object centroids gives relocalisation. Results of experiments in desktop environments demonstrate very high success rates even for frames with widely different viewpoints from those used to construct the map, significantly outperforming two appearance-based methods.