Solving Short-Term Relocalization Problems In Monocular Keyframe Visual SLAM Using Spatial And Semantic Data

TL;DR

This paper presents a novel multimodal keyframe descriptor combining semantic and spatial data to improve short-term relocalization in monocular visual SLAM, enabling reliable navigation in GPS-denied environments.

Contribution

It introduces a new multimodal keyframe descriptor and a multi-stage place recognition method for robust short-term relocalization in monocular SLAM systems.

Findings

Accurate pose recovery demonstrated on indoor GPS-denied datasets.

Outperforms traditional bag-of-words approaches.

Enhances SLAM robustness around human collaborators.

Abstract

In Monocular Keyframe Visual Simultaneous Localization and Mapping (MKVSLAM) frameworks, when incremental position tracking fails, global pose has to be recovered in a short-time window, also known as short-term relocalization. This capability is crucial for mobile robots to have reliable navigation, build accurate maps, and have precise behaviors around human collaborators. This paper focuses on the development of robust short-term relocalization capabilities for mobile robots using a monocular camera system. A novel multimodal keyframe descriptor is introduced, that contains semantic information of objects detected in the environment and the spatial information of the camera. Using this descriptor, a new Keyframe-based Place Recognition (KPR) method is proposed that is formulated as a multi-stage keyframe filtering algorithm, leading to a new relocalization pipeline for MKVSLAM systems. The proposed approach is evaluated over several indoor GPS denied datasets and demonstrates accurate pose recovery, in comparison to a bag-of-words approach.