Self-Supervised Domain Calibration and Uncertainty Estimation for Place Recognition

Abstract

Visual place recognition techniques based on deep learning, which have imposed themselves as the state-of-the-art in recent years, do not generalize well to environments visually different from the training set. Thus, to achieve top performance, it is sometimes necessary to fine-tune the networks to the target environment. To this end, we propose a self-supervised domain calibration procedure based on robust pose graph optimization from Simultaneous Localization and Mapping (SLAM) as the supervision signal without requiring GPS or manual labeling. Moreover, we leverage the procedure to improve uncertainty estimation for place recognition matches which is important in safety critical applications. We show that our approach can improve the performance of a state-of-the-art technique on a target environment dissimilar from its training set and that we can obtain uncertainty estimates. We believe that this approach will help practitioners to deploy robust place recognition solutions in real-world applications. Our code is available publicly: https://github.com/MISTLab/vpr-calibration-and-uncertainty

References in corpus (7)

• RTAB-Map as an Open-Source Lidar and Visual SLAM Library for Large-Scale and Long-Term Online Operation
• Where is your place, Visual Place Recognition?
• Towards Collaborative Simultaneous Localization and Mapping: a Survey of the Current Research Landscape
• DASGIL: Domain Adaptation for Semantic and Geometric-aware Image-based Localization
• Generalized Contrastive Optimization of Siamese Networks for Place Recognition
• Graph-based non-linear least squares optimization for visual place recognition in changing environments
• Self-Supervised Visual Place Recognition Learning in Mobile Robots

Cited by in corpus (4)

• Swarm-SLAM : Sparse Decentralized Collaborative Simultaneous Localization and Mapping Framework for Multi-Robot Systems
• VIPeR: Visual Incremental Place Recognition with Adaptive Mining and Continual Learning
• Self-Supervised Place Recognition by Refining Temporal and Featural Pseudo Labels from Panoramic Data
• Development and Adaptation of Robotic Vision in the Real-World: the Challenge of Door Detection