Unsupervised Quality Prediction for Improved Single-Frame and Weighted Sequential Visual Place Recognition
This work addresses the need for reliable VPR in safety-critical autonomous systems, though it is incremental as it builds on existing VPR techniques.
The paper tackles the problem of improving the predictability and integrity of Visual Place Recognition (VPR) for autonomous systems by introducing a training-free method to predict localization quality and using it to bias sequence matching, resulting in enhanced precision performance, particularly at high-precision/low-recall operating points across four datasets and three VPR techniques.
While substantial progress has been made in the absolute performance of localization and Visual Place Recognition (VPR) techniques, it is becoming increasingly clear from translating these systems into applications that other capabilities like integrity and predictability are just as important, especially for safety- or operationally-critical autonomous systems. In this research we present a new, training-free approach to predicting the likely quality of localization estimates, and a novel method for using these predictions to bias a sequence-matching process to produce additional performance gains beyond that of a naive sequence matching approach. Our combined system is lightweight, runs in real-time and is agnostic to the underlying VPR technique. On extensive experiments across four datasets and three VPR techniques, we demonstrate our system improves precision performance, especially at the high-precision/low-recall operating point. We also present ablation and analysis identifying the performance contributions of the prediction and weighted sequence matching components in isolation, and the relationship between the quality of the prediction system and the benefits of the weighted sequential matcher.