Delta Descriptors: Change-Based Place Representation for Robust Visual Localization

TL;DR

This paper introduces Delta Descriptors, a novel change-based place representation method that improves visual localization robustness by tracking temporal differences in learned descriptors, achieving state-of-the-art results when combined with sequence matching.

Contribution

The paper proposes Delta Descriptors, a new unsupervised change-based descriptor that enhances visual localization robustness across varying conditions and demonstrates superior performance with multiple descriptor types.

Findings

Delta Descriptors outperform existing methods in benchmark tests.

Combining Delta Descriptors with sequence matching yields state-of-the-art results.

The approach is robust to camera motion variations and dimensionality reduction.

Abstract

Visual place recognition is challenging because there are so many factors that can cause the appearance of a place to change, from day-night cycles to seasonal change to atmospheric conditions. In recent years a large range of approaches have been developed to address this challenge including deep-learnt image descriptors, domain translation, and sequential filtering, all with shortcomings including generality and velocity-sensitivity. In this paper we propose a novel descriptor derived from tracking changes in any learned global descriptor over time, dubbed Delta Descriptors. Delta Descriptors mitigate the offsets induced in the original descriptor matching space in an unsupervised manner by considering temporal differences across places observed along a route. Like all other approaches, Delta Descriptors have a shortcoming - volatility on a frame to frame basis - which can be overcome by combining them with sequential filtering methods. Using two benchmark datasets, we first demonstrate the high performance of Delta Descriptors in isolation, before showing new state-of-the-art performance when combined with sequence-based matching. We also present results demonstrating the approach working with four different underlying descriptor types, and two other beneficial properties of Delta Descriptors in comparison to existing techniques: their increased inherent robustness to variations in camera motion and a reduced rate of performance degradation as dimensional reduction is applied. Source code is made available at https://github.com/oravus/DeltaDescriptors.