Long-Term Visual Localization in Dynamic Benthic Environments: A Dataset, Footprint-Based Ground Truth, and Visual Place Recognition Benchmark

TL;DR

This paper introduces a new underwater dataset, a ground-truthing method, and benchmarks for long-term visual localization in benthic environments, addressing the lack of curated data and precise ground-truthing techniques.

Contribution

It provides the first curated underwater dataset for long-term visual localization across multiple sites and habitats, along with a novel footprint-based ground-truthing method and comprehensive benchmarking.

Findings

Recall@K is significantly lower on this dataset than on terrestrial benchmarks.

Traditional location-based ground-truthing can overestimate VPR performance in rugged terrains.

The new dataset enables more accurate evaluation of visual localization methods in underwater environments.

Abstract

Long-term visual localization has the potential to reduce cost and improve mapping quality in optical benthic monitoring with autonomous underwater vehicles (AUVs). Despite this potential, long-term visual localization in benthic environments remains understudied, primarily due to the lack of curated datasets for benchmarking. Moreover, limited georeferencing accuracy and image footprints necessitate precise geometric information for accurate ground-truthing. In this work, we address these gaps by presenting a curated dataset for long-term visual localization in benthic environments and a novel method to ground-truth visual localization results for near-nadir underwater imagery. Our dataset comprises georeferenced AUV imagery from five benthic reference sites, revisited over periods up to six years, and includes raw and color-corrected stereo imagery, camera calibrations, and sub-decimeter registered camera poses. To our knowledge, this is the first curated underwater dataset for long-term visual localization spanning multiple sites and photic-zone habitats. Our ground-truthing method estimates 3D seafloor image footprints and links camera views with overlapping footprints, ensuring that ground-truth links reflect shared visual content. Building on this dataset and ground truth, we benchmark eight state-of-the-art visual place recognition (VPR) methods and find that Recall@K is significantly lower on our dataset than on established terrestrial and underwater benchmarks. Finally, we compare our footprint-based ground truth to a traditional location-based ground truth and show that distance-threshold ground-truthing can overestimate VPR Recall@K at sites with rugged terrain and altitude variations. Together, the curated dataset, ground-truthing method, and VPR benchmark provide a stepping stone for advancing long-term visual localization in dynamic benthic environments.