Visual-Lidar Map Alignment for Infrastructure Inspections

TL;DR

This paper presents a novel visual-lidar map alignment algorithm that improves infrastructure inspection accuracy and efficiency by enabling automatic alignment of 3D maps from repeated inspections in GPS-denied environments.

Contribution

It introduces a versatile map alignment method combining visual and lidar data, and provides a new dataset for consecutive infrastructure inspections, enhancing long-term asset monitoring.

Findings

Enhanced place recognition robustness

Supports automatic multi-session map alignment

Facilitates long-term infrastructure monitoring

Abstract

Routine and repetitive infrastructure inspections present safety, efficiency, and consistency challenges as they are performed manually, often in challenging or hazardous environments. They can also introduce subjectivity and errors into the process, resulting in undesirable outcomes. Simultaneous localization and mapping (SLAM) presents an opportunity to generate high-quality 3D maps that can be used to extract accurate and objective inspection data. Yet, many SLAM algorithms are limited in their ability to align 3D maps from repeated inspections in GPS-denied settings automatically. This limitation hinders practical long-term asset health assessments by requiring tedious manual alignment for data association across scans from previous inspections. This paper introduces a versatile map alignment algorithm leveraging both visual and lidar data for improved place recognition robustness and presents an infrastructure-focused dataset tailored for consecutive inspections. By detaching map alignment from SLAM, our approach enhances infrastructure inspection pipelines, supports monitoring asset degradation over time, and invigorates SLAM research by permitting exploration beyond existing multi-session SLAM algorithms.