Visual-Lidar Map Alignment for Infrastructure Inspections

2025-01-24

AI Summary

In GPS-denied environments, automated alignment of multi-temporal 3D point cloud maps for infrastructure periodic inspection remains challenging—hindering long-term asset health assessment. To address this, we propose a SLAM-decoupled, vision–LiDAR cross-modal joint alignment algorithm that synergistically integrates robust visual feature matching with LiDAR geometric constraints, enabling reliable registration under weak-texture conditions and large viewpoint variations. We introduce the first dedicated benchmark dataset for continuous infrastructure inspection. Our method requires no GPS priors and achieves sub-meter (<0.5 m) automatic inter-epoch point cloud registration, reducing alignment time by over 90%. It further enables millimeter-level structural deformation analysis across time series. Key innovations include a SLAM-free map alignment paradigm and a cross-modal co-optimization mechanism that jointly refines visual correspondences and geometric consistency.

Technology Category

• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics

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.

Problem

• Infrastructure Inspection
• SLAM Technology
• GPS-denied Environment

Innovation

• Visual-LiDAR Integration
• Decoupled Map Alignment
• Infrastructure Monitoring Dataset