A Complete System for Automated 3D Semantic-Geometric Mapping of Corrosion in Industrial Environments

TL;DR

This work tackles automatic corrosion detection and 3D mapping in industrial environments by proposing a portable LiDAR‑inertial camera system that fuses LiDAR localization/mapping with vision‑based semantic segmentation to create semantic‑geometric maps. The methodology combines a robust calibration pipeline (camera intrinsics/extrinsics and LiDAR–camera fusion), a U‑Net corrosion segmentation module trained on a pixel‑level annotated offshore dataset, and a dual‑track localization/mapping framework (offline Graph‑SLAM and online UKF with NDT). Key results show indoor localization accuracy with absolute pose errors below $0.05\ \mathrm{m}$ and relative pose errors below $0.02\ \mathrm{m}$, together with approximately $70\%$ segmentation precision on the annotated data, and real‑time capable inference for corrosion masking. The approach enables low‑cost, semi‑autonomous corrosion monitoring suitable for offshore and industrial applications, with potential enhancements including probabilistic semantic fusion and synthetic data augmentation for segmentation.

Abstract

Corrosion, a naturally occurring process leading to the deterioration of metallic materials, demands diligent detection for quality control and the preservation of metal-based objects, especially within industrial contexts. Traditional techniques for corrosion identification, including ultrasonic testing, radio-graphic testing, and magnetic flux leakage, necessitate the deployment of expensive and bulky equipment on-site for effective data acquisition. An unexplored alternative involves employing lightweight, conventional camera systems, and state-of-the-art computer vision methods for its identification. In this work, we propose a complete system for semi-automated corrosion identification and mapping in industrial environments. We leverage recent advances in LiDAR-based methods for localization and mapping, with vision-based semantic segmentation deep learning techniques, in order to build semantic-geometric maps of industrial environments. Unlike previous corrosion identification systems available in the literature, our designed multi-modal system is low-cost, portable, semi-autonomous and allows collecting large datasets by untrained personnel. A set of experiments in an indoor laboratory environment, demonstrate quantitatively the high accuracy of the employed LiDAR based 3D mapping and localization system, with less then $0.05m$ and 0.02m average absolute and relative pose errors. Also, our data-driven semantic segmentation model, achieves around 70\% precision when trained with our pixel-wise manually annotated dataset.

Figures (10)

• Figure 1: Detailed design view of our portable data capture system for 3D semantic-geometric mapping.
• Figure 2: Proposed modular pipeline for semantic-geometric mapping of corrosion in metallic surfaces.
• Figure 3: Main coordinate systems and intrinsic parameters considered by our LiDAR camera system, including the camera coordinate system $\mathcal{C}$, the LiDAR coordinate system $\mathcal{L}$ and the map coordinate system $\mathcal{M}$
• Figure 4: Calibration targets used for intrinsic and extrinsic calibration.
• Figure 5: Reference point estimation using ArUco markers for monocular cameras (left) and edge detection for LiDARs (right).