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

TL;DR

This paper presents a low-cost, portable, semi-automated 3D mapping system using LiDAR and deep learning for corrosion detection in industrial environments, enabling large-scale data collection by untrained personnel.

Contribution

It introduces a novel multi-modal system combining LiDAR and vision-based deep learning for corrosion mapping, which is low-cost, portable, and semi-autonomous, unlike previous methods.

Findings

LiDAR-based 3D mapping achieves less than 0.05m pose error.

Semantic segmentation model attains around 70% precision.

System effectively collects large datasets in industrial settings.

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.