Methods for the Segmentation of Reticular Structures Using 3D LiDAR Data: A Comparative Evaluation

TL;DR

This paper compares analytical and deep learning methods for segmenting navigable surfaces in 3D LiDAR point clouds of metallic truss structures, aiming to improve autonomous robot navigation for infrastructure inspection.

Contribution

It introduces and evaluates both analytical and deep learning approaches for binary segmentation of truss structures, highlighting their trade-offs and performance in autonomous navigation tasks.

Findings

Analytical algorithm performs comparably to deep learning models in segmentation accuracy.

PointTransformerV3 achieves approximately 97% mIoU in segmentation.

Deep learning models are more computationally intensive but more accurate.

Abstract

Reticular structures form the backbone of major infrastructure like bridges, pylons, and airports, but their inspection and maintenance are costly and hazardous, often requiring human intervention. While prior research has focused on fault detection via images or robotic platform design, the autonomous navigation of robots within these structures is less explored. This study addresses that gap by proposing methods to detect navigable surfaces in truss structures, enhancing the autonomy of climbing robots. The paper introduces several approaches for binary segmentation of navigable surfaces versus background from 3D point clouds of metallic trusses. These methods fall into two categories: analytical algorithms and deep learning models. The analytical approach features a custom algorithm that segments structures by analyzing the eigendecomposition of planar patches in the point cloud. In parallel, advanced deep learning models PointNet, PointNet++, MinkUNet34C, and PointTransformerV3 are trained and evaluated for the same task. Comparative analysis shows that the analytical algorithm offers easier parameter tuning and performance comparable to deep learning models, which, while more computationally intensive, excel in segmentation accuracy. Notably, PointTransformerV3 achieves a Mean Intersection Over Union (mIoU) of about 97%. The study demonstrates the promise of both analytical and deep learning methods for improving autonomous navigation in complex truss environments. The results highlight the trade-offs between computational efficiency and segmentation performance, providing valuable guidance for future research and practical applications in autonomous infrastructure inspection and maintenance.