Autonomous Point Cloud Segmentation for Power Lines Inspection in Smart Grid

TL;DR

This work tackles automatic segmentation of power lines from LiDAR point clouds to enable reliable smart-grid inspection under dense vegetation conditions. It introduces an unsupervised, modular pipeline that begins with high-elevation extraction, proceeds to PCA-based candidate selection using Linear-likeness $LN = \frac{\\lambda_1 - \\lambda_2}{\\lambda_1}$, applies a two-stage DBSCAN clustering, and then performs parametric modeling with a catenary curve $y(x) = a + c \cosh(\frac{x-b}{c})$ (and a quadratic approximation $y(x) = a_2 x^2 + a_1 x + a_0$) with MSAC outlier rejection. The PLC is extracted via Kd-tree with an adaptive search radius $r$ defined as $r = \max \{\\Delta z, d_i\\}$ for complex environments or $r = \max \{a_0\\}$ otherwise, and hyperparameters are optimized through grid search to suit different datasets. The approach is XAI-friendly, does not require labeled data, and demonstrates competitive runtime performance against trained baselines, enabling autonomous, frequent PLC surveillance and vegetation hazard analysis in smart grids. The combination of DBSCAN-based segmentation, geometry-driven modeling, and adaptive PLC extraction provides a practical pathway toward scalable, explainable, and maintenance-friendly power line inspection.

Abstract

LiDAR is currently one of the most utilized sensors to effectively monitor the status of power lines and facilitate the inspection of remote power distribution networks and related infrastructures. To ensure the safe operation of the smart grid, various remote data acquisition strategies, such as Airborne Laser Scanning (ALS), Mobile Laser Scanning (MLS), and Terrestrial Laser Scanning (TSL) have been leveraged to allow continuous monitoring of regional power networks, which are typically surrounded by dense vegetation. In this article, an unsupervised Machine Learning (ML) framework is proposed, to detect, extract and analyze the characteristics of power lines of both high and low voltage, as well as the surrounding vegetation in a Power Line Corridor (PLC) solely from LiDAR data. Initially, the proposed approach eliminates the ground points from higher elevation points based on statistical analysis that applies density criteria and histogram thresholding. After denoising and transforming of the remaining candidate points by applying Principle Component Analysis (PCA) and Kd-tree, power line segmentation is achieved by utilizing a two-stage DBSCAN clustering to identify each power line individually. Finally, all high elevation points in the PLC are identified based on their distance to the newly segmented power lines. Conducted experiments illustrate that the proposed framework is an agnostic method that can efficiently detect the power lines and perform PLC-based hazard analysis.

Figures (6)

• Figure 1: Left: Extracted power lines from the LiDAR data. Right: Extracted power line corridor.
• Figure 2: The schematics of the proposed pipeline for extraction of power lines and Power Line Corridor (PLC).
• Figure 3: Aerial system for power line inspection.
• Figure 4: Autonomous inspection of power line with UAV.
• Figure 5: 3D Point Cloud map of the inspected area.