PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
February 2, 2026Remote Sensing0 citationsOpen Access

TPKE: Automated Keypoint Extraction for Multi-Type Transmission Pylons from LiDAR Point Clouds

View Full Paper
GWGufen WuYGY. N. GaoHLHaibo Liu

Key Points

  • This research introduces TPKE to automate the extraction of keypoints from transmission pylons using LiDAR data.
  • Developed TPKE framework for keypoint extraction from LiDAR point clouds.
  • Implemented adaptive density clustering and a morphological index for insulator positioning.
  • Used local geometric feature analysis for ground wire positioning.
  • Employed semantic segmentation to preprocess complex point clouds.
  • Achieved a mean absolute error (MAE) of 0.0747 m for insulator keypoints.
  • Obtained a mean absolute error (MAE) of 0.0696 m for ground wire points.
  • Maintained centimeter-level accuracy in sparse conditions.
  • Average processing time was 3.03 seconds per tower, showing high efficiency.

Abstract

Automated positioning of transmission tower keypoints is crucial for drone-based intelligent inspection systems. This paper proposes TPKE (Transmission Pylons Keypoint Extraction), a novel framework designed to extract multiple transmission tower keypoints from LiDAR point clouds. The method targets two core components: insulator string endpoints and ground wire hanging points. For insulator positioning, TPKE introduces adaptive density clustering, a morphological “concavity” index (η) for V-shaped insulators, and a “positioning-verification-compensation” strategy for handling missing data. For ground wire positioning, it combines local geometric feature analysis with spatial orthogonal projection. Using semantic segmentation for preprocessing, the framework reliably identifies components from complex transmission corridor point clouds. Validated on 1427 towers across 14 types, TPKE achieves an MAE of 0.0747 m for insulators and 0.0696 m for ground wires. It maintains centimeter-level accuracy even under challenging conditions like sparse point clouds. With an average processing time of 3.03 s per tower, the method demonstrates high efficiency, significantly reducing manual annotation workload while supporting autonomous navigation for transmission line maintenance.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Wu et al. (2026) studied this question.

synapsesocial.com/papers/6980fd81c1c9540dea80f2f0https://doi.org/10.3390/rs18030429
Ask AI
Helpful
Bookmark
Share
View Full Paper