MétaCan
Menu
Back to cohort
Record W4390659862 · doi:10.1109/jsen.2023.3348785

Identifying Areas of High-Risk Vegetation Encroachment on Electrical Powerlines Using Mobile and Airborne Laser Scanned Point Clouds

2024· article· en· W4390659862 on OpenAlexafffund
Aziz Al-Najjar, Marzieh Amini, Sreeraman Rajan, James R. Green

Bibliographic record

VenueIEEE Sensors Journal · 2024
Typearticle
Languageen
FieldEnvironmental Science
TopicRemote Sensing and LiDAR Applications
Canadian institutionsCarleton University
FundersNatural Resources Canada
KeywordsPoint cloudRemote sensingLidarVegetation (pathology)Computer scienceLeverage (statistics)Laser scanningRandom forestArtificial intelligenceEnvironmental scienceGeographyLaser

Abstract

fetched live from OpenAlex

Powerline vegetation encroachment detection is pivotal in averting power outages and forest fires, especially in urban areas where a high density of buildings, roads, and other urban structures complicates detection. While prior research has effectively detected encroachments within point clouds, they largely overlooked the challenges posed by urban environments and did not leverage publicly available urban datasets. These urban intricacies can hinder the precise classification of powerline and vegetation points. This paper proposes a two-stage method for accurately and automatically detecting vegetation encroachment on urban powerlines. The first stage classifies the points in the point cloud as either belonging to one of three classes of points: vegetation, powerlines or background. The classifier model in this stage is chosen based on a comparative analysis of two deep learning models, PointCNN and RandLA-Net. The second stage detects encroachment areas from the detected vegetation and powerline points using a novel Point-Based Encroachment Detection (P-BED) algorithm. This algorithm identifies encroachment areas with high precision using the following steps: sectioning the map, selecting informative sections in the map, voxel-based down-sampling of points in point cloud, and conducting proximity analysis between vegetation and powerlines voxels. The proposed methodology was trained and tested with two publicly available datasets namely, mobile laser-scanned (MLS) and airborne laser-scanned (ALS) datasets. The first stage achieves an F1-scores of 0.98 for classifying background and 0.96 and 0.94 for classifying vegetation and powerline points, respectively. The newly proposed P-BED method successfully detected encroachments with 100% precision and 96.0% recall, showcasing its potential for improved vegetation management and proactive maintenance in urban settings.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.001
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.021
Threshold uncertainty score0.041

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0000.001
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0000.001
Bibliometrics0.0020.002
Science and technology studies0.0000.000
Scholarly communication0.0010.001
Open science0.0010.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0010.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.012
GPT teacher head0.264
Teacher spread0.252 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designObservational
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations10
Published2024
Admission routes2
Has abstractyes

Explore more

Same venueIEEE Sensors JournalSame topicRemote Sensing and LiDAR ApplicationsFrench-language works237,207