MétaCan
Menu
← Back to cohort
Record W4412022655 · doi:10.1177/03611981251338725

Understanding the Effects of Point Cloud Density on Automated Traffic Sign Change Detection Using Lidar Technology

2025· article· en· W4412022655 on OpenAlexaff
Ahmed Khataan, Suliman Gargoum

Bibliographic record

VenueTransportation Research Record Journal of the Transportation Research Board · 2025
Typearticle
Languageen
FieldEnvironmental Science
TopicRemote Sensing and LiDAR Applications
Canadian institutionsUniversity of British Columbia
Fundersnot available
KeywordsLidarPoint cloudCloud computingRemote sensingChange detectionSign (mathematics)Computer scienceArtificial intelligenceEnvironmental scienceGeographyMathematics

Abstract

fetched live from OpenAlex

Change detection is the process of identifying variations in roadway asset conditions and flagging them for timely repair or replacement. This practice is crucial for maintaining road safety and infrastructure integrity but is highly time-consuming. Automating change detection with mobile lidar technology has been considered by many agencies, but the cost of high-resolution lidar is a significant burden. Although low-cost lidar is available, it is not clear whether the point cloud density from such systems is sufficient for accurate change detection. We addressed this gap by conducting a sensitivity analysis on the effect of varying mobile lidar point densities on the accuracy of traffic sign change detection. The assessment involved randomly simulating changes (e.g., damage) in traffic signs, then subsampling the point cloud to different densities. A machine learning algorithm was used to detect changes at these densities. Additionally, a logistic regression model was used to statistically assess the relationship between point density, traffic sign size, and change detection accuracy using data from over 130 traffic signs across three highways. Results show that point densities above 250 points/m 2 yield F1 scores and detection rates exceeding 95% for both partial breakage and rotational changes, establishing a critical threshold for high detection accuracy. The study revealed that both point density and change magnitude are significant predictors of detection accuracy, with traffic sign size being significant for partial breakage changes. This paper also highlights the effect of change size per unit area on detection precision, offering broader insights for road infrastructure maintenance.

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)0.006
metaresearch head score (Gemma)0.044
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.016
Threshold uncertainty score0.031

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0060.044
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0000.001
Bibliometrics0.0010.001
Science and technology studies0.0000.001
Scholarly communication0.0010.003
Open science0.0010.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0010.000

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 head0.096
GPT teacher head0.358
Teacher spread0.263 · 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 designSimulation or modeling
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

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueTransportation Research Record Journal of the Transportation Research Board→Same topicRemote Sensing and LiDAR Applications→French-language works237,207→