MétaCan
Menu
Back to cohort

Unsupervised Image Dataset Annotation Framework for Snow Covered Road Networks

2022· article· en· W4364857889 on OpenAlexaffabout
Mohamed Karaa, Hakim Ghazzai, Lokman Sboui, Hichem Besbes, Yehia Massoud

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldEnvironmental Science
TopicSmart Materials for Construction
Canadian institutionsÉcole de Technologie Supérieure
Fundersnot available
KeywordsCluster analysisComputer scienceAnnotationSnowArtificial intelligenceGraphProcess (computing)Snow coverUnsupervised learningFeature (linguistics)Machine learningData miningGeographyMeteorology

Abstract

fetched live from OpenAlex

Road surface condition estimation plays a crucial role in road safety and maintenance, especially in adverse weather conditions like snowfall. In this paper, we introduce a framework for unsupervised annotation of a dataset describing road snow cover level. This framework relies on feature learning using autoencoders and graph clustering using the Louvain community detection algorithm. We also incorporate time and weather data to facilitate the annotation process. We evaluate our method by assessing its different steps and comparing it to another density-based clustering method. We also present a large image dataset describing four road cover states in urban scenes, including different weather and visual conditions. The dataset comprises 41346 images collected from road monitoring cameras installed in Montreal, Canada, during the 2022 winter season. This dataset intends to help integrate computer vision techniques in planning snow removal operations.

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)0.001
metaresearch head score (Gemma)0.004
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: Methods · Consensus signal: Methods
Teacher disagreement score0.021
Threshold uncertainty score0.042

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.004
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0060.004
Science and technology studies0.0010.001
Scholarly communication0.0020.002
Open science0.0030.003
Research integrity0.0020.002
Insufficient payload (model declined to judge)0.0020.002

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 head0.011
GPT teacher head0.242
Teacher spread0.231 · 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
GenreMethods

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

Citations5
Published2022
Admission routes2
Has abstractyes

Explore more

Same topicSmart Materials for ConstructionFrench-language works237,207