MétaCan
Menu
Back to cohort
Record W3212886268 · doi:10.1109/lgrs.2021.3127964

Change Detection Approach for SAR Imagery Based on Arc-Tangential Difference Image and <i>k</i> -Means++

2021· article· en· W3212886268 on OpenAlexaboutno aff
Ümit Haluk Atasever, Mehmet Akıf Günen

Bibliographic record

VenueIEEE Geoscience and Remote Sensing Letters · 2021
Typearticle
Languageen
FieldEngineering
TopicRemote-Sensing Image Classification
Canadian institutionsnot available
Fundersnot available
KeywordsFilter (signal processing)Cluster analysisBackground subtractionSynthetic aperture radarArtificial intelligenceGaussianMathematicsLogarithmHistogramPattern recognition (psychology)Computer scienceImage (mathematics)Computer visionPixelMathematical analysisPhysics

Abstract

fetched live from OpenAlex

In this letter, an unsupervised change detection (CD) approach based on arc-tangential difference and$k$-Means++ clustering is presented for synthetic aperture radar (SAR) remote-sensing images. The images are first standardized with their variance values using a logarithmic function applied to multitemporal images. The difference image (DI) is then calculated by subtracting the SAR images using the arc-tangential subtraction operator. After that, the DI is subjected to a 2-D Gaussian filter and a median filter, respectively. Filters are essential for determining the best feature space for CD. The 2-D Gaussian filter smooths DIs to retain local area consistency, while the median filter handles edge information. Finally, using$k$-Means++, a quick and efficient clustering approach, filtered data is clustered into two classes. Experiments using real-world datasets in Bern, Ottawa, and Yellow River have demonstrated that the given technique is fast, successful, and effective.

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: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.003
Threshold uncertainty score0.006

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0000.001
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0020.002
Science and technology studies0.0010.000
Scholarly communication0.0010.001
Open science0.0010.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0020.001

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 head0.023
GPT teacher head0.219
Teacher spread0.195 · 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

Citations27
Published2021
Admission routes1
Has abstractyes

Explore more

Same venueIEEE Geoscience and Remote Sensing LettersSame topicRemote-Sensing Image ClassificationFrench-language works237,207