MétaCan
Menu
Back to cohort
Record W2059644815 · doi:10.1109/jstars.2014.2387374

A New Method for Land Cover Characterization and Classification of Polarimetric SAR Data Using Polarimetric Signatures

2015· article· en· W2059644815 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

fundA Canadian funder is recorded on the work.
no affNo Canadian affiliation: this work is invisible to an affiliation-only frame.
No Canadian affiliation. An affiliation-only frame, the usual design, would never have seen this work. It is one of the works that make the case for inverting the frame.

Bibliographic record

VenueIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · 2015
Typearticle
Languageen
FieldEngineering
TopicSynthetic Aperture Radar (SAR) Applications and Techniques
Canadian institutionsnot available
FundersCanadian Forest ServiceCanadian Space AgencyUniversity of Glasgow
KeywordsPolarimetryWishart distributionLand coverRemote sensingSynthetic aperture radarComputer sciencePattern recognition (psychology)Covariance matrixContextual image classificationArtificial intelligenceScatteringGeographyAlgorithmMachine learningLand usePhysicsImage (mathematics)

Abstract

fetched live from OpenAlex

Conventional methods for analyzing polarimetric synthetic aperture RADAR (PolSAR) data such as scattering matrix show polarimetric information just in a restricted number of polarization bases, whereas backscattering of the targets has information on wide range of polarizations. In order to solve this problem, polarimetric signatures have been investigated to have a better illustration of the target responses. Polarimetric signatures depict more details of physical information from target backscattering in various polarization bases. This paper presents a new method for generating polarimetric signatures for different features in PolSAR data by changing the polarization basis in the covariance matrix. Furthermore, various land cover classes were evaluated using their polarimetric signatures and the pattern recognition matching methods. On the basis of this background, an object-oriented and knowledge-based classification algorithm is proposed. The main idea of this method is to apply polarimetric signatures of various PolSAR features in the land cover classification. A Radarsat-2 image, acquired in leaf-off season of the forest areas, was chosen for this study. The backscattering from different classes, including six land cover classes: 1) red oak (Or); 2) white pine (Pw); 3) black spruce (Sb); 4) urban (Ur); 5) water (Wa); and 6) ground vegetation (GV) was analyzed by the proposed method. The results reported that the polarimetric signatures of PolSAR features introduce new concepts for the various targets which are different from the polarimetric power signatures. Also, the proposed classification was compared with the object-based form of the supervised Wishart classification as the baseline method. The mean accuracy of the proposed method is 6% better than the supervised Wishart classification.

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.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation 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 score0.882
Threshold uncertainty score0.430

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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 head0.063
GPT teacher head0.292
Teacher spread0.229 · 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