Evaluation of Polarimetric SAR Despeckling Methods for Crop Classification from RCM Compact Polarimetry Data
Bibliographic record
Abstract
Abstract. The presence of speckle in RADARSAT Constellation Mission (RCM) Compact Polarimetry (CP) Synthetic Aperture Radar (SAR) images can impair the performance of information extraction applications such as classification. Therefore, a critical preprocessing step known as despeckling is necessary to mitigate this granular, noise-like phenomenon in these images. This paper compared several PolSAR speckle reduction methods, including Box Car, IDAN, Lee Refined, Lee Sigma, Improved Lee Sigma, and Lopez filters. A CP SAR dataset collected over agricultural land in southern Quebec, QC, Canada, was utilized for the study. The assessment of despeckling was based on various no-reference quantitative indicators. Each despeckling method was evaluated for its effectiveness in reducing speckle in homogeneous areas, preserving details, and avoiding radiometric distortion. Additionally, the impact of despeckling on the classification of this agricultural land was assessed using the Random Forest classifier. The Stokes parameters, m-chi decomposition, and intensity images were utilized for this purpose. Experimental results indicated that the Box Car method excelled in speckle suppression at the expense of edge over-smoothing. Furthermore, the Lee Sigma and Improved Lee Sigma methods were the most effective in speckle reduction from homogeneous areas while preserving edges and preventing radiometric distortion. Moreover, the classification results demonstrated that appropriate despeckling could significantly enhance classification accuracy.
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 imitationNot 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.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".