A Compound-Plus-Noise Model for Improved Vessel Detection in Non-Gaussian SAR Imagery
Bibliographic record
Abstract
The commonly applied K-distribution to model the synthetic aperture radar image amplitude of the heterogeneous (non-Gaussian) sea surface as the basis for vessel detection has shown deficiencies in practical cases, particularly for space-based systems. Due to a deviation between the K-probability density function and measured histograms in the tails, even the inclusion of thermal noise is oftentimes not sufficient to cover the range of environments that are expected. As a consequence, virtually all detectors try to reduce the large number of obtained false detections by relying on rather heuristic postprocessing steps. Consequently, they forfeit the crucial property of a constant false alarm rate. This paper proposes a novel statistical sea clutter model that describes the data more accurately, especially in challenging environments and thermal-noise limited cases. This new model stands out through its numerical simplicity, permitting efficient parameter adaptation thereby enhancing robustness and reducing computational complexity. Accordingly, the presented sea data model has the potential to replace the widely adopted K-distribution as model of choice for future operational applications.
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 | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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.
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".