Indicating Ambiguous False Positives to Improve Wide-Area SAR Vessel Detection
Bibliographic record
Abstract
Automatic vessel detection based on wide-area synthetic aperture radar (SAR) imagery is achieved via a statistical hypothesis test in which a ship is declared detected when the pixel intensity exceeds a predetermined threshold. Inherent to the physical principle of SAR as a pulsed radar system, not only legitimate vessels are detected but also ambiguous reflections caused by the periodic sampling of the scene. These ambiguous returns occur in both directions, azimuth and range, and can originate at land or ships. Depending on the chosen beam mode and system parameters, many also exceed the threshold and can severely degrade the overall performance quality. In the literature, several elaborate technological and signal-processing techniques were proposed to either entirely avoid the emerging of ambiguities or at least suppress them significantly. While hardware-based solutions are not readily available on existing spacecraft and potentially cost prohibitive on future ones, most processing algorithms are computationally too laborious for near real-time applications. This article presents an alternative solution. As SAR-based ship detection is not about creating neat imagery, ambiguities may be tolerated as long as they can be reliably identified as such during a follow-on examination. This step is being proposed to be a novel additional statistical test that decides which hypothesis (vessel or ambiguity probability) was more likely to have generated the prior detected pixel cluster. The effectiveness of the method is shown theoretically and corroborated with real RADARSAT Constellation Mission (RCM) data.
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 | 0.005 | 0.022 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 0.002 |
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.
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".