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.
Bibliographic record
Abstract
Maritime surveillance is an issue of particular interest and importance for countries bordering on the sea. Monitoring and controlling maritime activities are essential for these countries to assert their sovereignty over their waters. Ship detection is one of the most vital elements of maritime control. Traditional surveillance methods suffer from narrow coverage and high cost to achieve comprehensive surveillance. However, Synthetic Aperture Radar (SAR) with its ability to provide images covering wide geographic areas and acquired with a variety of imaging modes, polarization configurations, incidence angles and resolutions may be considered as a promising alternative/complement for existing methods. Quad-polarimetric SAR data has been used successfully for ship detection. However, narrow swath of quad-polarimetric SAR promotes the urgent need to explore ship detectors for dual-polarimetric systems. Compact polarimetric (CP) SAR has high potential of providing more information than linear dual-polarimetric SAR. Even wider swaths will be provided in many of the CP imaging modes of the upcoming Canadian Radarsat Constellation Mission (RCM) SAR to be launched in 2018. In this thesis, the use of CP SAR for ship detection is explored. To fulfill this purpose, two novel contributions are introduced. The first is an investigation study of the possibility and benefits of using pseudo-quad data for improved ship detection. This is achieved by comparing the ship detection performance of dual-polarized CP and pseudo-quad data to linear and circular dual-polarized SAR. The pseudo-quad data is generated by a reconstruction algorithm that aims to reconstruct some elements of the quad-pol covariance matrix from CP data specifically for maritime applications. This study is applied on Radarsat-2 scenes with fine resolution and simulated medium and low resolution RCM data . The effect of spatial resolution, ship orientation and incidence angle on the detection performance has been explored. The second contribution is a new hybrid ship detection algorithm that utilized CP Stokes parameters and some of their derived parameters for ship detection. The pre-screener of the algorithm merges three detection strategies to declare candidate ships and the discriminator uses a CP decomposition technique to discriminate ships from false alarms based on the type of scattering mechanism. The proposed detection algorithm is applied to a number of simulated RCM scenes with medium and low resolutions. The findings of this thesis suggest the usefulness of CP reconstruction for improved ship detection. For the hybrid ship detection algorithm, a detection rate of 100% is obtained for medium resolution data and about 98% for low resolution 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.
Full frame distilled prediction
Teacher imitationNot 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.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 it