Information Content of Very High Resolution SAR Images: Study of Dependency of SAR Image Structure Descriptors with Incidence Angle
Bibliographic record
Abstract
This paper provide systematic results of the influence of the Synthetic Aperture Radar image structure descriptors with incidence angle and orbit direction. The evaluation is done on TerraSAR-X data and the interpretation is done semi-automatically. In the first part, we study and assess the behavior of the primitive feature extracted methods for images of the same scene with 2 look angles covering the min-max range of the sensor. After that the influence of the orbit looking is shortly discuss. The tests are done on TerraSAR-X products High Resolution Spotlight mode at 3 m resolution and two sites covering the Berlin and Ottawa area are found to be suitable for this investigation. To identify the best features and appropriate incidence angle for them the Support Vector Machine and as a measure of the classification accuracy the precision–recall were considered. The recall shows that the optimal value of the incidence angle in order to have a higher classification is obtained for a value of the incidence angle closer to upper bound of the sensor range. In the second part of the paper a list of queries that can be asked by Earth Observation users are presented and proposed to be implemented in the next generation of our system. The first contribution of this paper is the evaluation of four primitive features that are very known (gray level cooccurrence matrix, Gabor filter, quadrature mirror filter, and non-linear short time Fourier transform) but not used and compared for SAR images. After the best primitive feature is identified the second contribution of this paper lies in the fact that the parameters of the data namely, incidence angle and orbit direction are systematically investigated in order to find the dependency between these parameters and the accuracy of the retrieved classes. Keywords-classes; features; inicdence angle; orbit direction;
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 | 0.006 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| 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".