Strategies for filtering incorrect matches in seabed mosaicking
Bibliographic record
Abstract
Monitoring animal populations in benthic habitats is essential to detecting changes in the local ocean environment and marine ecosystem. Images of animals on the seafloor are obtained by drop-cameras or digital still-cameras mounted on Remotely Operated Vehicles (ROVs). Population statistics have a wide range of applications in the fishery industry, oceanographic research (e.g. population studies, habitat analysis), as well as for the oil and gas industry (e.g. population monitoring for environmental impact assessment). Most ROV imaging transects deliberately produce overlap between successive or adjacent images, such that individual animals could appear in several images, which could yield inaccurate counts. In order to eliminate the possibility of counting the same animal more than once, the overlap between images must be detected and cropped from one of the images. We are developing a feature-based mosaicing algorithm that uses Scale Invariant Feature Transform (SIFT) features in which feature descriptors of images are extracted and appropriate correspondences are found and matched by computing the Standardized Euclidean distance between descriptor vectors. The Homography matrix between each pair of images is then estimated by RANdom SAmple Consensus (RANSAC). Finally, by using the estimated Homography the final mosaic is generated with a multi-band blending algorithm.
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 | 0.018 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.003 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.001 |
| 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".