A deep convolutional network approach with attention mechanism for green sea urchin detection and localization
Bibliographic record
Abstract
Green sea urchin, Strongylocentrotus droebachiensis, exerts considerable influence on marine benthic habitats in Arctic and sub-Arctic regions, including kelp forests. Additionally, the species’ gonads (roe) are a highly prized delicacy on Asian markets. To assess and monitor ecological conditions in coastal regions due to sea urchin overgrazing or to establish aquaculture of green sea urchins, computer-assisted autonomous detection might be desirable. However, the accuracy of underwater identification of green sea urchins is affected by a number of factors, including low picture quality, scattering and absorption of light, overlap or occlusion of underwater species, differences in the sizes of the species, and the presence of background objects. In this work, we present a multi-step process for the autonomous identification of green sea urchins in natural habitats using an underwater image dataset consisting of 2,400 images. The process includes augmentation, color correction and enhancement based on the state-of-the-art YOLOv7 object detector. The results of the experiments demonstrate that the proposed framework is capable of accurately recognizing green sea urchins in various underwater scenes and for varying distances between the camera and the target with a mean Average Precision (mAP) of 83.6%.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".