Optimizing constrained mine hunting surveys for the multi-aspect classification of sidescan sonar detections
Bibliographic record
Abstract
When conducting remote mine hunting operations, an initial lawn-mowing search pattern is standard if no prior information on potential target locations is available. After completion of this initial survey, a sidescan sonar equipped vehicle may have limited additional time to revisit some contacts in order to increase the overall classification performance. Using real multi-aspect sonar images obtained from the 2005 Citadel sea trial, this thesis quantifies the classification performance achieved by computer-aided classification algorithms. For different types of minelike objects, single aspect classification performance with traditional and non-traditional features sets is studied. These results are then extended to multi-aspect classification where the hit and false alarm rates are expressed as functions of the angular increments between aspects. This secondary looks information is combined with route-optimizing algorithms designed to generate multi-aspect routes improving the performance of current mine hunting systems. This thesis presents new planning algorithms designed to enable current remote mine hunting systems to achieve secondary paths minimizing the total distance to be travelled while satisfying all motion and imaging constraints. Also, a more flexible algorithm maximizing the overall classification performance for minefields incorporating multiple types of mines is introduced. These numerical techniques are applied to two test sites created for the 2007 Mongoose sea trial. Keywords. computer-aided classification, multi-aspect sidescan sonar images, optimal route planning, Dubins curves, travelling salesman problem.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 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".