Autonomous real-time infrared detection ofsub-surface vessels for unmanned aircraft systems
Bibliographic record
Abstract
The threat of small self-propelled semi-submersible vessels cannot be understated; payloads from drugs to weapons of mass destruction could be housed in these small, inconspicuous vessels. With a current apprehension rate of approximately 10%, a method resulting in increased interdiction of this illegal traffic is required for national security both in the ports along the coastlines of Canada, as well as the rest of North America. A smart, autonomous payload containing an infrared imaging device, designed for use in small unmanned aircraft systems for the specific mission of detecting self-propelled semi-submersibles over the vast ocean coastline will address the current security needs. Thermal imagery of the disturbed colder water layers, driven to the surface by the vessel will allow for the detection of this traffic using long wave infrared technology. Infrared signatures of ship wakes are highly variable in both persistence and temperature contrast as compared to the surrounding surface water, thus infrared imaging devices with a high resolution, a high responsivity, and a very low minimum resolvable temperature will be required to provide high quality imagery for airborne detection of the thermal wake. A theoretical understanding of the physics associated with the energy collected by the infrared sensor and the resulting infrared images is provided. Explanation of the factors affecting the resulting image with respect to the camera properties are detailed. A variety of examples of airborne thermal images are presented, with detailed explanations of the imaged scenes based on theory and sensor characteristics provided in the previous sections. Infrared images taken over the Atlantic and Pacific oceans from manned and unmanned aircraft platforms are presented. Temperature measurements taken using Vemco Minilog II temperature loggers confirmed the thermal stratification of the upper 5 meters of the water. Thermal scarring due to upwelled colder water to the surface was noted during the day time under normal conditions, with temperature differences found to be consistent with the measured temperature profile. A custom gimbal system, with corresponding ground control station for real-time, visual feedback is presented. An algorithm for the detection of submerged vessel ship wakes using a LWIR camera, specifically for a small unmanned aircraft, with limited power, space, and computing power is developed. A time sequential processing method is presented to reduce the required computing, while allowing high frame rate, real-time operation. Moreover, a windowed triple-vote method is continually applied to ensure that the detection mode is correctly set by the algorithm, while ignoring unexpected targets in the image. A simple background estimation method is presented to remove any nonuniformity in the captured images, resulting in a high detection rate with low false alarms. Finally, a complete, mission-ready payload system is prepared for small UA platforms, with an accuracy rate greater than 97% for the detection of self-propelled semi-submersible vessels.
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 | 0.000 |
| 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) | 0.002 | 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".