The Future of Underwater Asset Surveys | Completely Remote Visualizations in 2D and 3D
Bibliographic record
Abstract
Abstract The adoption of imaging technologies to create 2D and 3D models is becoming more and more common in the management of critical infrastructure. In most cases of submerged infrastructure, remotely operated vehicles (ROVs) are the only way to easily capture reliable data for modeling. Underwater asset surveys previous to ROVs relied on commercial dive teams using handheld equipment. This methodology is primarily limited to commercial diving safety regulations related to maximum depths, working in confined entry, and time limitations from oxygen levels. Alternatively, autonomous unmanned vehicles (AUVs), unmanned surface vessels (USVs), or a standard ships equipped with imaging technologies could be utilized, however, details are limited at depths or confined spaces. The use of different imaging sensors on ROVs such as stereo cameras, sonars, and laser scanners allow operators to capture data to build detailed structural models in both 2D or 3D with unparalleled accuracy. Recent field results have confirmed the validity of the application of these technologies for real-world use. The variety offered by the three different practices, and modular simplicity of integration allows for these modeling techniques to be be widely interchangeable between use-cases. Using a mounted dual-frequency imaging sonar, ROV operators were recently able to complete an entire 2D model of a submerged tunnel measuring 60 metres in length, with widths raging from 0.7 - 1.0 metres. A battery powered ROV was remotely deployed from a small topside vessel, and performed multiple runs of the submerged tunnel within a three day period to examine this otherwise impossible enter tunnel for a pre-construction assessment. Similarly, an offshore survey company based in Newfoundland was able to generate a 2D model of a Floating Production, Offloading, and Storage (FPSO) Vessel’s prop using an ROV-mounted laser scanner to verify the necessary blade clearances within millimetres. The most detailed model was generated in 2022 by a southern Ontario archaeology team within a civil engineering company. The crew used two different ROVs to repeatedly capture high resolution photos every two seconds as they ran multiple passes over a historical dam structure. After running their collected images through the modeling program Agisoft Metashape, the crew successfully generated an extremely accurate 3D model of the submerged structure from just one day’s worth of imagery.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| 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 | 0.001 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".