Computer vision-assisted human-in-the-loop measurements: augmenting qualitative by increasing quantitative analytics for CI situational awareness
Bibliographic record
Abstract
Many infrastructure problems are reported by the public, yet this can result in human-in-the loop, qualitative measurements and lead to slow response times as quantitative data is needed. Cameras already exist in many settings such as smartphones, or moving objects such as UAV-mounted cameras. Since many critical infrastructure (CI) problems often are first noticed by the general public and then reported, their qualitative descriptions can then be accompanied with quantitative measurements by using the indirect measurement of parameters provided using machine vision. In this paper, the authors propose a framework using Agile IoT to add new modalities to already existing sensors (cameras) such as smartphone devices to determine additional parameters using machine vision. This can result in an increase in situational awareness, and meanwhile, response and repair times can decrease, then the overall infrastructure resilience increases. This has the potential to improve preventative maintenance and increase resilience by increasing situational awareness, so resources can be deployed quickly and efficiently where they are needed. This proposed framework can apply to multiple small infrastructure such as lighting standards, playground structures, signage, access gates and fences, electrical wires, and utility poles and its affixed hardware components. The paper shows a proof-of-concept application of this methodology to the concept of tilt detection, with lean determined from simulated and field images. Quick follow-up to problems at appropriate locations can increase system resilience by quickly enabling solving the 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 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".