Computer Vision Fire Hydrant Obstruction Detection System
Bibliographic record
Abstract
Well-maintained and accessible fire hydrant infrastructure can reduce response times and minimize fire damage. Hydrant access and visibility can be impeded by transient obstructions, such as illegally parked vehicles, or by incremental obstructions, such as snow coverage or encroachment of vegetation. We here develop a computer vision system to automatically survey all hydrants within a city to determine whether they are accessible, partially obstructed, or fully obstructed. The system is developed and validated using Google Streetview images from three distinct urban environments. The dataset is augmented with winter weather and synthetic obstructions, including snowbanks. A YOLOv8 model is fine-tuned to detect fire hydrants. Partially obstructed hydrants are then detected using a bounding box aspect ratio threshold.Evaluation on a test city results in an mAP of 97.1%, indicating strong hydrant detection performance, even in challenging scenarios such as partially snow-covered hydrants. Partially blocked hydrants are classified with precision and recall of 92%. Results are displayed on a geographic information system dashboard for maintenance and bylaw personnel to ensure continuous access to this critical firefighting infrastructure.
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) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| 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) | 0.007 | 0.007 |
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".