Bibliographic record
Abstract
Road quality assessment is a key task in a city's duties as it allows a city to operate more efficiently. This assessment means a city's budget can be allocated appropriately to make sure the city makes the most of its usually limited budget. However, this assessment still relies largely on manual annotation to generate the Overall Condition Index (OCI) of a pavement stretch. Manual surveying can be inaccurate, while on the other side of the spectrum a large portion of automatic surveying techniques rely on expensive equipment (such as laser line scanners). To solve this problem, we propose an automated infrastructure assessment method that relies on street view images for its input and uses a spectrum of computer vision and pattern recognition methods to generate its assessments. We first segment the pavement surface in the natural image. After this, we operate under the assumption that only the road pavement remains, and utilize a sliding window approach using Fisher Vector encoding to detect the defects in that pavement; with labelled data, we would also be able to classify the defect type (longitudinal crack, transverse crack, alligator crack, pothole ... etc.) at this stage. A weighed contour map within these distressed regions can be used to identify exact crack and defect locations. Combining this information allows us to determine severities and locations of individual defects in the image. We use a manually annotated dataset of Google Street View images in Hamilton, Ontario, Canada. We show promising results, achieving a 93% Fl-measure on crack region detection from perspective images.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.005 | 0.004 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.002 |
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".