Automated Data Collection System of Pavement Distresses: Development, Evaluation & Validation of Distress Types and Severities
Bibliographic record
Abstract
This study presented an affordable and simpler technique that does not require complex technology and is suitable for middle size road networks. This technique involves taking pictures of various sections of the road network using cameras that can be mounted on public vehicles and transmitting taken images to a processing center. Each image is processed using image filtering techniques to produce an initial estimate of the PI. A total of 5,070 images and 507 sections (4 x 10 m per section) were taken and tested on a part of the Sheikh Maktoum Bin Rashid Highway E11 in Abu-Dhabi city (UAE) based on the quantity and clarity of the distresses. Six types of pavement distresses were tested; (1) longitudinal cracking, (2) alligator cracking, (3) block cracking, (4) pothole distress, (5) transverse cracking and (6) edge cracking. Three severity levels were considered: (1) low, (2) medium and (3) high. There were two distress measurement methods used to identify pavement distresses; semi-automated measurement (SAM) method and automated measurement (AM) method. In order to evaluate the accuracy of the AM method, two expert observers were used individually to extract the pavement distress by using the SAM method. The Cohen's weighted Kappa used to determine the agreement between the two observers. The overall agreement result of the pavement distresses between the two observers was 98%, which is almost a perfect agreement. The overall agreement result of the pavement distresses between the two measurement methods was 89%, which is again an almost perfect agreement. In addition, the AM method validated by using R2 method and was found to be 0.93. The weighted mean speed of all distresses and standard deviation were found to be 58.56 km/h and 28.24 km/h respectively.
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 | 0.007 | 0.010 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.005 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| 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 | 0.001 |
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".