Potential of Low-Cost, Close-Range Photogrammetry Toward Unified Automatic Pavement Distress Surveying
Bibliographic record
Abstract
Automatic pavement distress detection and data collection is important for pavement management systems. It is estimated that pavement defects cause damage costing $10 billion/year in the US alone. Despite the importance of image-based distress detection systems, they are still semi-automatic to a great extent. They rely internally on one or more threshold values during processing or may need a pre-processing stage, and the quality is affected by shadows and low or extra illumination among other factors. After years of research, processing still typically relies heavily on global or in-context pixels content analysis. Such systems lack the robust sensor modeling, hence, robust detection and modeling which cannot be achieved directly through 2D image space analysis. The exploitation of arrays of laser profilers for 3D data acquisition is an expensive approach and has limitations for enhancing or replacing image-based output. Alternatively, 3D surfaces can be generated using stereo vision techniques. This research has investigated close range photogrammetry as a robust approach to overcome the above disadvantages. The experimental work is carried out using a non-metric DSLR camera with its built-in flash and natural daylight as sources of illumination. Initial investigations show significant potential for 3D distress detection and modeling with higher spatial precision and a higher level of automation, while retaining 2D color and shading information for data fusion. The output of automatic photogrammetric processing can be further exploited directly in existing automated and semi-automated systems for updating the content, analysis and visualization of pavement management system (PMS) and geographic information systems (GIS).
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.002 |
| 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 | 0.001 |
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".