Deep Learning Techniques for Efficient Evaluation of Asphalt Pavement Condition
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
For the last few decades, researchers have been devising a simple and cost-effective method to evaluate pavement distresses to give decision-makers adequate feedbacks about the pavement condition of a certain road. Fortunately, with the evolution and progression of computer vision tools and techniques, good results had been achieved regarding the detection, classification, and quantification of road distress. In this paper, a new efficient process of road distress analysis using deep learning models is introduced. This new process was tested on a collected road dataset to evaluate the efficiency and speed of this low-cost road maintenance system. Promising results were obtained from the proposed process based on the deep learning model used with an outstanding performance of ~400 fps and distress detection every ~5 cm for a vehicle moving at 40 km/h. Furthermore, the output of the developed process was used as an input for the Pavement Condition Index (PCI) calculation module to determine the pavement condition of the road on a single-day mission. The proposed system focuses on detecting some specific types of distresses: Alligator cracks, longitudinal cracks, transverse cracks, block cracks, lane longitudinal cracks, reflective cracks, and sealed cracks. Experimental results show that this process based on deep learning models achieved promising results of ~5% difference from the true PCI, currently calculated in a month, just in a single day using very low-cost methods.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 it