Pothole Detection and Assessment on Highways Using Enhanced YOLO Algorithm With Attention Mechanisms
Bibliographic record
Abstract
Economic and social prosperity heavily relies on well‐maintained highways. However, road maintenance faces challenges due to limited funding and resources, with potholes posing significant safety risks. This work introduces a pothole detector designed to detect and estimate pothole areas for timely maintenance. It enhances detection by modifying the YOLO algorithm, using the Xception backbone, and integrating attention mechanisms to improve the prediction of small or clustered objects. Xception’s depthwise separable convolutions enhance feature extraction, outperforming the standard YOLO algorithm in detecting small, irregular potholes and preventing overfitting. The improved YOLO model, along with spatial and channel attention mechanisms, focuses on relevant regions and refines important features specific to pothole areas. Accurate area estimation is achieved through computer vision and traditional segmentation processes. A custom dataset, including the MakeML pothole dataset, a Kaggle dataset, and real‐time footage of Kerala roadways, is used for training and validation. Performance evaluation with mean average precision (mAP) and average precision (AP) metrics shows the pothole detector’s superiority, effectively identifying potholes under various conditions and ensuring safe road 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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| 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) | 0.001 | 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".