Robust curved road boundary identification using hierarchical clustering.
Bibliographic record
Abstract
We develop a new method for automatic curved road boundary detection in images captured by traffic cameras. The proposed method combines data driven (edge segments) and model based (2nd degree polynomial models for road boundaries) techniques to identify dominant road boundary in images exhibiting extreme weather conditions, low visibility and poor lighting. The proposed method constructs a ranked list of possible road boundaries through agglomerative hierarchical clustering of edge segments. Each node in the hierarchical clustering is a potential road boundary. Top ranked road boundaries are paired with each other to identify potential road regions. The road regions are then ranked using appearance and perspective cues and the top ranked road region is used to construct the dominant road boundary in the image. We evaluate our method on a realistic dataset captured by traffic cameras managed by Ontario’s Ministry of Transportation. ii Acknowledgements I would like to express my sincere gratitude to my supervisors, Dr. Ken Q. Pu and Dr. Faisal Z. Qureshi for their continuous guidance, support, motivation, and patience during my graduate studies. Special thanks to my fellow lab members, Mohamed Helala, Luis Zarrabeita, Zheng
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 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.004 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.003 |
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".