Development of an unsupervised 3D LiDAR-based methodology for automated safety monitoring of railway facilities
Bibliographic record
Abstract
Railway safety (e.g., at grade crossings, platforms, or rail tracks) is a primary concern for transportation authorities. Unfortunately, preventable railway collisions claim the lives of hundreds annually, often involving individuals crossing illegally at highway-railway grade crossings or trespassing at unauthorized railroad facilities. Transportation authorities often deploy a range of engineering countermeasures to mitigate the frequency or risk of such events. These countermeasures include technological solutions that automatically activate warning systems, barriers, or gates to alert and deter road users from unlawfully entering restricted railway facilities. For the safety monitoring of such facilities, alternative sensing technologies such as video-based computer-vision systems have been evaluated and, in some cases, utilized in practice. Despite their merits, implementing automated LiDAR-based detection and tracking methods has yet to be explored in railway safety applications. This research aims to introduce and assess an unsupervised 3D-LiDAR-based methodology for monitoring rail-road level facilities. This study’s core is the implementation of an unsupervised learning algorithm designed to detect, track, and classify road users using point clouds gathered by a 3D-LiDAR sensor. The proposed methodology demonstrates encouraging results when monitoring rail-road level crossings. The aggregate average absolute percentage deviation (AAPD) for motorized road users and counting motorized road users stands at 5% and 3%, for non-motorized road users at 10% and 14% on two separate test days, each featuring distinct system installations.
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) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 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".