A Combined Index of Proactive and Reactive Data for Rating the Safety of Road Sections
DOI: 10.1007/s40996-024-01552-0
archive: archived pipeline: cataloged verified
Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)
Summary
This paper presents initial results from the European Road Safety Inspection (EuRSI) mobile mapping project, addressing the need for standardized, automated tools to assess road infrastructure safety. Motivated by the European Commission’s goal to reduce road fatalities and the implementation of Directive 2008/96/EC, which mandates road safety audits, the authors aim to develop efficient methods for extracting road features from geospatial data. While current inspections are often manual and inconsistent, mobile mapping systems (MMS) offer high-density, georeferenced 3D data. The study focuses on developing a novel algorithm to automatically extract road edges from LiDAR point clouds, applicable to both urban and rural environments, to facilitate accurate 3D reconstruction of route corridors. The researchers utilized a custom terrestrial mobile mapping platform (XP-1) equipped with an IXSEA LandINS GPS/INS navigation system and a Riegl VQ-250 LiDAR sensor. The LiDAR was mounted at a 45-degree angle to capture rich 3D information, generating up to one million points every 3.5 seconds. The proposed method employs a two-stage unsupervised segmentation algorithm. First, the system generates orthogonal cross-sections of the road based on processed navigation data (GPS and INS). Second, it processes these cross-sections by fitting 2D cubic splines to the elevation data, calculating slopes, and identifying peaks and troughs that correspond to potential road edges. These candidates are filtered using LiDAR intensity and pulse width thresholds to distinguish road boundaries from noise or non-road objects. Experiments were conducted on two distinct road sections: a regional urban road with structured curb boundaries and a rural secondary road with uneven, non-uniform boundaries. The vehicle traveled at approximately 30 km/h, and algorithm parameters, including line length and width, were kept constant. The results demonstrated that the algorithm successfully extracted road edges in both environments. In the urban setting, the system accurately identified curbs on both sides. In the rural setting, it handled the irregular road boundaries effectively. The authors noted that edge detection quality varied depending on the LiDAR’s position relative to the road; for instance, the left edge was detected with higher quality than the right edge due to the single LiDAR sensor’s placement and the vehicle driving on the left side of the road. This asymmetry could be mitigated by using dual sensors or bidirectional data collection. The significance of this work lies in providing a robust, automated solution for road segmentation that supports the broader objectives of road safety management and infrastructure maintenance. By enabling the automatic extraction of road edges from mobile LiDAR data, the method reduces the reliance on manual, labor-intensive inspection processes. This contributes to the standardization of road safety assessments across Europe, allowing for more consistent and scalable evaluation of road infrastructure risks. The study validates the feasibility of using terrestrial mobile mapping systems for detailed road surface analysis, paving the way for further development in autonomous vehicle navigation and precise road safety auditing.
Provenance
The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed.
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | Crossref | — | — | 1 | 2026-06-20 |
| archive | success | canonical_url | — | — | 1 | 2026-06-26 |
| extract | success | pdftotext | — | — | 2 | 2026-06-26 |
| clean | success | clean | — | — | 1 | 2026-06-26 |
| chunk | success | chunk | — | — | 1 | 2026-06-26 |
| embed | success | embed | Qwen/Qwen3-Embedding-8B | — | 1 | 2026-06-26 |
| enrich | failed | — | — | — | 4 | 2026-06-26 |
| promote | success | — | — | — | 1 | 2026-06-20 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 1 | 2026-06-26 |
| tag | success | vector_similarity | — | — | 6 | 2026-06-26 |
| verify | success | — | — | — | 1 | 2026-06-26 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-26; verification: verified.
Topics
Ranked by relevance to this paper. Hover a topic for its definition.
Information type
What kind of knowledge this paper contributes, grouped by family — independent of topic (what it is about) and method (how it was studied).
- Empirical Findings: crash risk outcomes
- Methodological Resource: dataset resource, metric or index