A Methodology for Automated Segmentation and Reconstruction of Urban 3-D Buildings from ALS Point Clouds
Bibliographic record
Abstract
In this paper, a methodology which allows automated and efficient reconstruction of three-dimensional (3-D) geometric building models from an Airborne Laser Scanning (ALS) point cloud is introduced and its performance is analyzed and evaluated. The proposed method avoids abnormal and/or infinite solutions which are typically encountered in previously published methods that use the rooftop primitive adjacency matrix to solve the critical rooftop vertices. In particular, first, an improved random sample consensus (RANSAC) algorithm is proposed to segment the rooftop primitives, i.e., the planar patches that constitute rooftops, of each building or group of connected buildings. The algorithm successfully maintains topological consistency among primitives and avoids under- and over-segmentation with high efficiency. Second, a novel Voronoi-based primitive boundary extraction algorithm under constraints of outer and inner building boundaries is introduced in order to extract each primitive boundary. In this algorithm, the adjacent segmented primitive relationships among the various primitives are preserved by a subgraph of the Voronoi diagram so that the reconstructed neighbor primitives are seamlessly connected. Third, in order to refine the boundary shapes of primitives with irregular geometry, various criteria for making the boundary adjustments more effective are proposed. In this way, more regular 3-D buildings can be produced. Finally, the primitive boundary simplification criteria are formally introduced to generate compact 3-D building models. By using the simplification criteria, nonadjacency between neighbor primitives, intersection between boundaries, and self-intersections are, to a great extent, avoided. Numerous experimental results obtained using multiple data sets, including data from the cities of Toronto and Enschede as well as from the Niagara area, have shown that the proposed methodology has excellent performance and it can produce watertight 3-D polyhedral building models.
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 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.002 |
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".