Automated Extraction of Digital Terrain Models, Roads and Buildings Using Airborne Lidar Data
Bibliographic record
Abstract
This dissertation presents a collection of algorithmsdeveloped for automatically extracting useful information from lidar data exclusively. The algorithms focus on automated extraction of DTMs, 3-D roads and buildingsutilizing single- or multi-return lidar range and intensity data. The hierarchical terrain recovery algorithm can intelligently discriminate between terrain and non-terrain lidar points by adaptive and robust filtering. It processes the range data bottom up and top down to estimate high quality DTMs using the hierarchical strategy. Road ribbons are detected by classifying lidar intensity and height data. The 3-D grid road networks are reconstructed using a sequential Hough transformation, and are verified using road ribbons and lidar-derived DTMs. The attributes of road segments including width, length and slope are computed. Building models are created with a high level of accuracy. The building boundaries are detected by segmenting lidar height data. A sequential linking technique is proposed to reconstruct building boundaries to regular polygons, which are then rectified to be of cartographical quality. Then prismatic models are created for flat roof buildings, and polyhedral models are created for non-flat roof buildings by theincremental selective refining and vertical wall rectification procedures. Many attributes of these building models are derived from the lidar data. These algorithms have beentested using many lidar datasets of varying terrain type, coverage type and point density. The results show that in most areas the lidar-derived DTMs retain most terrain details and remove non-terrain objects reliably; the road ribbons and grid road networks are sketched well in built-up areas; and the extracted building footprints have high positioning accuracy equivalent to ground-truth data surveyed in field. A toolkit, called Lidar Expert, has been developed to bundle these algorithms and to offer the capability of performing fast information extraction from lidar data.
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 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".