Efficient First Floor Height Estimation of Buildings from Sequential Images and Airborne LiDAR for Flood Risk Analysis
Bibliographic record
Abstract
First Floor Height (FFH) is an essential parameter for flood risk analysis, where buildings with a lower FFH are at higher risk of content damage for a given base flood elevation. Despite its importance, FFH is often missing from building databases and can be time-consuming or expensive to collect. Here, an efficient and cost-effective method is proposed to accurately estimate FFH using high-resolution, sequential images extracted from video collected with a vehicle-mounted GoPro camera and used to derive a 3D representation of the environment. To improve positional accuracy, the 3D model is georeferenced using preexisting airborne LiDAR, achieving global map consistency. FFH is then determined as the difference in elevation between the door bottom extracted from GoPro data and the ground level determined from a surface terrain model aligned to a common global coordinate system. To improve efficiency, the Segment Anything Model for videos (SAM-2) is used to track door instances across image frames, facilitating FFH estimation. The proposed method achieves a Mean Absolute Error of 21 cm. Unlike other methods that estimate FFH from street-view imagery, our approach is more robust to occlusion by exploiting multiple viewpoints and does not rely on proprietary data sources, making it more reliable.
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 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| 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".