A Novel Framework for Rapid Detection of Damaged Buildings Using Pre-Event LiDAR Data and Shadow Change Information
Bibliographic record
Abstract
After a major earthquake in a dense urban area, the spatial distribution of heavily damaged buildings is indicative of the impact of the event on public safety. Timely assessment of the locations of severely damaged buildings and their damage morphologies using remote sensing approaches is critical for search and rescue actions. Detection of damaged buildings that did not suffer collapse can be highly challenging from aerial or satellite optical imagery, especially those structures with height-reduction or inclination damage and apparently intact roofs. A key information cue can be provided by a comparison of predicted building shadows based on pre-event building models with shadow estimates extracted from post-event imagery. This paper addresses the detection of damaged buildings in dense urban areas using the information of building shadow changes based on shadow simulation, analysis, and image processing in order to improve real-time damage detection and analysis. A novel processing framework for the rapid detection of damaged buildings without collapse is presented, which includes (a) generation of building digital surface models (DSMs) from pre-event LiDAR data, (b) building shadow detection and extraction from imagery, (c) simulation of predicted building shadows utilizing building DSMs, and (d) detection and identification of shadow areas exhibiting significant pre- and post-event differences that can be attributed to building damage. The framework is demonstrated through two simulated case studies. The building damage types considered are those typically observed in earthquake events and include height-reduction, over-turn collapse, and inclination. Total collapse cases are not addressed as these are comparatively easy to be detected using simpler algorithms. Key issues are discussed including the attributes of essential information layers and sources of error influencing the accuracy of building damage detection.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".