3D Dense Reconstruction for Structural Defect Quantification
Bibliographic record
Abstract
Recent advancements in vision-based visual inspection enable the identification, localization, and quantification of damage on structures. However, existing damage quantification methods are limited to measuring one- or two-dimensional attributes such as length or area, which is insufficient for certain damage types such as spalling that require depth in addition to in-plane measurements, as outlined in inspection manuals. To address this limitation, we propose utilizing image-based dense 3D reconstruction to perform full 3D quantifications to assess damages for concrete structure inspections. The proposed method is applied to quantify spalling damage in 3D to compute volumetric loss and maximum depth of the damage in line with bridge inspection manuals. Our approach involves using a convolutional neural network-based interactive segmentation algorithm to accurately segment spalling boundaries from images. Structure-from-motion and multiview stereo algorithms are then applied to generate a detailed 3D point cloud reconstruction of the spalling using multiple images. From this point cloud, a 3D mesh representation of the spalling is created for precise quantification. To validate our proposed technique, we conducted laboratory and field experiments to capture images and interactively segment the damage. The results demonstrate the effectiveness and reliability of our approach for 3D damage quantification in structure inspections.
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) | 0.000 | 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 | 0.001 | 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".