Multi-camera vision-based structural health monitoring of historic masonry minarets with LLM/VLM-assisted damage interpretation
- 1Department of Civil Engineering, Faculty of Engineering, Karadeniz Technical University
Abstract
This study proposes an LLM/VLM-orchestrated multi-agent framework for multi-camera vision-based Structural Health Monitoring (SHM) of historic masonry minarets. The main novelty of the framework is its region-aware and auditable decision-support strategy: camera-derived displacement anomalies, degradation in inter-sensor relationships, and VLM-based visual observations are preserved as traceable evidence streams and integrated at the decision layer rather than being merged through opaque feature-level fusion. The framework was experimentally validated on a scaled masonry minaret subjected to controlled shaking-table excitation. Multi-camera optical-flow tracking provided displacement time series for global and relation-based anomaly analysis, while region-specific inspection images were interpreted by a VLM as qualitative visual evidence. The global reconstruction-error pathway showed more frequent and persistent anomaly behavior during the damage-candidate phases compared with the reference condition. The relation-based pathway identified non-uniform degradation in inter-sensor consistency, with the strongest localization cue associated with the sensor region corresponding to the experimentally damaged area. Most importantly, the fused region-level risk map showed qualitative spatial agreement with the damage observed on the minaret model after the shaking table tests. These findings indicate that the proposed multi-agent framework can transform heterogeneous SHM evidence into interpretable regional risk priorities and reviewable reporting outputs for historic masonry structures, while maintaining a conservative expert-in-the-loop interpretation strategy.
Related
- False Positives in Esophageal pH Monitoring: The Pitfalls of Single-Value Interpretation
- AI-Assisted Tissue-Based Antibody Interpretation in Autoimmune Encephalitis: Prospective Validation and Reader Study
- AI-Assisted Interpretation of Neurologic Autoantibody Cell-Based Assays
- Genetic and structural interpretation of NLRP1 FIIND domain variants in glioma in an Indian cohort: a pilot study
- Antepartum electronic fetal monitoring interpretation: multicenter observational study.
BibTeX
@article{hacıefendioglu2026multicamera,
title = {{Multi-camera vision-based structural health monitoring of historic masonry minarets with LLM/VLM-assisted damage interpretation}},
author = {Kemal Hacıefendioğlu and Tunahan Aslan and Hasan Basri Başağa},
journal = {Scientific Reports},
year = {2026},
month = jul,
doi = {10.1038/s41598-026-61030-7},
url = {https://doi.org/10.1038/s41598-026-61030-7},
note = {CC BY},
}
RIS
TY - JOUR
TI - Multi-camera vision-based structural health monitoring of historic masonry minarets with LLM/VLM-assisted damage interpretation
AU - Kemal Hacıefendioğlu
AU - Tunahan Aslan
AU - Hasan Basri Başağa
PY - 2026
DA - 2026/07/01
JO - Scientific Reports
DO - 10.1038/s41598-026-61030-7
UR - https://doi.org/10.1038/s41598-026-61030-7
AB - This study proposes an LLM/VLM-orchestrated multi-agent framework for multi-camera vision-based Structural Health Monitoring (SHM) of historic masonry minarets. The main novelty of the framework is its region-aware and auditable decision-support strategy: camera-derived displacement anomalies, degradation in inter-sensor relationships, and VLM-based visual observations are preserved as traceable evidence streams and integrated at the decision layer rather than being merged through opaque feature-level fusion. The framework was experimentally validated on a scaled masonry minaret subjected to controlled shaking-table excitation. Multi-camera optical-flow tracking provided displacement time series for global and relation-based anomaly analysis, while region-specific inspection images were interpreted by a VLM as qualitative visual evidence. The global reconstruction-error pathway showed more frequent and persistent anomaly behavior during the damage-candidate phases compared with the reference condition. The relation-based pathway identified non-uniform degradation in inter-sensor consistency, with the strongest localization cue associated with the sensor region corresponding to the experimentally damaged area. Most importantly, the fused region-level risk map showed qualitative spatial agreement with the damage observed on the minaret model after the shaking table tests. These findings indicate that the proposed multi-agent framework can transform heterogeneous SHM evidence into interpretable regional risk priorities and reviewable reporting outputs for historic masonry structures, while maintaining a conservative expert-in-the-loop interpretation strategy.
SN - 2045-2322
ER -