New pipeline enhances thermographic anomaly detection for heritage sites

Researchers have developed a new pipeline to improve the accuracy of thermographic anomaly detection in cultural heritage digital twins. This method corrects per-pixel emissivity, which is crucial for accurate temperature retrieval on heterogeneous surfaces. The pipeline utilizes SAM 3.1 for segmentation and a material-keyed emissivity table, significantly reducing mean absolute error on synthetic benchmarks and real-world datasets. However, the correction's impact is noted to be small on typical weathered heritage surfaces, with its effectiveness concentrated on genuine low-emissivity exceptions. AI

IMPACT Improves accuracy in digital twin creation for cultural heritage, potentially aiding preservation efforts.

RANK_REASON Academic paper detailing a new methodology. [lever_c_demoted from research: ic=1 ai=0.7]

Read on arXiv cs.CV →

• arXiv
• SAM 3.1

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →