Artificial Intelligence for Detecting Surface Alteration Phenomena in Stone-Built Heritage: The Case of the ‘Unfinished Church’ of Venosa
Published 2025-12-22
Keywords
- Artificial Intelligence,
- Built Heritage,
- Image Processing,
- Point Cloud,
- Surface Alteration
Abstract
Point clouds and 3D models have become essential not only for the digitisation process but also for the non-invasive assessment of deterioration and potential decay mapping in Cultural Heritage, particularly in the built environment and architectural landmarks. These resources facilitate precise digital inspections and enable a comprehensive analysis of the morphological and material properties of heritage assets, in strict alignment with conservation principles. Recent advancements in Artificial Intelligence have further refined 3D data and image processing, introducing sophisticated techniques for segmentation and classification through both supervised and unsupervised learning paradigms. Building upon these breakthroughs, this study explores the semi-automatic identification of surface alterations in the stone masonry of the south-east façade of the ‘Unfinished Church’, which is part of the Most Holy Trinity Complex in Venosa (Southern Italy). The mapping process started with the photogrammetric point cloud, employing RGB colour-detection techniques, followed by the implementation of two Machine Learning algorithms (Fast Random Forest and K-Nearest Neighbours) to examine the UV texture of the polygonal model. Comparative analyses, both quantitative and qualitative, were conducted to assess the effectiveness of these methods in identifying and classifying alterations, highlighting their potential to support preservation efforts and guide future maintenance strategies.
References
- 1. Vecco M (2010) A definition of cultural heritage: From the tangible to the intangible. Journal of Cultural Heritage 11:321–324. https://doi.org/10.1016/j.culher.2010.01.006
- 2. Gulotta D, Toniolo L (2019) Conservation of the Built Heritage: Pilot Site Approach to Design a Sustainable Process. Heritage 2:797–812. https://doi.org/10.3390/heritage2010052
- 3. Biasi A, Riavis V, Zamboni I, Cervesato A (2024) Urban Architectural Heritage and Climate Change. An opportunity to address its complexity. Agathon - International Journal of Architecture, Art and Design 16:130–143. https://doi.org/10.19229/2464-9309/16112024
- 4. Nastou MPP, Zerefos SC (2024) Effects of climate change on open air heritage: a review and the situation in the region of Mediterranean. Heritage Science 12:1–25. https://doi.org/10.1186/s40494-024-01484-y
- 5. Russo M, Manferdini AM (2014) Integration of image and range-based techniques for surveying complex architectures. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences 2:305–312. https://doi.org/10.5194/isprsannals-II-5-305-2014
- 6. Mendoza MAD, De La Hoz Franco E, Gómez JEG (2023) Technologies for the Preservation of Cultural Heritage-A Systematic Review of the Literature. Sustainability 15:1-28. https://doi.org/10.3390/su15021059
- 7. Silva C, Oliveira L (2024) Artificial Intelligence at the Interface between Cultural Heritage and Photography: A Systematic Literature Review. Heritage 7:3799–3820. https://doi.org/10.3390/heritage7070180
- 8. Zhao J, Hua X, Yang J, et al (2023) A Review of Point Cloud Segmentation of Architectural Cultural Heritage. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences 10:247–254. https://doi.org/10.5194/isprs-annals-x-1-w1-2023-247-2023
- 9. Zhang R, Wu Y, Jin W, Meng X (2023) Deep-Learning-Based Point Cloud Semantic Segmentation: A Survey. Electronics 12:1–25. https://doi.org/10.3390/electronics12173642
- 10. Mishra M, Zhang K, Mea C, et al (2024) Deep Learning-Based AI-Assisted Visual Inspection Systems for Historic Buildings and their Comparative Performance with ChatGPT-4O. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives 48:327–334. https://doi.org/10.5194/isprs-archives-XLVIII-2-W8-2024-327-2024
- 11. Lee SY, Cho HH (2023) Damage Detection and Safety Diagnosis for Immovable Cultural Assets Using Deep Learning Framework. In: International Conference on Advanced Communication Technology (ICACT). Global IT Research Institute (GiRI), pp 310–313. https://doi.org/10.23919/ICACT56868.2023.10079559
- 12. Meroño JE, Perea AJ, Aguilera MJ, Laguna AM (2015) Recognition of materials and damage on historical buildings using digital image classification. South African Journal of Science 111:1–9. https://doi.org/10.17159/sajs.2015/20140001
- 13. Kwon D, Yu J (2019) Automatic Damage Detection of Stone Cultural Property based on Deep Learning Algorithm. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives 42:639–643. https://doi.org/10.5194/isprs-archives-XLII-2-W15-639-2019
- 14. Grilli E, Remondino F (2019) Classification of 3D digital heritage. Remote Sensing 11:1–23. https://doi.org/10.3390/RS11070847
- 15. Fatiguso F, Buldo M (2020) Complesso della SS. Trinità di Venosa (PZ). In: De Fino M, Fatiguso F (eds) La diagnostica per gli edifici storici: Metodi non distruttivi e tecnologie innovative per la valutazione e il controllo. Collana Architettura sostenibile/culture costruttive per il recupero sostenibile. EdicomEdizioni, Monfalcone, Italy, pp 169–180
- 16. Latifi R, Hadzima-Nyarko M, Radu D, Rouhi R (2023) A Brief Overview on Crack Patterns, Repair and Strengthening of Historical Masonry Structures. Materials 16:1–22. https://doi.org/10.3390/ma16051882
- 17. Valero E, Forster A, Bosché F, et al (2019) Automated defect detection and classification in ashlar masonry walls using machine learning. Automation in Construction 106:102846. https://doi.org/10.1016/j.autcon.2019.102846
- 18. Buldo M, Agustín-Hernández L, Verdoscia C (2024) Semantic Enrichment of Architectural Heritage Point Clouds Using Artificial Intelligence: The Palacio de Sástago in Zaragoza, Spain. Heritage 7:6938–6965. https://doi.org/10.3390/heritage7120321
- 19. Matrone F, Felicetti A, Paolanti M, Pierdicca R (2023) Explaining AI: Understanding Deep Learning Models for Heritage Point Clouds. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences 10:207–214. https://doi.org/10.5194/isprs-annals-X-M-1-2023-207-2023
- 20. Buldo M, Agustín-Hernández L, Verdoscia C, Tavolare R (2023) A Scan-to-BIM workflow proposal for Cultural Heritage. Automatic point cloud segmentation and parametric-adaptive modelling of vaulted systems. Int Arch Photogramm Remote Sens Spat Inf Sci - ISPRS Arch 48:333–340. https://doi.org/10.5194/isprs-archives-XLVIII-M-2-2023-333-2023
- 21. Aricò M, Ferro C, La Guardia M, et al (2024) Scan-to-BIM Process and Architectural Conservation: Towards an Effective Tool for the Thematic Mapping of Decay and Alteration Phenomena. Heritage 7:6257–6281. https://doi.org/10.3390/heritage7110294
- 22. Tiribelli S, Pansoni S, Frontoni E, Giovanola B (2024) Ethics of Artificial Intelligence for Cultural Heritage: Opportunities and Challenges. IEEE Transactions on Technology and Society 5:293–305. https://doi.org/10.1109/TTS.2024.3432407
- 23. Ge C (2024) The review of AI and cultural heritage protection-Taking the whole process of cultural heritage protection as an example. Applied and Computational Engineering. pp 137–143. https://doi.org/10.54254/2755-2721/71/20241666
- 24. de Lachenal L (1998) L’Incompiuta di Venosa. Un’abbaziale fra propaganda e reimpiego. Mélanges l’Ecole française Rome Moyen-Age, Temps Modernes 110:299–315. https://doi.org/10.3406/mefr.1998.3628
- 25. Laviano R, Summa V (1999) Incompiuta di Venosa (Potenza): caratteri mineralogici, petrografici e chimici dei materiali utilizzati e loro provenienza. In: Mineralogica et Petrographica Acta. 42:211–222
- 26. Ente Italiano di Normazione (UNI) (2006) UNI 11182:2006 Cultural Heritage - Natural and artificial stone - Description of the alteration - Terminology and Definition
- 27. International Scientific Committee for Stone (ICOMOS) (2008) Illustrated Glossary on Stone Deterioration Patterns: Monuments and Sites
- 28. Arganda-Carreras I, Kaynig V, Rueden C, et al (2017) Trainable Weka Segmentation: A machine learning tool for microscopy pixel classification. Bioinformatics 33:2424–2426. https://doi.org/10.1093/bioinformatics/btx180
