Journals / Eskiz: Şehir ve Bölge PLanlama Dergisi / 2026 / Cilt: 08

COMPUTER VISION-SUPPORTED URBAN CONSERVATION: AN EVALUATION ON SİİRT HISTORICAL CITY CENTER

BİLGİSAYARLI GÖRÜ DESTEKLİ KENTSEL KORUMA: SİİRT TARİHİ KENT MERKEZİ ÜZERİNE BİR DEĞERLENDİRME

Pages
—
Publication Date
2026-09-14
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

These findings indicate that computer vision systems should be positioned as a "human-in-the-loop" decision support mechanism necessitating expert human supervision, rather than as autonomous decision-makers.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:The urban conservation discipline faces sustainable documentation challenges, particularly in large-scale historical areas bearing the risk of rapid deterioration, due to the labor-intensive, costly, and time-consuming nature of traditional methods.
📊
Key Findings & Data:Analyses conducted using the X-AnyLabeling tool on a visual dataset comprising 90 images obtained from the Siirt Historical City Center revealed that the computer vision model exhibits high success and statistical consistency in detecting damages with geometric clarity, particularly in cases of loss of joint mortar and plaster detachment.
💡
Conclusion & Impact:These findings indicate that computer vision systems should be positioned as a "human-in-the-loop" decision support mechanism necessitating expert human supervision, rather than as autonomous decision-makers.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:bilgisayarlı görü · görüntü işleme · Grounding DINO

Abstract

The urban conservation discipline faces sustainable documentation challenges, particularly in large-scale historical areas bearing the risk of rapid deterioration, due to the labor-intensive, costly, and time-consuming nature of traditional methods. In this study, the usage potential and limitations of computer vision Technologies, specifically deep learning-based semantic segmentation and object detection algorithms, in the documentation and conservation processes of architectural heritage are examined through the case of the Siirt Historical City Center. The primary objective of the research is to measure the automated detection success of material deteriorations on historical building surfaces utilizing the Grounding DINO model based on an "Open Vocabulary" architecture, and to discuss the practical implications of this digital approach in conservation practice. Analyses conducted using the X-AnyLabeling tool on a visual dataset comprising 90 images obtained from the Siirt Historical City Center revealed that the computer vision model exhibits high success and statistical consistency in detecting damages with geometric clarity, particularly in cases of loss of joint mortar and plaster detachment. However, the study also revealed instances of "hallucination" where image processing technologies experienced "contextual blindness" such that commercial signboards and text-bearing panels were perceived by the algorithm as structural deterioration. These findings indicate that computer vision systems should be positioned as a "human-in-the-loop" decision support mechanism necessitating expert human supervision, rather than as autonomous decision-makers.

Özet

Kentsel koruma disiplini, geleneksel yöntemlerin yoğun emek gerektiren, maliyetli ve zaman alıcı doğası nedeniyle, özellikle geniş ölçekli ve hızlı bozulma riski taşıyan tarihi alanlarda sürdürülebilir belgeleme sorunlarıyla karşı karşıyadır. Bu çalışmada, mimari mirasın belgelenmesi ve korunması süreçlerinde bilgisayarlı görü teknolojilerinin, özellikle derin öğrenme tabanlı anlamsal segmentasyon ve nesne algılama algoritmalarının kullanım potansiyeli ve sınırları Siirt Tarihi Kent Merkezi örneği üzerinden incelenmektedir. Araştırmanın temel amacı, "Açık Kelime Hazinesi" mimarisine dayanan Grounding DINO modeli kullanılarak, tarihi yapı yüzeylerindeki malzeme bozulmalarının otomatik tespit başarısını ölçmek ve bu dijital yaklaşımın koruma pratiğindeki karşılığını tartışmaktır. Siirt Tarihi Kent Merkezi’nden elde edilen 90 adetlik görsel veri seti üzerinde X-AnyLabeling aracı ile gerçekleştirilen analizler, bilgisayarlı görü modelinin özellikle derz boşalmaları ve sıva dökülmeleri gibi geometrik netliğe sahip hasarları tespit etmede yüksek başarı ve istatistiksel tutarlılık sergilediğini ortaya koymuştur. Ancak çalışmada aynı zamanda görüntü işleme teknolojilerinin "bağlamsal körlük" yaşadığı, ticari tabelalar ve metin içeren levhaların algoritma tarafından yapısal bir bozulma olarak algılandığı "halüsinasyon" vakaları da ortaya çıkmıştır. Bu bulgular, bilgisayarlı görü sistemlerinin otonom bir karar verici olmaktan ziyade, insan uzman denetimini zorunlu kılan "insan döngülü" bir karar destek mekanizması olarak konumlandırılması gerektiğini göstermektedir.

🔖

Cite This Article

Dündar, S., Altuntaş, A. (2026). COMPUTER VISION-SUPPORTED URBAN CONSERVATION: AN EVALUATION ON SİİRT HISTORICAL CITY CENTER. Eskiz: Şehir ve Bölge PLanlama Dergisi, Cilt: 08. https://doi.org/10.5281/zenodo.22691253

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (27)

  1. Akın, C. T., Bekleyen, A. ve Yıldırım, M. (2016). Preservation Initiatives for the Truncated Pyramid-Shaped Traditional Houses of Siirt, Turkey, Frontiers of Architectural Research, 5 (3), 360–370. https://doi.org/10.1016/j.foar.2016.06.005
  2. AlSayyad, N. (2001). Consuming Tradition, Manufacturing Heritage, Routledge, London.
  3. Calvano, M., Calcerano, F., Martinelli, L. ve Gigliarelli, E. (2023). Digital Surveys for the Implementation of Heritage BIM. İçinde L. Carlevaris ve G.M. Valenti (Der.), Digital and Documentation, Reading and Communicating Cultural Heritage (ss.170-183) Publisher: Pavia University Press.
  4. Croce, V., Caroti, G., De Luca, L., Piemonte, A. ve Véron, P. (2020). Semantic Annotations on Heritage Models: 2D/3D Approaches and Future Research Challenges, The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLIII-B2-2020, 829–836. https://doi.org/10.5194/isprs-archives-XLIII-B2-2020-829-2020
  5. Doratli, N. (2005). Revitalizing Historic Urban Quarters: A Model for Determining the Most Relevant Strategic Approach, European Planning Studies, 13(5), 749–772. https://doi.org/10.1080/09654310500139558
  6. Dore, C. ve Murphy, M. (2017). Current State of the Art Historic Building Information Modelling. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLII-2/W5, 185–192. https://doi.org/10.5194/isprs-archives-XLII-2-W5-185-2017
  7. Dündar, S. (2026). Bilgisayarlı görü destekli kentsel koruma: Siirt tarihi kent merkezi üzerine bir değerlendirme [Yayınlanmamış Yüksek Lisans Tezi]. Fen Bilimleri Enstitüsü, Siirt Üniversitesi, Siirt.
  8. Ergün, R. ve Bekleyen, A. (2025). An Architectural Taxonomic Proposal for Passive Design Strategies Used in Traditional Architecture of Areas with Hot and Dry Climates, Journal of Engineering Research, 13 (3), 2234-2251. https://doi.org/10.1016/j.jer.2024.05.019
  9. Fai, S. ve Sydor, M. (2013). Building Information Modelling and the Documentation of Architectural Heritage: Between the ‘Typical’ and the ‘Specific’. 2013 Digital Heritage International Congress (DigitalHeritage), 1, 731-734. https://doi.org/10.1109/DigitalHeritage.2013.6743828
  10. Ghaith, K. (2024). AI Integration in Cultural Heritage Conservation – Ethical Considerations and the Human Imperative. International Journal of Emerging and Disruptive Innovation in Education:Visionarium, 2 (1), 6.
  11. Grilli, E. ve Remondino, F. (2019). Classification of 3D Digital Heritage, Remote Sensing, 11 (7), 847.
  12. Letellier, R. ve Eppich, R. (2011). Recording, Documentation and Information Management for the Conservation of Heritage Places, Routledge, 388. ISBN: 9781873394946.
  13. Matrone, F., Grilli, E., Martini, M., Paolanti, M., Pierdicca, R. ve Remondino, F. (2020). Comparing Machine and Deep Learning Methods for Large 3D Heritage Semantic Segmentation, ISPRS International Journal of Geo-Information, 9(9), 535. https://doi.org/10.3390/ijgi9090535
  14. Mociran, H. A. ve Lapuste, A.V. (2025). Structural Health Monitoring of Buildings Using Computer Vision: A State-of-the-Art Review, Engineering and Technology Quarterly Reviews, 8(2), 35-45. https://doi.org/10.5281/zenodo.17625389
  15. Orbaşlı, A. (2000). Tourists in Historic Towns: Urban Conservation and Heritage Management, Taylor & Francis, London, 224 p. https://doi.org/10.2307/4126422
  16. Orbaşlı, A. (2008). Architectural Conservation: Principles and Practice, Wiley-Blackwell, Oxford, 240 p. ISBN: 978-0-632-04025-4
  17. Orta, N. (2024). Somut Olmayan Kültürel Mirasın Korunmasında Yapay Zekâ, Veri Bilimi ve Makine Öğrenmesinden Yararlanma. RumeliDE-Dil ve Edebiyat Araştırmaları Dergisi, (38), 748- 777. https://doi.org/10.29000/rumelide.1439731
  18. Parlak, S., Kunt, H. İ. ve Kocadağıstan, M. (2013). Siirt Ulu Camii Minaresi ve 2008 Yılı Restorasyonu, Hacettepe Üniversitesi Edebiyat Fakültesi Dergisi, 30(1), 167-198. https://izlik.org/JA89JZ28NM
  19. Qiu, H., Zhang, J., Zhuo, L., Xiao, Q., Chen, Z. ve Tian, H. (2024). Research on Intelligent Monitoring Technology For Roof Damage of Traditional Chinese Residential Buildings Based on Improved Yolov8: Taking Ancient Villages in Southern Fujian as an Example, Heritage Science, 12, 231. https://doi.org/10.1186/s40494-024-01345-8
  20. Remondino, F., Barazzetti, L., Nex, F., Scaioni, M. ve Sarazzi, D. (2011). UAV Photogrammetry for Mapping and 3D Modeling: Current Status and Future Perspectives. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume XXXVIII-1/C22, ss. 25-31. https://doi.org/10.5194/isprsarchives-XXXVIII-1-C22-25-2011
  21. Rypkema, D.D. (2005). The Economics of Historic Preservation: A Community Leader’s Guide. National Trust for Historic Preservation.
  22. Shivottam, J. ve Mishra, S., 2023. Tirtha – An automated platform to crowdsource images and create 3D models of heritage sites, arXiv:2308.01246, [online], https://arxiv.org/abs/2308.01246
  23. Siirt Belediyesi İmar ve Şehircilik Müdürlüğü. (2021). Siirt İmar Planı. Siirt Belediyesi.
  24. Tan, M., ve Bayezit, G. (2023). Kent Kimliğinin Mekânsal Yansımaları: Siirt Güres Caddesi Örneği, International Journal of Innovative Approaches in Social Sciences, 7(3), 127-141. https://doi.org/10.29329/ijiasos.2023.607.1
  25. Westenberger, P. ve Farmaki, D. (2025). Artificial Intelligence for Cultural Heritage Research: The Challenges in UK Copyright Law and Policy, European Journal of Cultural Management and Policy, 15: 14009. https://doi.org/10.3389/ejcmp.2025.14009
  26. Yang, S., Zheng, L., Chen, Y., Huang, Y. ve Huang, Y. (2025). Artificial Intelligence Assists the Identification and Application of Rural Heritage Wall Surface Damage in Zhejiang. npj Heritage Science, 13, 143. https://doi.org/10.1038/s40494-025-01725-8
  27. Zancheti, S.M., ve Jokilehto, J.I. (1997). Values and Urban Conservation Planning: Some Reflections on Principles and Definitions, Journal of Architectural Conservation, 3, 37-51. https://doi.org/10.1080/13556207.1997.10785179