Abstract
Weathering effects caused by physical, chemical, or biological processes result in visible damage that alters the appearance of stones’ surfaces. Consequently, weathered stone monuments can offer a distorted perception of the artworks to the point of making their interpretation misleading. Being able to detect and monitor decay is crucial for restorers and curators to perform important tasks, such as identifying missing parts, assessing the preservation state, or evaluating curating strategies. Decay mapping, the process of identifying weathered zones of artworks, is essential for preservation and research projects. This is usually carried out by marking the affected parts of the monument on a two-dimensional (2D) drawing or picture of it. One of the main problems of this methodology is that it is manual work based only on experts’ observations. This makes the process slow and often results in disparities between the mappings of the same monument made by different experts. In this article, we focus on the weathering effect known as “scaling,” following the International Council on Monuments and Sites, International Scientific Committee for Stone (ICOMOS ISCS) definition. We present a novel technique for detecting, segmenting, and classifying these effects on stone monuments. Our method is user-friendly, requiring minimal user input. By analyzing 3D reconstructed data considering geometry and appearance, the method identifies scaling features and segments weathered regions, classifying them by scaling subtype. It shows improvements over previous approaches and is well received by experts, representing a significant step toward objective stone decay mapping.
- [1] . 2021. Automatizing degradation mapping of ancient stelae by dual-band imaging and machine learning-based classification. In ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences VIII-M-1-2021 (2021), 9–16.
DOI: Google ScholarCross Ref - [2] . 2020. Combined use of ultrasonic pulse velocity (UPV) testing and digital technologies: A model for long-term condition monitoring memorials in historic Grove Street Cemetery, New Haven. J. Cult. Herit. 41 (2020), 84–95.
DOI: Google ScholarCross Ref - [3] . 2020. Data-driven structural health monitoring and damage detection through deep learning: State-of-the-art review. Sensors 20, 10 (2020).
DOI: Google ScholarCross Ref - [4] . 2018. Graph-cut RANSAC. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 6733–6741.Google ScholarCross Ref
- [5] . 2019. Deep learning-based automatic volumetric damage quantification using depth camera. Autom. Construct. 99, March (2019), 114–124.Google ScholarCross Ref
- [6] . 2015. Defining, mapping and assessing deterioration patterns in stone conservation projects. J. Cult. Herit. 16, 3 (2015), 267–275.
DOI: Google ScholarCross Ref - [7] . 2004. Efficient graph-based image segmentation. Int. J. Comput. Vis. 59, 2 (2004), 167–181.Google ScholarDigital Library
- [8] . 2020. Machine learning for cultural heritage: A survey. Pattern Recogn. Lett. 13, May (2020), 102–108.
DOI: Google ScholarCross Ref - [9] . 2002. Damage index for stone monuments. In Protection and Conservation of the Cultural Heritage of the Mediterranean Cities, and (Eds.). Swets & Zeitlinger, Lisse, The Netherlands, 315–326.Google Scholar
- [10] . 1997. Weathering forms at natural stone monuments: Classification, mapping and evaluation/Verwitterungsformen an Natursteinbauwerken: Klassifizierung, Kartierung und Auswertung. Restor. Build. Monuments 3, 2 (1997), 105–124.
DOI: DOI: https://doi.org/doi:10.1515/rbm-1997-0204Google ScholarCross Ref - [11] . 2019. Classification of 3D digital heritage. Remote. Sens. 11, 7 (2019), 847.Google ScholarCross Ref
- [12] . 2020. Determining the weathering classification of stone cultural heritage via the analytic hierarchy process and fuzzy inference system. J. Cult. Herit. 44, July-August, (2020), 120–134.
DOI: Google ScholarCross Ref - [13] . 2020. Deep learning-based weathering type recognition in historical stone monuments. J. Cult. Herit. 45, September-October (2020), 193–203.
DOI: Google ScholarCross Ref - [14] . 2021. Intelligent detection of deterioration in cultural stone heritage. J. Build. Eng. 44, 12 (2021), 102690.Google ScholarCross Ref
- [15] . 2008. Monuments and Sites XV—Illustrated Glossary on Deterioration patterns. ICOMOS International Scientific Committee for Stone.Google Scholar
- [16] . 2022. Geometric primitive extraction from semantically enriched point clouds. Int. Arch. Photogram. Remote Sens. Spat. Inf. Sci. 46, 2/W1 (2022), 291–298.Google ScholarCross Ref
- [17] . 2022. Multi-defect segmentation from façade images using balanced copy–paste method. Comput.-Aid. Civil Infrastruct. Eng. 37, 11 (2022), 1434–1449.Google ScholarCross Ref
- [18] . 2022. A performance improvement strategy for concrete damage detection using stacking ensemble learning of multiple semantic segmentation networks. Sensors 22, 9 (2022), 3341.Google ScholarCross Ref
- [19] . 2023. Surface damage identification for heritage site protection: A mobile crowd-sensing solution based on deep learning. J. Comput. Cult. Herit. 16, 2 (2023), 25:1–25:24.
DOI: Google ScholarDigital Library - [20] . 2018. An ontological model for the reality-based 3D annotation of heritage building conservation state. J. Cult. Herit. 29, January-February (2018), 100–112.
DOI: Google ScholarCross Ref - [21] . 2021. Machine learning techniques for structural health monitoring of heritage buildings: A state-of-the-art review and case studies. J. Cult. Herit. 47, January-February (2021), 227–245.
DOI: Google ScholarCross Ref - [22] . 2017. Towards semi-automatic scaling detection on flat stones. In Eurographics Workshop on Graphics and Cultural Heritage. 49–58.Google ScholarDigital Library
- [23] . 2002. Mesh smoothing by adaptive and anisotropic Gaussian filter applied to mesh normals. In Vision, Modeling, and Visualization. IOS Press Amsterdam, The Netherlands, 203–210.Google Scholar
- [24] . 2020. Another brick in the wall: Improving the assisted semantic segmentation of masonry walls. In Eurographics Workshop on Graphics and Cultural Heritage. The Eurographics Association.Google Scholar
- [25] . 2007. Efficient RANSAC for point-cloud shape detection. In Computer Graphics Forum, 26, May. Wiley Online Library, 214–226.Google ScholarCross Ref
- [26] . 2014. Developing a toolkit for mapping and displaying stone alteration on a web-based documentation platform. J. Cult. Herit. 15, 1 (2014), 1–9.
DOI: Google ScholarCross Ref - [27] . 2007. Fast and effective feature-preserving mesh denoising. IEEE Trans. Vis. Comput.r Graph. 13, 5 (2007), 925–938.Google ScholarDigital Library
- [28] . 2008. Quick shift and kernel methods for mode seeking. In Proceedings of the 10th European Conference on Computer Vision (ECCV ’08) Part IV 10. Springer, 705–718.Google ScholarCross Ref
- [29] . 2018. Damage classification for masonry historic structures using convolutional neural networks based on still images. Comput.-Aid. Civil Infrastruct. Eng. 33, 12 (2018), 1073–1089.Google ScholarDigital Library
- [30] . 2019. Automatic damage detection of historic masonry buildings based on mobile deep learning. Autom. Construct. 103, July (2019), 53–66.Google ScholarCross Ref
- [31] . 2020. Autonomous damage segmentation and measurement of glazed tiles in historic buildings via deep learning. Comput.-Aid. Civil Infrastruct. Eng. 35, 3 (2020), 277–291.Google ScholarDigital Library
- [32] . 2003. Condition assessment for building stone conservation: A staging system approach. Build. Environ. 38, 9–10 (2003), 1113–1123.
DOI: Google ScholarCross Ref
Index Terms
- A 3D Feature-based Approach for Mapping Scaling Effects on Stone Monuments
Recommendations
Inscription Segmentation Using Synthetic Inscription Images for Text Detection at Stone Monuments
Document Analysis and Recognition – ICDAR 2021 WorkshopsAbstractStone monuments have historical value, and the inscriptions engraved on them can tell us about the events and people at the time of their installation. Photography is an easy way to record inscriptions; however, the light falling on the monument, ...
The Elephant Stone - Tracing a New Path for the Digital Approach to Unsurveyable Monuments
VSMM '09: Proceedings of the 2009 15th International Conference on Virtual Systems and MultimediaAbstract— The stone of the elephant is a well known monument in the northern part of Sardinia, one of the main island in the Mediterranean sea. It is a large volcanic stone with a particular shape which recall the shape of an elephant. The natural ...
Mapping MPEG-7 to CIDOC/CRM
TPDL'11: Proceedings of the 15th international conference on Theory and practice of digital libraries: research and advanced technology for digital librariesThe MPEG-7 is the dominant standard for multimedia content description; thus, the audiovisual Digital Library contents should be described in terms of MPEG-7. Since there exists a huge amount of audiovisual content in the cultural heritage domain, it is ...
Comments