This paper presents Segmentation for Diagnose (Seg4D), a holistic tool for processing 3D point clouds in the field of historical constructions. This tool incorporates state-of-the-art algorithms for the segmentation and analysis of construction systems and damage. Seg4D applies both supervised and unsupervised machine learning and deep learning methods, including the Point Transformer Neural Network for point cloud segmentation. Additionally, it facilitates the extraction of geometrical and statistical features, colour-scale conversion, noise reduction with anisotropic filters and the use of custom scripts for analysing deflections in slabs or out-of-plane movements in arches and vaults, among others. The Seg4D installer and source code are are publicly available in a GitHub repository.
26 June 2023 in The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
This paper aims at evaluating the possibility of using wearable mobile mapping solutions as a tool for detecting deflections in timber floors. These construction systems are prone to present this type of damage due to the mechanical properties of the wood (relatively low flexural stiffness and creep behaviour). During this study we have evaluated the chance of introducing an additional stage to the general workflow. This stage is devoted to reduce the noise of the 3D point cloud by using the Statistical Outlier Removal filter in combination with a noise-reduction filter such as the Anisotropic filter, the PointCleannet or the Scored-based denoised networks (Deep Learning methods). According with our results, the use of this strategies improves the quality of the 3D point cloud form a qualitative and quantitative point of view. However, these improvements seem to be not sufficient for using this product as a universal source of information for deflection analysis. In this sense, and according with the sensor and study case exploited, this type of point clouds could be used in floors with 5-8-meter length and a relative deflection of about L/200 or higher.
Underground wine cellars represent a fragile form of cultural heritage, where long-term microclimatic imbalance can lead to material degradation, structural instability, and internal collapses. High humidity, limited ventilation, and the difficulty of access complicate both diagnosis and conservation. This study presents preliminary results from a preventive monitoring strategy applied to the underground wine cellars of Baltanás (Palencia, Spain), focusing on temperature, relative humidity, wall moisture content, and ventilation as key drivers of deterioration. A wireless network of commercial temperature–humidity sensors, wall moisture probes, and airflow sensors was deployed in four sections of a representative cellar over a monitoring period exceeding two years. In addition, mobile monitoring was performed using a quadruped robot equipped with a rotating environmental sensing module, enabling measurements in confined and unstable areas. Results reveal strong thermal inertia, persistently high relative humidity frequently approaching saturation, low and intermittent natural ventilation, and sustained internal wall moisture. These conditions are consistent with observed material decay and internal landslides. The monitoring with quadruped robot proved particularly valuable for identifying localized humidity pockets and stagnant air zones beyond the reach of fixed sensors. The study demonstrates how different solutions for monitoring can support preventive conservation strategies for subterranean heritage, providing a scalable framework for early risk detection and informed management decisions.
In the field of Cultural Heritage, 3D point clouds are pivotal for representing scenes with high resolution and accuracy. Although traditionally used for planimetries and computational modelling, this study explores their potential in diagnostics. A novel methodology is proposed that leverages 3D point clouds to evaluate deflection in historic timber slabs. By combining Artificial Intelligence with advanced 3D point cloud techniques, an approach is developed for detecting beam deflections with high precision. Specifically, a multi-resolution Random Forest classifier identifies beams and their faces, while deflection is computed using connected component and minimum bounding rectangle algorithms. Applied to timber slabs in the Nuestra Señora convent in Ávila. This methodology demonstrates promising results, achieving 99% accuracy in beam detection and a high degree of automation in deflection assessment. This approach offers significant advancements in the diagnostic capabilities of 3D point clouds in heritage conservation.