Feature-Based Point Cloud-Based Assessment of Heritage Structures for Nondestructive and Noncontact Surface Damage Detection

Abstract

Assessment and evaluation of damage in cultural heritage structures are conducted primarily using nondestructive and noncontact methods. One common deployment is laser scanners or ground-based lidar scanners that produce a point cloud containing information at the centimeter to the millimeter level. This type of data allows for detecting surface damage, defects, cracks, and other anomalies based only on geometric surface descriptors using a single dataset, which does not rely on a change detection approach. Moreover, geometric features are not influenced by color, which is essential for heritage structures because they are nonuniform in color due to anthropologic and environmental effects (e.g., painting or moisture). In this work, a damage detection method developed based on local geometric features is evaluated and expanded for crack detection within the example fresco walls of Sala degli Elementi in the Palazzo Vecchio. The workflow’s performance is then compared in a qualitative manner to that of manual crack mapping results identified using images.

LiDAR-Based Structural Health Monitoring: Applications in Civil Infrastructure Systems

“…The proposed method was validated after being tested on an unseen heritage site, proving accurate damage detection of complex heritage structures. Through a voxelating process, the point-to-point spacing was made uniform, such that the damaged areas of the point cloud showed a different point distribution [79]. Based on the eigenvalues, neighboring points covariance matrix, normal vector variation, and mean curvature to its closest neighboring points of each point, the damage was detected and re-evaluated.…”

Segmentation in application to deformation analysis of cultural heritage surfaces

“…In [11], a segmentation method was developed to identify the damaged areas in heritage surfaces using local geometric variations computing on voxelated cloud. However, the method was limited in detecting cracks and other surface defects that result in a change in geometry equal to or larger than that of voxelating grid step size.…”