Algorithms for the Automatic Detection and Characterization of Pathologies in Heritage Elements From Thermographic Images

Abstract

Heritage elements, from historic buildings to stone sculptures and panels, stand as key elements in the history of humanity. Unfortunately, the deterioration of both the surface and the interior of these elements is inevitable, endangering the quality and existence of these structures of high historical value in the event of a delay in the implementation of the required maintenance tasks. InfraRed Thermography, IRT, appears as one of the most recent techniques to detect and characterize possible pathologies in structures in their early stages, being very useful for a preventive analysis in heritage elements. This paper presents a methodology for the automatic detection and characterization of one of the most severe and frequent pathologies in heritage structures, moisture, from thermal images. The proposal stands as a demonstration of the potential of the IRT technique for heritage conservation applications, and as a new step towards the automation of the inspection process and optimization of the decision-taking in conservation actions within cultural heritage. For that, two thermal criteria and a semiautomatic image rectification process are implemented as main phases of the methodology, obtaining good results for the detection of moisture zones and accurate area values with regard to the real dimensions of each moisture zone. Specifically, an F-score average of 78%±19% regarding detection performance and a percentage relative error of minimum 4%, and maximum of 12%, referred to the area computation in unit metrics are obtained.

Development of Thermal Principles for the Automation of the Thermographic Monitoring of Cultural Heritage

“…Despite the problem of high reflectivity index, an issue that must be mitigated in the mosaic in future works, similar results are obtained in comparison with the results of methodologies that automatically delimit contours of the thermal footprints of moisture from single thermal images [ 18 , 22 ] both in precision , recall and F-score . Table 3 shows the average and standard deviation values of the performance metrics represented in Figure 10 :…”

“…In [ 15 ], the presence of concrete deterioration, water seepage, cover delamination and significant cracks were detected and, in [ 16 ], the most relevant damages produced in the structures by an earthquake are revealed. Moreover, Solla et al [ 17 ] detected moisture in a masonry arch bridge through Ground-Penetrating Radar (GPR), photogrammetry and IRT, and Garrido et al [ 18 ] automatically delimited and geometrically characterized different moisture areas from three ancient walls. As for paintings, Cadelano et al [ 19 ] assessed the decomposition of fresco mural painting inside a medieval chapel through the detection of the presence of water on the decorated surfaces and inside the walls, while Sfarra et al [ 20 ] studied the state of a mural painting with IRT in combination with other NDTs and micro-destructive analytical techniques, identifying a sandwich structure having the interstitial void full of moisture.…”

IRT and GPR Techniques for Moisture Detection and Characterisation in Buildings

“…It should be noted that all the steps are based on the fact that areas affected by moisture produce a Gaussian temperature distribution on the histogram of the thermal images, which is independent of the Gaussian temperature distribution presented by the unaltered zones. This assumption has been proved in previous papers published by the authors of this work [ 20 , 28 , 49 , 59 ]. In addition, the thermal images are automatically processed in all the steps.…”

Automation of Thermal Point Clouds Analysis for the Extraction of Windows and Thermal Bridges of Building Facades

“…This procedure uses both geometric characteristics and temperature differences with the surroundings. Besides thermal bridges, methodologies are also developed to detect and characterize pathologies in structures (Garrido et al, 2019).…”