Automatic detection of moistures in different construction materials from thermographic images

Abstract

Moisture is a pathology that damages all type of construction materials, from materials of building envelopes to materials of bridges. Its presence can negatively affect the users' conditions of indoor comfort. Furthermore, heating and cooling energy demand can be increased by the presence of moist materials. Infrared thermography (IRT) is a common technique in the scientific field to detect moisture areas, because of its non-destructive, non-contact nature. In addition, IRT allows an earlier moisture detection compared to the analysis using visible images. In order to optimize thermographic inspections, this paper presents one of the first methodologies for the automatic detection of moisture areas affecting the surface of construction materials. The methodology is based on the application of visible image processing techniques adapted to thermographic images through the consideration of an image conversion format, a thermal criterion and a thermal and a geometric filter. The precision, recall and F-score parameters obtained are around 83.5%, 73.5% and 72.5%, respectively, considering the false positives/negatives through a series of 12 tests made in different construction materials and ambient conditions, comparing the preliminary results with existing methodologies. Keywords Moisture Á Infrared thermography Á Automation Á Adapted visible image processing Á Construction materials Á Different environmental conditions & I. Garrido

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

“…This is based on the thermal criterion that the temperature distribution of a thermal image of a structure, with areas affected by pathologies, presents an approximate bimodal distribution. In other words, the thermal image histogram of a heritage element with moisture areas consists roughly of a combination of two Gaussian distributions, one belonging to the unaltered zones and the other to the pathology (Garrido et al, 2019). Thus, by counting the number of maximum peaks in the histogram of the thermal image, it can automatically be determined whether (2 maximums peaks) or not (more or less than 2 maximums peaks) a material will have anomalous areas.…”

“…More examples of passive IRT are: i) Garrido et al (2018b) and Garrido et al (2019), which search moisture areas on surfaces of internal/external walls and of construction materials of different scale sizes, respectively (qualitative IRT), ii) Barreira et al (2016), who assess moisture related phenomena in building components (qualitative IRT), iii) Georgescu et al (2017), who monitor the interior of a church to evaluate improvements made after restoration works in search of moisture areas to remove (qualitative IRT), and iv) Barreira et al (2017), who analyse the humidification phenomena in lightweight concrete specimens, both in qualitative and quantitative IRT.…”

“…As will be seen in Section 2, there are several investigations focusing on the application of IRT to moisture analysis. However, all these IRT studies require the interpretation of the data by a human operator, increasing the risk of a wrong assessment due to the high-level of subjectivity and dependence on the expertise of the operator, except for Garrido et al (2018b) and Garrido et al (2019). Then, with the aim of taking a step forward towards the automation of the inspection process and optimization of the decision-taking in conservation actions within cultural heritage, this work presents a methodology for the automatic detection and characterization of moisture in heritage elements, from the thermal images acquired with IRT.…”

Assessing Rebar Corrosion through the Combination of Nondestructive GPR and IRT Methodologies

“…The thermographic study was made with a two-fold approach: on one hand, the temperature profile of each image was studied in order to identify the presence of pathologies based on the temperature anomaly they imply. On the other hand, each image was subjected to a filtering process, as in [27], for the delimitation of the pathologies in the image, focusing on their two dimensions. This process is based on two assumptions:…”

Quantitative Infrared Thermography to Evaluate the Humidification of Lightweight Concrete

“…This non-contact and non-destructive technique was used to assess buildings for a couple of decades [1][2][3][4][5][6]. Particularly, when used to evaluate moisture problems [7][8][9][10][11][12], thermal patterns can result from (a) evaporative cooling at the moist area as evaporation decreases surface temperature [13][14][15][16][17][18][19], (b) reduced thermal resistance of the wet materials [20,21], and (c) increased heat storage capacity of the moist material [22,23].…”