Metric contrast of thermal 3D models of large industrial facilities obtained by means of low-cost infrared sensors in UAV platforms

Monitoring for maintenance or studies of energy efficiency in buildings, large infrastructure, industrial facilities, etc., are common nowadays. These kind developed with inspections which determine the state facilities that analysed. The difficulty is increased along size and complexity facility itself, even more when attribute to be surveyed not noticeable responsive human eye. In recent years, a series techniques rely on different sensors mounted UAVs allow detecting problems associated dimensions. Almost all them work visible band (RGB), but generation thermal 3D models permits any heat anomaly related functioning these facilities. This research proposes methodology workflow Metric Contrast Thermal Models (MCTM). metrically applied mining-industrial conditions have great influence proper functioning. For this metric contrast, several distances been measured field compared those obtained from models. average difference between true magnitude RGB 5 31 cm, their standard deviations 7 29 respectively. comparison model provides an distance points 0.19 m, 75% lesser than 0.35 m. Although accurate, precision enough objectives set.