Aerospace Instrument-Making Annotation << Back AN INTELLIGENT ALGORITHM FOR RECOGNIZING STRUCTURAL MATERIALS OF HIDDEN SUBSURFACE REMOTE MONITORING OBJECTS BASED ON THE DATA OF ESTIMATION OF THEIR THERMOPHYSICAL PARAMETERS USING DEEP LEARNING Yu.Yu. Gromov, I.N. Ishchuk, A.M. Filimonov, A.A. Zenkin The article presents a neural network algorithm for processing multi-time images obtained using a multispectral optoelectronic system of an unmanned aerial vehicle. To analyze the visibility of objects when conducting infrared reconnaissance, it is very important to know the patterns of temperature changes both on the earth's surface itself and remote monitoring objects. A mathematical model of thermophysical processes has been formed to obtain numerical estimates of the thermophysical parameters of hidden subsurface objects based on a genetic algorithm depending on the geometric, thermophysical parameters of the located objects and external factors. Based on an intelligent algorithm for recognizing structural materials of hidden subsurface objects of remote monitoring based on estimates of their thermophysical parameters using deep learning, the phono-target situation is segmented in the visible and infrared wavelength ranges by types of models (single-layer model of anthropogenic soil and three-layer model of a hidden subsurface object in the ground) using deep learning with a teacher, at the same time, the recognition of structural materials of hidden subsurface objects is performed on the basis of a genetic algorithm that implements the solution of the coefficient inverse problem of thermal conductivity with obtaining estimates of the thermophysical parameters of materials.The article presents an analysis of changes in the radiation and thermaodynamic temperatures of materials and backgrounds during the day, for their further comparison and determination of the rational characterristics of the observed process with theuse of optical-electronic systemof unmanned aerial vehicles. Keywords: mathematical model, segmentation, processing, image, modeling, processing. DOI: 10.25791/aviakosmos.3.2023.1328 Pp. 23-35.