Applied photogrammetry systems, which act as measuring instruments, are often influenced by the external environment and operating conditions, which determine the accuracy of the results. In this regard, the problem of dynamic adjustment of algorithms for these changing conditions arises. To avoid an increase in the likelihood of human error and to reduce the requirements for personnel qualifications, you can resort to the tools of intelligent systems. For these purposes, the development of appropriate components is required, including machine learning tools. This article proposes a method and procedure for machine learning of the photogrammetric algorithm based on the observation of operator actions and a system of production rules.

Keywords: inductive learning, machine learning, photogrammetry, pattern recognition, photogrammetry, forestry, pipe industry, measurement, mobile app, automation