Method of neural network recognition of ground-based air objects
Ігор Вікторович Рубан, Kirill Smelyakov, Vitalii Martovytskyi, Pribylnov Dmitry, Nataliia Bolohova · 2018 IEEE 9th International Conference on Dependable Systems, Services and Technologies (DESSERT) · 2018
Present article describes the method, which allows to define a type of air vehicle in automatic mode during the processing of optoelectronic scouting images. The method is based on neural network technology of images recognition with processing of a prior received data by the network itself. This makes possible to increase the probability of correct recognition, as well as to take into account potential errors of exact parameters.