AIRPLANES DETECTION IN AERIAL IMAGES USING YOLO NEURAL NETWORK

Abstract

Purpose: The represented research results are aimed to benchma rk performance of state-of-the-art methods of objects detection. There were tested two popular single-stage neural networks based on the “you only looks once” approach. Methods: convolutional neural network, logi stic regression, probabilistic theory, stochastic gradient descent. Results: The considered artificial neural network architectures for objects detection has been trained and applied for the particul ar task of the airplanes detection in aerial images taken from unmanned aerial vehicles and satellites. Discussion: Presented results of experimental verification prove their high detection ability, lo cation precision and real-time processing speed using modern graphics processing unit. The considered neural networks can be easily re-trained for detection of different classes of ground objects

Authors and Affiliations

Volodymyr Kharchenko, Iurii Chyrka

Keywords

Related Articles

NUMERICAL SIMULATION OF DYNAMICS OF ELASTIC TUBULAR SPIRALS CONVEYING INTERNAL MASSES OF NONHOMOGENEOUS BOILING LIQUID

The computer simulation problem of the dynamics of elastic tube serpentines with internal flows of boiling liquid is set up. The clots motion model of the non-homogeneous boiling liquid is proposed. The numerical solutio...

ACOUSTIC RADIATION ENERGY AT A VARIATION OF THE COMPOSITE MECHANICAL DESTRUCTION AREA

Purpose: The technological parameters of composite materials machining and also cutting tool state determine deforming and destruction of their surface layers conditions. Change of this conditi...

THE ISSUE OF OPTIMIZATION OF THE LEGAL REGULATION OF CERTIFICATION OF GENERAL AVIATION AIRCRAFT: DOMESTIC AND INTERNATIONAL EXPERIENCE

Purpose: to reveal directions of optimization of the legal adjusting of certification of air ships of general aviation, by realization of analysis of rules, procedure and subjects of registration of civil air ships and p...

RAISING LEVEL OF FLIGHT SAFETY DURING AGRICULTURAL-AIR WORKS

The article presents an analysis of the causes of a serious incident that occurred during the aircraftchemical works on the An-2 plane. Objective: The aim of this work is to investigate the causes of aircraft collisions...

TRENDS IN VOCATIONAL TRAINING OF PHARMACISTS IN UKRAINE

Purpose: In the article there has been substantiated the practicality of analysing trends emerging in the contemporary vocational training system of pharmacists- to-be in higher medical educat...

Download PDF file
  • EP ID EP510264
  • DOI 10.18372/2306-1472.76.13149
  • Views 129
  • Downloads 0

How To Cite

Volodymyr Kharchenko, Iurii Chyrka (2018). AIRPLANES DETECTION IN AERIAL IMAGES USING YOLO NEURAL NETWORK. Вісник Національного Авіаційного Університету, 76(3), 8-15. https://europub.co.uk/articles/-A-510264