AIRPLANES DETECTION IN AERIAL IMAGES USING YOLO NEURAL NETWORK
Journal Title: Вісник Національного Авіаційного Університету - Year 2018, Vol 76, Issue 3
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
- EP ID EP510264
- DOI 10.18372/2306-1472.76.13149
- Views 136
- Downloads 0
MODELS OF AIR TRAFFIC CONTROLLERS ERRORS PREVENTION IN TERMINAL CONTROL AREAS UNDER UNCERTAINTY CONDITIONS
Purpose: the aim of this study is to research applied models of air traffic controllers’ errors prevention in terminal control areas (TMA) under uncertainty conditions. In this work the theoretical framework descripting...
ECONOMIC EFFICIENCY ANALYSIS OF THE SYSTEM FOR METEOROLOGICAL DATA COLLECTION AND DESSEMINATION
In this paper, the system of meteorological information collection and dissemination that takes into account modern aviation requirements as well as technical achievements is presented. The study of the economic benefits...
COMPLEX USAGE OF CLAY USED MATERIALS
The article represents the results of research on th e application of technological wastes of aerosol gas dynamic suspension treatment of aircraft elements for the he avy metal ions sorption...
BUSINESS SIMULATIONS AS A COMPON ENT OF AN INNOVATIVE MODEL OF MODERN ECONOMIC EDUCATION
Purpose: In the article there has substantiated the au thor’s research viewpoint on understanding the essence of the notions of «innovation», «innovative model of development», specified the role and impo...
COMPLETE SEPARATION OF THE VERTICAL AND HORIZONTAL INDEPENDENT COMPONENTS OF THE FLIGHT IN POLICOPTER UAV NAU PKF "AURORA" AND MATHEMATICAL MODEL OF THIS FLIGHT
Purpose: This article presents a mathematical model and the experimental results of automatic flights of the policopter UAV NAU PKF "Aurora" of oktacopter scheme with additional elektroimpeler engines of horizontal thrus...