PROBABILISTIC APPROACH TO OBJECT DETECTION AND RECOGNITION FOR VIDEOSTREAM PROCESSING

Abstract

Purpose: The represented research results are aimed to improve theoretical basics of computer vision and artificial intelligence of dynamical system. Proposed approach of object detection and recognition is based on probabilistic fundamentals to ensure the required level of correct object recognition. Methods: Presented approach is grounded at probabilistic methods, statistical methods of probability density estimation and computer-based simulation at verification stage of development. Results: Proposed approach for object detection and recognition for video stream data processing has shown several advantages in comparison with existing methods due to its simple realization and small time of data processing. Presented results of experimental verification look possible for object detection and recognition in video stream. Discussion: The approach can be implemented in dynamical system within changeable environment such as remotely piloted aircraft systems and can be a part of artificial intelligence in navigation and control systems.

Authors and Affiliations

Volodymyr Kharchenko, Alexander Kukush, Nataliia Kuzmenko, Ivan Ostroumov

Keywords

Related Articles

THE USE OF DIFFERENTIAL TRANSFORMATIONS FOR SOLVING NON-LINEAR BOUNDARY VALUE PROBLEMS

Purpose: The aim of our study is comparison of method applications based on differential transformations for solving boundary value problems which are described by non-linear ordinary differential equations. Methods: Thi...

SIMULATION OF PRECISION ATTITUDE AND HEADING REFERENCE SYSTEM PERTURBED BY ENVIRONMENTAL DISTURBANCES

Purpose: The paper focuses on problems of simulation of perturbed robust precision attitude and heading reference systems, which can be applied in navigation of marine vehicles. The main goal is to create the mathematica...

THE CONTROL OF INCIPIENT STATE TREATING TOOL WEAR WITH USAGE OF ACOUSTIC EMISSION

Purpose: The aim of this article is the experimental research of acoustic emission at composite material machining with the analysis of influencing treating tool wear from composite material on registered signals paramet...

COMPARATIVE ANALYSIS OF TECHNILOGIES OF CHITOSAN PRODUCTION FROM DEAD BEES

Objective: The aim of this work is to study the characteristics of technology of chitosan obtaining from unconventional sources, namely from dead bees. Methods: The article considers three methods of chitosan obtaining f...

APPROACHES TO FORMALIZATION OF MOTION DYNAMICS OF ARTIFICIAL FORCE FIELD METERS

Purpose: The aim of our study is to analyze virtual measurers with different functioning principles. In our case they are: a mathematical pendulum without quality factor, with quality factor...

Download PDF file
  • EP ID EP459676
  • DOI 10.18372/2306-1472.71.11741
  • Views 107
  • Downloads 0

How To Cite

Volodymyr Kharchenko, Alexander Kukush, Nataliia Kuzmenko, Ivan Ostroumov (2017). PROBABILISTIC APPROACH TO OBJECT DETECTION AND RECOGNITION FOR VIDEOSTREAM PROCESSING. Вісник Національного Авіаційного Університету, 71(2), 8-14. https://europub.co.uk/articles/-A-459676