Browsing by Author "Kukush, Alexander"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    PROBABILISTIC APPROACH TO OBJECT DETECTION AND RECOGNITION FOR VIDEOSTREAM PROCESSING
    (Вісник Національного Авіаційного Університету, 2017) Харченко, Володимир Петрович; Kharchenko, Volodymyr; Kukush, Alexander; Кукуш, О.Г.; Kuzmenko, Nataliia; Кузьменко, Н.С.; Ostroumov, Ivan; Остроумов, І.В.
    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 plausible 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.
  • Thumbnail Image
    Item
    SIMPLE OBJECTS DETECTION AND RECOGNITION BY THE PROBABILISTIC APPROACH
    (Вісник Національного Авіаційного Університету, 2017-12-27) Kharchenko, Volodymyr; Kukush, Alexander; Chyrka, Iurii; Харченко, В.П.; Кукуш, О.Г.; Чирка, Ю.Д.; Харченко, Володимир Петрович
    Purpose: The represented research results are aimed to better understanding of computer vision methods and their capabilities. The statistical approach of object detection and recognition allows processing of typical objects with simple descriptors. Methods: Considered approach is grounded at probabilistic methods, kernel density estimation and computer-based simulation as a verification tool. Results: Considered approach for object detection and recognition 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 prove that the considered method can be applied for detection and classification of objects with various shapes. Discussion: The approach can be implemented in a variety of computer vision systems that observe objects in difficult noisy conditions.