Please use this identifier to cite or link to this item: https://dspace.mnau.edu.ua/jspui/handle/123456789/14102
Title: Improving a neural network model for semantic segmentation of images of monitored objects in aerial photographs
Authors: Petrova, Olena
Петрова, Олена Іванівна
Slyusar, Vadym
Protsenko, Mykhailo
Chernukha, Anton
Melkin, Vasyl
Kravtsov, Mikhail
Velma, Svitlana
Kosenko, Nataliia
Sydorenko, Olga
Sobol, Maksym
Keywords: Aerial photograph
Convolutional neural network
Semantic segmentation of images
Unmanned aerial vehicle
Object Detection
Deep Learning
IOU
Issue Date: 2021
Publisher: Mykolayiv National Agrarian University
Central Scientific Research Institute of Armament and Military Equipment of the Armed Forces of Ukraine
National University of Civil Defence of Ukraine
Kharkiv National Automobile and Highway University
National University of Pharmacy
O. M. Beketov National University of Urban Economy in Kharkiv
National Technical University “Kharkiv Polytechnic Institute”
Citation: Slyusar, V., Protsenko, M., Chernukha, A., Melkin, V., Petrova, O., Kravtsov, M., . . . Sobol, M. (2021). Improving a neural network model for semantic segmentation of images of monitored objects in aerial photographs. Eastern-European Journal of Enterprise Technologies, 6(2-114), 86-95. doi:10.15587/1729-4061.2021.248390
Abstract: This paper considers a model of the neural network for semantically segmenting the images of monitored objects on aerial photographs. Unmanned aerial vehicles monitor objects by analyzing (processing) aerial photographs and video streams. The results of aerial photography are processed by the operator in a manual mode; however, there are objective difficulties associated with the operators handling a large number of aerial photographs, which is why it is advisable to automate this process. Analysis of the models showed that to perform the task of semantic segmentation of images of monitored objects on aerial photographs, the U-Net model (Germany), which is a convolutional neural network, is most suitable as a basic model. This model has been improved by using a wavelet layer and the optimal values of the model training parameters: speed (step) − 0.001, the number of epochs — 60, the optimization algorithm — Adam. The training was conducted by a set of segmented images acquired from aerial photographs (with a resolution of 6,000×4,000 pixels) by the Image Labeler software in the mathematical programming environment MATLAB R2020b (USA). As a result, a new model for semantically segmenting the images of monitored objects on aerial photographs with the proposed name U-NetWavelet was built. The effectiveness of the improved model was investigated using an example of processing 80 aerial photographs. The accuracy, sensitivity, and segmentation error were selected as the main indicators of the models efficiency. The use of a modified wavelet layer has made it possible to adapt the size of an aerial photograph to the parameters of the input layer of the neural network, to improve the efficiency of image segmentation in aerial photographs; the application of a convolutional neural network has allowed this process to be automatic.
URI: https://dspace.mnau.edu.ua/jspui/handle/123456789/14102
Appears in Collections:Публікації науково-педагогічних працівників МНАУ у БД Scopus
Статті (Факультет ТВППТСБ)

Files in This Item:
File Description SizeFormat 
Petrova-2021-1.pdf1,2 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.