Кафедра інформаційних технологій і систем (ДМетІ)

Permanent URI for this community

http://crust.ust.edu.ua/handle/123456789/14593

UK: Кафедра інформаційних технологій і систем (Дніпровський металургійний інститут, ДМетІ) EN: Department of Information Technologies and Systems (DMetI)

Browse

Now showing 1 - 20 of 23

Aircraft Detection with Deep Neural Networks and Contour-Based Methods
(National University "Zaporizhzhia Polytechnic", Zaporizhzhia, 2024) Radionov, Y. D.; Kashtan, Vita Yu.; Hnatushenko, Volodymyr V.; Kazymyrenko, O. V.
ENG: Context. Aircraft detection is an essential task in the military, as fast and accurate aircraft identification allows for timely response to potential threats, effective airspace control, and national security. The use of deep neural networks improves the accuracy of aircraft recognition, which is essential for modern defense and airspace monitoring needs. Objective. The work aims to improve the accuracy of aircraft recognition in high-resolution optical satellite imagery by using deep neural networks and a method of sequential boundary traversal to detect object contours. Method. A method for improving the accuracy of aircraft detection on high-resolution satellite images is proposed. The first stage involves collecting data from the HRPlanesv2 dataset containing high-precision satellite images with aircraft annotations. The second stage consists of preprocessing the images using a sequential boundary detection method to detect object contours. In the third stage, training data is created by integrating the obtained contours with the original HRPlanesv2 images. In the fourth stage, the YOLOv8m object detection model is trained separately on the original HRPlanesv2 dataset and the dataset with the applied preprocessing, which allows the evaluation of the impact of additional processed features on the model performance. Results. Software that implements the proposed method was developed. Testing was conducted on the primary data before preprocessing and the data after its application. The results confirmed the superiority of the proposed method over classical approaches, providing higher aircraft recognition accuracy. The mAP50 index reached 0.994, and the mAP50-95 index reached 0.864, 1% and 4.8% higher than the standard approach. Conclusions. The experiments confirm the effectiveness of the proposed method of aircraft detection using deep neural networks and the process of sequential boundary traversal to detect object contours. The results indicate this approach’s high accuracy and efficiency, which allows us to recommend it for use in research related to aircraft recognition in high-resolution images. Further research could focus on improving image preprocessing methods and developing object recognition technologies in machine learning.
Application of Two-Dimensional Padé-Type Approximations for Image Processing
(National University «Zaporizhzhia Polytechnic», Zaporizhzhia, 2023) Olevskyi, V. I.; Hnatushenko, Volodymyr V.; Korotenko, G. M.; Olevska, Yu. B.; Obydennyi, Ye. O.
ENG: Context. The Gibbs phenomenon introduces significant distortions for most popular 2D graphics standards because they use a finite sum of harmonics when image processing by expansion of the signal into a two-dimensional Fourier series is used in order to reduce the size of the graphical file. Thus, the reduction of this phenomenon is a very important problem. Objective. The aim of the current work is the application of two-dimensional Padé-type approximations with the aim of elimination of the Gibbs phenomenon in image processing and reduction of the size of the resulting image file. Method. We use the two-dimensional Padé-type approximants method which we have developed earlier to reduce the Gibbs phenomenon for the harmonic two-dimensional Fourier series. A definition of a Padé-type functional is proposed. For this purpose, we use the generalized two-dimensional Padé approximation proposed by Chisholm when the range of the frequency values on the integer grid is selected according to the Vavilov method. The proposed scheme makes it possible to determine a set of series coefficients necessary and sufficient for construction of a Padé-type approximation with a given structure of the numerator and denominator. We consider some examples of Padé approximants application to simple discontinuous template functions for both formulaic and discrete representation. Results. The study gives us an opportunity to make some conclusions about practical usage of the Padé-type approximation and about its advantages. They demonstrate effective elimination of distortions inherent to Gibbs phenomena for the Padé-type approximant. It is well seen that Padé-type approximant is significantly more visually appropriate than Fourier one. Application of the Padé-type approximation also leads to sufficient decrease of approximants’ parameter number without the loss of precision. Conclusions. The applicability of the technique and the possibility of its application to improve the accuracy of calculations are demonstrated. The study gives us an opportunity to make conclusions about the advantages of the Padé-type approximation practical usage.
Automated Building Damage Detection on Digital Imagery Using Machine Learning
(Dnipro University of Technology, Ukraine, 2023) Kashtan, Vita Yu.; Hnatushenko, Volodymyr V.
ENG: Purpose. To develop an automated method based on machine learning for accurate detection of features of a damaged building on digital imagery. Methodology. This article presents an approach that employs a combination of unsupervised machine learning techniques, specifically Principal Component Analysis (PCA), K-means clustering, and Density-Based Spatial Clustering of Applications with Noise (DBSCAN), to identify building damage resulting from military conflicts. The PCA method is utilized to identify principal vectors representing the directions of maximum variance in the data. Subsequently, the K-means method is applied to cluster the feature vector space, with the predefined number of clusters reflecting the number of principal vectors. Each cluster represents a group of similar blocks of image differences, which helps to identify significant features associated with fractures. Finally, the DBSCAN method is employed to identify areas where points with similar characteristics are located. Subsequently, a binary fracture mask is generated, with pixels exceeding the threshold being identified as fractures. Findings. The introduced methodology attains an accuracy rate of 98.13 %, surpassing the performance of conventional methods such as DBSCAN, PCA, and K-means. Furthermore, the method exhibits a recall of 82.38 %, signifying its ability to effectively detect a substantial proportion of positive examples. Precision of 58.54 % underscores the methodology’s capability to minimize false positives. The F1 Score of 70.90 % demonstrates a well-balanced performance between precision and recall. Originality. DBSCAN, PCA and K-means methods have been further developed in the context of automated detection of building destruction in aerospace images. This allows us to significantly increase the accuracy and efficiency of monitoring territories, including those affected by the consequences of military aggression. Practical value. The results obtained can be used to improve automated monitoring systems for urban development and can also serve as the basis for the development of effective strategies for the restoration and reconstruction of damaged infrastructure.
Computer Modeling of Territory Flooding in the Event of an Emergency at Seredniodniprovska Hydroelectric Power Plant
(Dnipro University of Technology, Ukraine, 2022) Ivanov, D. V.; Hnatushenko, Volodymyr V.; Kashtan, Vita Yu.; Garkusha, I. M.
ENG: Purpose. Computer modeling of territory flooding in the event of an emergency at Seredniodniprovska Hydroelectric Power Plant (HPP). Methodology. The computer model of possible territory flooding at Seredniodniprovska HPP is developed using simulation modeling methods and geometric and hydrological approaches and considers initial boundary conditions of the water-engineering system. Calculations of the wave break height and the half-divided cross-sectional area of the river bed were made and a three-dimensional model of the territory flooding was built using the Python language and ArcGIS Desktop software. Findings. The data for each creation of the hydraulic node, namely the depth and width of the flooded territory, were calculated. This allowed analyzing the macro level considering the triangulation model of the surface. The wave break parameters and flaps (intersections) were taken into account in case of a dam break at a hydroelectric power plant or a rise in the water level. A mathematical model, and a 3D model were developed, and a forecast of the flood zone due to an emergency was made using satellite survey data. Originality. The mathematical method received further development for calculating flood territories in the event of an emergency at Seredniodniprovska Hydroelectric Power Plant, taking into account the parameters of the breakthrough wave and the calculation of cross-sections for the cases when a hydroelectric dam breaks or the water level rises; the method uses one-dimensional and two-dimensional systems of Saint-Venant equations, and geometric and hydrological approaches. A three-dimensional model of the territory flooding is developed to predict possible consequences. Practical value. The obtained results can be used to model the flooding of the territory located near dangerous hydro-technical objects, such as dams, dikes as well as to forecast flooded territories during the construction of drainage and protective structures.
Computer Technology for Satellite Imagery Processing in Nature Management Problem Solving Using Lineament Analysis
(Український державний університет науки і технологій, ІВК «Системні технології», Дніпро, 2023) Kashtan, Vita Yu.; Nikulin, Serhii; Hnatushenko, Volodymyr V.; Sergieieva, Kateryna; Korobko, Olha; Ivanov, Denys
ENG: This study focuses on analyzing the techniques used to highlight lineaments in images. Various mask algorithms, including the widely used optimal Kenny detector, were employed to identify brightness boundaries. Additionally, several quality criteria were developed to assess the accuracy of boundary selection. Based on the results of the analysis, conclusions were drawn regarding the effectiveness of different pre-processing methods for space images, along with recommendations to streamline data processing and analysis and enhance the reliability of results. Our analysis of image processing methods for selecting brightness boundaries revealed that the most effective approach involves applying filters to the source images to increase the number of selected boundaries while maintaining their integrity and length.
Decentralized Information System for Supply Chain Management Using Blockchain
(RWTH Aachen, Germany, 2022) Sytnyk, Roman; Hnatushenko, Viktoriia V.; Hnatushenko, Volodymyr V.
ENG: Development of international and domestic trade, globalization, creation of longer and more complex supply chains, increase in sales of goods and similar trends lead to an increase in requirements and load on information systems that manage and monitor the shipments of goods, resources and products. The aim of this paper is to make improvements to the existing approaches of building and designing logistics information systems. The paper proposes usage of blockchain technology in order to simplify and make more transparent the processes of monitoring and managing the movement of products between different equal participants in logistics supply chain information systems. A prototype of the supply chain information system based on the use of blockchain technology and smart-contracts using a decentralized Ethereum virtual machine was developed and studied in comparison with traditional approaches.
Detection of Forest Fire Consequences on Satellite Images Using a Neural Network
(German Society for Photogrammetry, Remote Sensing and Geoinformation, 2023) Hnatushenko, Viktoriia V.; Hnatushenko, Volodymyr V.; Kashtan, Vita; Heipke, Christian
ENG: The objective of this research is the detection of burnt forest areas from Sentinel-2 imagery. The proposed algorithm uses an approach based on convolutional neural networks (CNN). The functionality of the created system allows solving the task, starting from the moment of receiving the input data, image preprocessing and ending with the export of a hot-spot fire polygonal file describing the area that was burnt. These results are compared to methods based on the dNBR and a variant of BAIS2 called dBAIS2, which are generated from measurements in the near and middle IR channels of the Sentinel images. The proposed algorithm was tested on Sentinel satellite images acquired from June to September 2021for the Tizi Ouzou region, Algeria. We found it to have an overall accuracy of 97%, outperforming the results obtained from dNBR and dBAIS2 by large margins.
Enhancing the Quality of CNN-Based Burned Area Detection in Satellite Imagery through Data Augmentation
(Copernicus GmbH (Copernicus Publications) on behalf of the International Society of Photogrammetry and Remote Sensing, 2023) Hnatushenko, Viktoriia V.; Hnatushenko, Volodymyr V.; Soldatenko, Dmytro V.; Heipke, Christian
ENG: This study aims to enhance the quality of detecting burned areas in satellite imagery using deep learning by optimizing the training dataset volume through the application of various augmentation methods. The study analyzes the impact of image flipping, rotation, and noise addition on the overall accuracy for different classes of burned areas in a forest: fire, burned, smoke and background. Results demonstrate that while single augmentation techniques such as flipping and rotation alone did not result in significant improvements, a combined approach and the addition of noise resulted in an enhancement of the classification accuracy. Moreover, the study shows that augmenting the dataset through the use of multiple augmentation methods concurrently, resulting in a fivefold increase in input data, also enhanced the recognition accuracy. The study also highlights the need for further research in developing more efficient CNN models and in experimenting with additional augmentation methods to improve the accuracy of burned area detection, which would benefit environmental protection and emergency response services.
Homomorphic Filtering in Digital Multichannel Image Processing
(Dnipro University of Technology, Dnipro, Ukraine, 2023) Hnatushenko, Volodymyr V.; Spirintseva, O. V.; Spirintsev, V. V.; Kravets, O. V.; Spirintsev, D. V.
ENG: Purpose. The purpose of this article is to develop a preprocessing method for digital multispectral remote sensing images obtained through optical and infrared means in the electromagnetic spectrum. The method aims to ensure invariance with respect to positional formation conditions that determine spatial and radiometric resolution. By implementing homomorphic filtering in this method, we can significantly increase the informative value of processed imagery. Methodology. The problem solving, including the development of the spatial and radiometric resolution increase ways for multispectral geospatial data are based on the methods of brightness spatial distribution fusion, methods of data dimension reduction, de-correlation techniques and geometric correction of image spatial distributions. Findings. The method of preprocessing digital remote sensing data has been developed, which is a component of the methodology for identifying geometric shapes (GS) of objects in multi-channel aerospace images, allowing for a significant improvement in their recognition efficiency when noise is present. Originality. The method of preprocessing photogrammetric scenes using homomorphic filtering to enhance their informational significance is proposed. The method ensures invariance to positional conditions of fixation, improves the accuracy of further recognition, eliminates the drawbacks of known methods associated with the existence of parametric uncertainty dependence, the features of fixation of species information, low values of information indices of synthesized images, and computational process peculiarities. Practical value. Practical value consists in improving of identification accuracy of objects GS in digital geospatial data, in significant increasing of raster multispectral images information value and in rising of automated image processing efficiency. The use of the method can greatly enhance the value and usefulness of multispectral photogrammetric images in a wide range of applications, from environmental monitoring to urban planning.
Identification of Objects on Satellite Images Using the Image Texture Properties
(CEUR-WS Team, Aachen, Germany, 2023) Hnatushenko, Volodymyr V.; Shedlovska, Yana; Shedlovsky, Igor; Gorev, Vyacheslav
ENG: This paper focuses on identifying objects in satellite images using image texture properties, which is an important problem in agriculture. Texture segmentation can distinguish areas that correspond to tree plantations. Orchards and tree plantations can cover vast areas with thousands of trees, making the automation of harvest estimation crucial. Satellite images enable the creation of an effective automatic system for counting trees in plantations. In this work, we applied image texture segmentation to identify areas corresponding to agricultural plantations. We calculated textural properties of the image using the gray-level cooccurrence matrix, including mean value, variance, homogeneity, second angular moment, correlation, contrast, divergence, and entropy. These characteristics were used for segmentation, with multi-scale segmentation employed to distinguish areas of the image with specific textures. We proposed an algorithm for counting objects in satellite images, based on identifying individual objects that create a texture according to their spectral characteristics. The images used in this work primarily featured three object classes: trees, soil, and tree shadows. Since trees in gardens and plantations are arranged uniformly and have the same size, they can be easily distinguished from other image pixels based on their spectral characteristics. We analyzed NDVI and NSVDI spectral indices for tree detection and used the automatic spectral index histogram splitting method to distinguish objects with a high index value corresponding to trees.
Improvement of the Algorithm for Setting the Characteristics of Interpolation Monotone Curve
(Lublin University of Technology, Lublin, 2023) Kholodniak, Yuliia; Havrylenko, Yevhen; Halko, Serhii; Hnatushenko, Volodymyr V.; Suprun, Olena; Volina, Tatiana; Miroshnyk, Oleksandr; Shchur, Taras
ENG: Interpolation of a point series is a necessary step in solving such problems as building graphs de-scribing phenomena or processes, as well as modelling based on a set of reference points of the line frames defining the surface. To obtain an adequate model, the following conditions are imposed upon the interpolating curve: a minimum number of singular points (kinking points, inflection points or points of extreme curvature) and a regular curvature change along the curve. The aim of the work is to develop the algorithm for assigning characteristics (position of normals and curvature value) to the interpolating curve at reference points, at which the curve complies with the specified conditions. The characteristics of the curve are assigned within the area of their possible location. The possibilities of the proposed algorithm are investigated by interpolating the point series assigned to the branches of the parabola. In solving the test example, deviations of the normals and curvature radii from the corresponding characteristics of the original curve have been determined. The values obtained confirm the correctness of the solutions proposed in the paper.
Information System for Air Quality Assessment and Data Processing: Design and Implementation
(CEUR-WS Team, Aachen, Germany, 2024) Hnatushenko, Volodymyr V.; Bulana, Tetiana; Gomilko, Igor; Molodets, Bohdan; Boldyriev, Daniil
ENG: In recent years, the issue of air quality has become increasingly critical. This article presents a hardware and software-based solution for collecting and processing data from ground stations monitoring air quality. The system is designed to collect real-time data from monitoring stations, store the data in a central database, perform data processing, and detect anomalies. Additionally, the system offers data visualization through maps and tables. The developed solution consists of three core components: a web server, a web application, and ground stations. A key feature of the software is its ability to handle real-time data aggregation and fill data gaps using custom-built aggregators. This is achieved through real-time data parsing, managed by Celery workers and queued via RabbitMQ. All data is stored in an SQL database, with PostgreSQL and Django frameworks facilitating database management and administration. Python scripts are used to process raw data into user-friendly formats such as AQI indices and graphical representations. The system is designed for seamless deployment across multiple remote servers, ensuring high flexibility and reliability for researchers. This software architecture enables scalable, conflict-free deployment, enhancing the efficiency and accuracy of air quality assessments.
Information System of Air Quality Assessment Based of Ground Stations and Meteorological Data Monitoring
(CEUR-WS Team, Aachen, Germany, 2023) Molodets, Bohdan; Hnatushenko, Volodymyr V.; Boldyriev, Daniil; Bulana, Tetiana
ENG: Monitoring ground stations and collecting meteorological data are essential solutions for assessing air quality. A developed information system can aggregate and process the data obtained. The data is transformed into a unified format and returned through written application programming interfaces (APIs). Client interfaces were created for convenient display of the results. The project infrastructure is designed for easy deployment. The architectural solution for creating the system proposes a toolkit that optimizes system operation when performing complex tasks through asynchronous execution. The use of Docker during deployment provides additional capabilities. To calculate the distribution of emissions in Kryvyi Rih, the CALPUFF model was employed for data processing. The article describes the client part structure and interface description. It also displays the processed data, which is the result of applying a mathematical model to the meteorological and station data.
Information System of Air Quality Assessment Using Data Interpolation from Ground Stations
(CEUR-WS Team, Aachen, Germany, 2023) Molodets, Bohdan; Hnatushenko, Volodymyr V.; Boldyriev, Daniil; Bulana, Tetiana
ENG: Monitoring ground stations is crucial for creating interactive maps that assist in assessing air quality. A developed information system can aggregate and process the data obtained, which is then transformed into a unified format and used as input data for interpolation methods that create raster imagery. After processing, the data is stored in Amazon Simple Storage Service or database and can be retrieved using application program interfaces (APIs). The proposed architectural solution for creating the system includes a toolkit that can work with different volumes of data with ease. Using Docker during deployment provides additional capabilities for creating a flexible and scalable system. Specific tools such as PostGis and Geospatial Data Abstraction Library (GDAL) simplify the processing of data. For instance, GDAL helps with the interpolation, cropping, and tiling of the air quality raster image. The article describes the structure of the client part and the interface in detail. By using the Mapbox Graphics Library system, the system can easily visualize big data as a vector layer, helping users recognize hazardous zones and find safe places.
Information System to Enhance Agricultural Production Efficiency Based on Sustainable Development Principles
(CEUR-WS Team, Aachen, Germany, 2024) Hnatushenko, Volodymyr V.; Shuleshko, Victor; Bulana, Tetiana; Molodets, Bohdan
ENG: The increasing global demand for sustainable agricultural practices necessitates innovative solutions to optimize resource use and minimize environmental impact. This paper presents the information technology developed to automate and optimize the operation of a hydroponic system to improve energy and resource efficiency in sustainable agriculture. An automated control platform at the system's base continuously monitors key environmental parameters within the hydroponic facility, including water level, nutrient distribution, lighting, and energy consumption. The system can precisely regulate the processes by collecting real-time data on these variables, providing ideal conditions for plant growth. The hydroponic system is equipped with a set of sensors and actuators that control water flow, fertilizer supply, and lighting according to the needs of each plant. The developed spectral composition is based on combining the spectra of HPS and two peaks of photosynthetic efficiency. This combination of the spectrums complements each other, which allows photosynthesis to proceed as efficiently as possible. The system makes it possible to save up to 25% of electricity consumption without losing quality and quantity characteristics, to reduce the number of hours of illumination, and to be placed in cost-effective climatic conditions.
Information Technologies in IT Education as a Factor of Digitalization of Ukrainian Society
(CEUR-WS Team, Aachen, Germany, 2024) Sokolova, Natalya; Hnatushenko, Volodymyr V.
ENG: The article investigates the digitization of Ukrainian society, the role of digital skills in labor market demand, digital literacy among the population, and the key audience of educators - teenagers. It outlines the approaches and experiences of the Department of Information Technology and Computer Engineering at Dnipro University of Technology in transforming IT education. It specifically examines the teaching of programming courses to first-year students to build foundational competencies for continued learning and the use of digital technologies in training specialists for government bodies. The article also highlights the integration of Cisco International Network Academy courses into the curriculum and the training of specialists through educational partnership projects with businesses.
Information Technology for Detecting Forest Fire Contours Using Optical Satellite Data
(Український державний університет науки і технологій, ННІ ≪Інститут промислових та бізнес технологій≫, ІВК ≪Системні технології≫, Дніпро, 2023) Kashtan, Vita; Hnatushenko, Volodymyr V.
ENG: The number of forest fires has increased significantly over the past ten years. It indicates that forest area estimates fires are a very urgent task today. The use of satellite-based data simplifies the process of assessing forest fires. The aim is to develop an information technology for automated forest fire contours detection on digital optical satellite datas in conditions of non-stationarity and uncertainty based on convolutional neural networks. The most popular tools for forest fire analysis are considered. This work proposed using hotspots to identify all fire and smoke pixels for automated forest fire contour detection. It made it possible to obtain contour polygons of the corresponding areas with various attributes: position, size, etc. The results are tested on Sentinel 2 satellite images of the Бvila region. The proposed method has an overall accuracy of 94.3% for the selection of forest fires.
Intelligent Sentinel Satellite Image Processing Technology for Land Cover Mapping
(Dnipro University of Technology, Dnipro, 2024) Kashtan, Vita Yu.; Hnatushenko, Volodymyr V.; Laktionov, I. S.; Diachenko, H. H.
ENG: Purpose. This article proposes to develop an intelligent Sentinel satellite image processing technology for land cover mapping using convolutional neural networks. The result will be an image with improved spatial resolution. Methodology. The paper presents a technology using a combination of biquadratic interpolation, histogram alignment, PCA transform, as well as a parallel residual architecture of convolutional neural networks. The technology increases the information content of Sentinel-2 optical images by combining 10 and 20-meter resolution data, resulting in primary 20-meter images with improved spatial resolution. Findings. The root mean square error (RMSE = 3.64) indicates a high accuracy in reproducing the spectral properties of the images. The correlation coefficient (CC = 0.997) confirms a high linear relationship between the estimated and observed images. The low value of Spectral Angle Mapper (SAM = 0.52) with the high Universal Image Quality Index (UIQI = 0.999) indicates high quality and structural similarity between the synthesized and reference images. These results confirm the proposed technology’s effectiveness in enhancing the spatial resolution of Sentinel satellite images. Originality. Traditional pansharpening methods of multispectral images developed for satellite images with panchromatic channels cannot be directly applied to Sentinel multispectral data, because these images do not contain a panchromatic channel. In addition, atmospheric conditions and the presence of clouds affect the quality of optical images, complicating their further thematic processing. The proposed technology, using biquadratic interpolation, histogram alignment, convolutional neural networks, and PCA transformation, removes clouds and enhances the spatial resolution of the primary 20-meter optical satellite image channels of Sentinel-2. This technology reduces color distortion and increases the detail of digital optical images, which allows for more accurate analysis of the state of the earth’s surface. Practical value. The results obtained can be used to improve the methods for processing Sentinel satellite images, which provide high spatial resolution and accurate preservation of spectral characteristics. It provides the foundation for the development of new geographic information systems for land cover monitoring.
Machine Learning for Automatic Extraction of Water Bodies Using Sentinel-2 Imagery
(National University "Zaporizhzhia Polytechnic", Zaporizhzhia, 2024) Kashtan, Vita Yu.; Hnatushenko, Volodymyr V.
ENG: Context. Given the aggravation of environmental and water problems, there is a need to improve automated methods for extracting and monitoring water bodies in urban ecosystems. The problem of efficient and automated extraction of water bodies is becoming relevant given the large amount of data obtained from satellite systems. The object of study is water bodies that are automatically extracted from Sentinel-2 optical satellite images using machine learning methods. Objective. The goal of the work is to improve the efficiency of the process of extracting the boundaries of water bodies on digital optical satellite images by using machine learning methods. Method. The paper proposes an automated information technology for delineating the boundaries of water bodies on Sentinel-2 digital optical satellite images. The process includes eight stages, starting with data download and using topographic maps to obtain basic information about the study area. Then, the process involved data pre-processing, which included calibrating the images, removing atmospheric noise, and enhancing contrast. Next, the EfficientNet-B0 architecture is applied to identify water features, facilitating optimal network width scaling, depth, and image resolution. ResNet blocks compress and expand channels. It allows for optimal connectivity of large-scale and multi-channel links across layers. After that, the Regional Proposal Network defines regions of interest (ROI), and ROI alignment ensures data homogeneity. The Fully connected layer helps in segmenting the regions, and the Fully connected network creates binary masks for accurate identification of water bodies. The final step of the method is to analyze spatial and temporal changes in the images to identify differences, changes, and trends that may indicate specific phenomena or events. This approach allows automating and accurately identifying water features on satellite images using machine learning. Results. The implementation of the proposed technology is development through Python software development. An assessment of the technology’s accuracy, conducted through a comparative analysis with existing methods, such as water indices and K-means, confirms a high level of accuracy in the period from 2017 to 2023 (up to 98%). The Kappa coefficient, which considers the degree of consistency between the actual and predicted classification, confirms the stability and reliability of our approach, reaching a value of 0.96. Conclusions. The experiments confirm the effectiveness of the proposed automated information technology and allow us to recommend it for use in studies of changes in coastal areas, decision-making in the field of coastal resource management, and land use. Prospects for further research may include new methods that seasonal changes and provide robustness in the selection and mapping of water surfaces.
Neural Network-Based Analysis of Forest Fire Aftermath in Class-Imbalanced Remote Sensing Earth Image Classification
(ISPRS, Hannover, Germany, 2024) Hnatushenko, Viktoriia V.; Hnatushenko, Volodymyr V.; Soldatenko, Dmytro V.
ENG: Today's agricultural sector is characterized by an important role of accurate mapping and monitoring of agriculture with the help of satellite imagery, which allows to optimize the use of resources, to plan crop areas and to forecast productivity. Classification of satellite images with unbalanced sample distribution is a critical problem in this regard. Traditional machine learning algorithms in particular have limitations in dealing with sample imbalance. In this paper, we proposed convolution neural networks for semantic segmentation, where sample imbalance is considered based on a particular loss function coupled with data augmentation. To illustrate our method, we use Sentinel-2 remote sensing (RS) images covering a number of regions in Ukraine, and then we create an image dataset of the region and for training and testing make data augmentation. The models with different architectural features were investigated. The results demonstrate that the proposed CNN has a higher classification accuracy than the ones discussed in the paper: the classification accuracy on the test dataset reached 96.7% with intersection-over-union values of up to 89.7%. This opens the way for further research in the direction of refining algorithms for classify satellite data with an imbalanced class structure.

Browse

Browsing Кафедра інформаційних технологій і систем (ДМетІ) by Author "Hnatushenko, Volodymyr V."

Results Per Page

Sort Options