Relevance of the topic.
In the modern era of digital development, the automation of the processes of processing and analysis of cartographic images is gaining more and more importance. Segmentation of a cartographic image is one of the key stages in the process of digital processing of maps, which allows you to distinguish and classify various objects of the area: water bodies, forests, urban development, transport infrastructure, etc. Automation of this process not only significantly speeds up the processing of large sets of map data, but also completes the accuracy and objectivity of the results.
The expediency of this study is determined by the rapid development of geographic information systems (GIS) and the growing need for operational updating of cartographic information. The use of machine learning and computer vision methods for solving segmentation tasks deserves special attention.
The purpose and tasks of the research.
The purpose of the work is the development of an automated system for the segmentation of cartographic images.
To achieve the set goal of the work, a number of tasks must be solved:
- conduct a review of scientific literature on the topic of scientific research, consider existing developments in the field of image segmentation using neural networks;
- develop software algorithms;
- select parameters and metrics;
- test the algorithm;
- train a neural network.- select parameters and metrics;
- train a neural network.
- test the algorithm;
The object of research is the process of automated analysis of cartographic images.
The subject of research is methods of automated semantic segmentation of cartographic images.
Research methods.
To solve the problems, an analysis of information on existing developments in image segmentation using machine learning, familiarization with theoretical material, comparative analysis of existing segmentation methods, architectures, training of developed algorithms was carried out.
Scientific novelty of the obtained results.
The result of the development is a system of segmentation of cartographic images. The novelty of the created system consists in increasing the accuracy of segmentation.
Publications.
The work of the conference "Analysis of the efficiency of neural network architectures for automated segmentation of cartographic images" was published in the collection of works of the XX All-Ukrainian Scientific and Practical Conference of Students, Postgraduate Students and Young Scientists "Efficiency and Automation of Engineering Solutions in Instrumentation" using the results obtained in the master's qualification work.
Structure of work. The master's qualification work consists of an explanatory note and graphic materials. The explanatory note contains an introduction, 5 chapters, conclusions, a list of used sources and appendices. Scope of work: explanatory note - 97 sheets of A4 format, 34 illustrations, 27 tables, 39 sources were processed.
Research advisor: A. Momot
