Detection of Urban Areas using Genetic Algorithms and Kohonen Maps on Multispectral images

Mokadem, Djelloul; Amine, Abdelmalek; Elberrichi, Zakaria; Helbert, David

doi:10.4018/ijoci.2018010104

Cited by 2 publications

(2 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Even the most modern satellite images will not allow to obtain the necessary information without the fast and reliable decryption methods found in most modern specialized software products. Techniques for automated decoding of images developed by a number of international research institutes and research institutes of Ukraine, including classification, contouring and recognition of images of topographic objects [9,10,11,12], allow to maximize the efficiency of decryption, in comparison with traditional non-automated methods. However, the developers of these techniques emphasize that the presence of a number of interactive processes, such as contouring, searching for reference information, classification of images by texture and brightness characteristics, significantly reduces labor productivity during decryption.…”

Section: A R C H I T E C T U R E C I V I L E N G I N E E R I N G E N V I R O N M E N Tmentioning

confidence: 99%

See 1 more Smart Citation

Geospatial Data Processing Characteristics for Environmental Monitoring Tasks

Butenko¹,

Horelik

Zynyuk

2020

Architecture, Civil Engineering, Environment

View full text Add to dashboard Cite

This paper explores the specifics of working with geospatial data when making decisions about the current environmental status of objects based on Earth space monitoring data. The expediency of sharing statistical data, Earth remote sensing data, and contact measurements is displayed. An analysis of the specifics of this approach to solving the problems of complex processing of multi-temporal a priori data obtained by various shooting equipment was carried out. The existing methods for combining such data are analyzed and possible options for reducing temporary resources and reducing requirements for information resources when working with large volumes of information are considered. It is appropriate to use the method of hierarchical partitioning of multi-temporal image data or images of the analyzed areas obtained at the same time, but from different satellites taking into account the specifics of the shooting equipment and subject to their correspondence to the given a priori geospatial information. One of the criteria for hierarchical partitioning is the identification of areas of greatest correspondence with a priori data with their geographical reference in satellite imagery to reduce the localization time of the corresponding zones throughout the analyzed image array. The economic application effect of this method is substantiated by reducing the computational complexity of costly pattern matching processes, as well as performance improvement of change determination algorithms in topological and geometric characteristics of these objects. An algorithm is shown for detecting changes in heterogeneity in images based on the result of overlay operations with time-differentiated satellite imagery. To confirm the adequacy of the proposed method, the results of its practical implementation are shown on the Ukraine-Poland border area. A comparative analysis of the obtained results with real data is carried out.

show abstract

Section: A R C H I T E C T U R E C I V I L E N G I N E E R I N G E N V I R O N M E N Tmentioning

confidence: 99%

“…The new trees formed as a result of the transformation, built only in the area of interest revealed by changes in overlay operations, with a geographical reference, allow for a much clearer distinction of previously existing objects [10].…”

Section: Determining the Dynamics Of Changes In The Objects Geomet-ric Characteristics From Satel-lite Imagerymentioning

confidence: 99%