Issue 2 (200), article 3


Cybernetics and Computer Engineering, 2020, 2(200)

GRITSENKO V.I., Corresponding Member of NAS of Ukraine,
Director of International Research and Training Center for Information Technologies and Systems of the NAS of Ukraine and MES of Ukraine

Senior Researcher of the Intelligent Control Department

BOGACHUK Yu.P., PhD. (Engineering),
Leading Researcher of the Intelligent Control Department

Senior Researcher of the Intelligent Control Department

Researcher of the Intelligent Control Department

SHEPETUKHA Yu.M., PhD. (Engineering),
Leading Researcher of the Intelligent Control Department

Researcher of the Intelligent Control Department

International Research and Training Center for Information Technologies and Systems of the National Academy of Sciences of Ukraine and of Ministry of Education and Science of Ukraine,
40, Acad. Glushkov av., Kyiv, 03187, Ukraine


Introduction. Nowadays, geoinformation systems (GIS) are widely used in transport, construction, navigation, geology, geography, military affairs, topography, economics and more.

Problem Statement. Modern GIS publications highlight a number of pressing issues regarding the need to develop technologies and methods for the rapid formation of spatial-temporal geoinformation data bases and dynamic mapping images. The process of prompt formation of cartographic images of the area of unmanned aerial vehicles (UAV) flights in GIS databases is based on the simultaneous solution of two problems – determining the location of UAV in space, as well as the formation of a mapping image of the area under study.

 The purpose of the paper is to descript the method of topographic clustering of the obtained photographic images of UAV flights, which allows to combine visual images due to the semantic search of their topographic similarity, in order to realize the visual localization of UAV and high-precision layout of the mapping image of the navigation environment in the operational GIS database.

Materials and methods. The research conducted is based on the technologies of intelligent processing of large arrays of video and photo data, the theory of automatic control, methods of image processing and recognition based on descriptors of special points, methods of computer vision, as well as on methods and algorithms of own development, theory of navigation and dynamics of UAV flight.

Results. Procedures of topographic clustering of visual images obtained with UAV are developed, which are used for cognitive detection, description and matching among the characteristic features of the navigation environment.

Conclusions. The formation of a mapping image of the area of the navigation environment using the proposed method of topographic clustering of visual images achieved a decimeter accuracy in spatial coordinates, allowing visual localization and mapping with a high level of accuracy.

Keywords: unmanned aerial vehicle, geoinformation system, information technology, computer vision, intelligent control, cartographic image, aerial photography.

Download full text!


1 Artes T., Cencerrado A., Cortes A., Margalef T. Real-time genetic spatial optimization to improve forest fire spread forecasting in high-performance computing environments. International Journal of Geographical Information Science. 2016, Vol. 30, No 3, pp. 594-611.

2 Li J., Bi Y., Lan M., Qin H., Shan M., Lin F., Chen B.M. Real-time Simultaneous Localization and Mapping for UAV: A Survey. Proc. of International micro air vehicle competition and conference. 2016, Beijing, China, 2016, pp. 237-242.

3 Kozub, A. M., Suvorova, N. O., & Chernyavsky, V. M. (2011). Analiz zasobiv zboru informatsiyi dlya heohrafichnykh informatsiynykh system. Systemy ozbroyennya i viys’kova tekhnika. 2011, No 3, pp. 42-47. (In Ukrainian)

4 Gonzales D., Harting S. Designing Unmanned Systems with Greater Autonomy: Using a Federated, Partially Open Systems Architecture Approach. Santa Monica, Calif: RAND, 2014, 96 p.

5 Agunbiade O., Zuva T., A Review: Simultaneous Localization and Mapping in Application to Autonomous Robot. Preprints 2018. 2018050293 (doi: 10.20944/preprints201805.0293.v1).

6 Fuentes-Pacheco J., Ruiz-Ascencio J., Rendon-Mancha J.M. Visual simultaneous localization and mapping: a survey. Artificial Intelligence Review. 2015, Vol. 43, No1, pp. 55-81.

7 Silpa C., Hartley R. Optimised KD-trees for fast image descriptor matching. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2008, pp. 1-8.

8 Dufournaud Y., Schmid C., Horaud R. Image matching with scale adjustment. Computer Vision Image Understanding. 2004, No 93(2), pp. 175-194.

9 Zhang W., Kosecka J. Image based localization in urban environments. Proceedings of the Third International Symposium on 3D Data Processing, Visualization, and Transmission. 2006, Chapel Hill, USA, pp. 33-40.

10 Schubert J., Brynielsson J., Nilsson M., Svenmarck P. Artificial Intelligence for Decision Support in Command and Control Systems. Proceedings of the 23rd International Command and Control Research & Technology Symposium “Multi-Domain C2”. 2018, Playa Vista, California, USA, pp. 18-33.

11 Bradski G., Kaehler A. Learning OpenCV. O’Reilly Media, 2008, 576 p.

Received 27.02.2020