Detection of image objects for autonomous localisation of unmanned aerial vehicles and map formation of the surrounding space

Authors

  • Viktor Yu. Tsviatkou Belarusian State University of Informatics and Radioelectronics, 6 P. Browki Street, Minsk 220013, Belarus
  • Viyaleta V. Rabtsevich Stormnet Technologies, 168 Niezaliezhnasci Avenue, 2 building, Minsk 220141, Belarus
  • Ma Jun Belarusian State University of Informatics and Radioelectronics, 6 P. Browki Street, Minsk 220013, Belarus
  • Mikhail I. Zorko Belarusian State University of Informatics and Radioelectronics, 6 P. Browki Street, Minsk 220013, Belarus

Keywords:

simultaneous localisation and mapping, SLAM, wave segmentation of images, region growing, image object identification, point detectors, line detectors
Supporting Agencies
This work was carried out with the financial support of the Belarusian Republican Foundation for Fundamental Research and the National Natural Science Foundation of China (project T25KI-054 «Outdoor multi-camera simultaneous localisation and mapping technology»).

Abstract

The problem of autonomous localisation of an unmanned aerial vehicle and construction of a map of its environment is considered. The low stability of keypoint detectors to changing weather and time conditions of image formation in the surrounding space is demonstrated compared to the stability of line detectors. To improve the stability of unmanned aerial vehicles localisation it is proposed to use image regions (segments) with uniform brightness as key identification objects. An algorithm for segmentation based on local minima of the brightness gradient of halftone images obtained from the original colour images of the unmanned aerial vehicle’s surrounding space has been developed. To equalise the growth rates of local minima a wave segmentation algorithm with automatic stopping is proposed. This algorithm is based on identifying new initial and additional growth points of regions using a monotonically varying threshold and taking into account the rate of change of the brightness gradient along the region growth trajectory in the stopping criterion. It is shown that the proposed algorithms provide more stable localisation of areas, when changing weather and time conditions for image formation in comparison with known algorithms for extracting lines and key points.

Author Biographies

  • Viktor Yu. Tsviatkou, Belarusian State University of Informatics and Radioelectronics, 6 P. Browki Street, Minsk 220013, Belarus

    doctor of science (engineering), full professor; head of the department of infocommunication technologies, faculty of information security

  • Viyaleta V. Rabtsevich, Stormnet Technologies, 168 Niezaliezhnasci Avenue, 2 building, Minsk 220141, Belarus

    lecturer

  • Ma Jun, Belarusian State University of Informatics and Radioelectronics, 6 P. Browki Street, Minsk 220013, Belarus

    assistant at the department of infocommunication technologies, faculty of information security

  • Mikhail I. Zorko, Belarusian State University of Informatics and Radioelectronics, 6 P. Browki Street, Minsk 220013, Belarus

    assistant at the department of infocommunication technologies, faculty of information security

References

  1. Ince OF, Kim J-S. TIMA SLAM: tracking independently and mapping alto-gether for an uncalibrated multi-camera system. Sensors. 2021;21(2):409. DOI: 10.3390/s21020409.2.
  2. Hu Z, Fang H, Zhong R, Wei S, Xu B, Dou L. GMP-SLAM: a real-time RGB-D SLAM in dynamic environments using GPU dynamic points detection method. IFAC-PapersOnLine. 2023;56(2):5033–5040. DOI: 10.1016/j.ifacol.2023.10.1282.
  3. Li D, Shi X, Long Q, Liu S, Yang W, Wang F. DXSLAM: a robust and efficient visual SLAM system with deep features. In: Institute of Electrical and Electronics Engineers. 2020 IEEE/RSJ International conference on intelligent robots and systems (IROS); 2020 October 24 – 2021 January 24; Las Vegas, USA. [S. l.]: Institute of Electrical and Electronics Engineers; 2020. p. 4958–4965. DOI: 10.1109/IROS45743.2020.9340907.
  4. Matsuki H, Scona R, Czarnowski J, Davison AJ. CodeMapping: real-time dense mapping for sparse SLAM using compact scene representations. IEEE Robotics and Automation Letters. 2021;6(4):7105–7112. DOI: 10.1109/LRA.2021.3097258.
  5. Dai W, Zhang Y, Li P, Fang Z, Scherer S. RGB-D SLAM in dynamic environments using point correlations. IEEE Transactions on Pattern Analysis & Machine Intelligence. 2022;44(1):373–389. DOI: 10.1109/TPAMI.2020.3010942.
  6. Favorskaya MN. Deep learning for visual SLAM: the state-of-the-art and future trends. Electronics. 2023;12(9):1–29. DOI: 10.3390/electronics12092006.
  7. Wang S, Hu Q, Zhang X, Li W, Wang Y, Zheng E. LVID-SLAM: a lightweight visual-inertial SLAM for dynamic scenes based on semantic information. Sensors. 2025;25(13):4117. DOI: 10.3390/s25134117.
  8. Sun Y, Wang Q, Yan C, Feng Y, Tan R, Shi X, et al. D-VINS: dynamic adaptive visual-inertial SLAM with IMU prior and semantic constraints in dynamic scenes. Remote Sensing. 2023;15(15):3881. DOI: 10.3390/rs15153881.
  9. Zhu D, Liu P, Qiu Q, Wei J, Gong R. BY-SLAM: dynamic visual SLAM system based on BEBLID and semantic information extraction. Sensors. 2024;24(14):4693. DOI: 10.3390/s24144693.
  10. Al-Furaiji OJM, Nguyen AT, Tsviatkou VYu. A new approach of finding local extrema in grayscale images based on space-oriented masks. Engineering Letters. 2020;28(2):586–593.
  11. Gonzalez RC, Woods RE. Digital image processing. 3rd edition. Delhi: Pearson; 2008. 976 p.
  12. Adams R, Bischof L. Seeded region growing. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1994;16(6):641–647. DOI: 10.1109/34.295913.
  13. Fan M, Lee TCM. Variants of seeded region growing. IET Image Processing. 2015;9(6):478–485. DOI: 10.1049/iet-ipr.2014.0490.
  14. Fan J, Zeng G, Body M, Hacid MS. Seeded region growing: an extensive and comparative study. Pattern Recognition Letters. 2005;26(8):1139–1156.
  15. Lowe DG. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision. 2004;60(2):91–110.
  16. Bay H, Tuytelaars T, van Gool L. SURF: speeded up robust features. In: Leonardis A, Bischof H, Pinz A, editors. Proceedings of the 9th European conference on computer vision; 2006 May 7–13; Graz, Austria. Part 1. Berlin: Springer Verlag; 2006. p. 404–417 (Lecture notes in computer science; volume 3951).

Downloads

Additional Files

Published

2026-05-08

Issue

No. 1 (2026): Journal of the Belarusian State University. Mathematics and Informatics

Section

Data Science

License

Copyright (c) 2026 Journal of the Belarusian State University. Mathematics and Informatics

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

The authors who are published in this journal agree to the following:

  1. The authors retain copyright on the work and provide the journal with the right of first publication of the work on condition of license Creative Commons Attribution-NonCommercial. 4.0 International (CC BY-NC 4.0).
  2. The authors retain the right to enter into certain contractual agreements relating to the non-exclusive distribution of the published version of the work (e.g. post it on the institutional repository, publication in the book), with the reference to its original publication in this journal.
  3. The authors have the right to post their work on the Internet (e.g. on the institutional store or personal website) prior to and during the review process, conducted by the journal, as this may lead to a productive discussion and a large number of references to this work. (See The Effect of Open Access.)

How to Cite

[1]
Tsviatkou, V.Y. et al. 2026. Detection of image objects for autonomous localisation of unmanned aerial vehicles and map formation of the surrounding space. Journal of the Belarusian State University. Mathematics and Informatics. 1 (May 2026), 156–162.