Enhanced Method for Image Alignment of Urban Infrastructure Images by UAV Shooting

Relevance. Reducing the computational cost of image alignment procedures is an important field of research. The article considers the problem of processing urban infrastructure images obtained by UAV. The development of a high-speed method will make it possible to construct a digital map of an area by images from several UAVs in a limited time (ideally in real-time), which can be used to solve operational problems.

Purpose of the work. Reducing the computational cost of the alignment procedure by preliminary estimating the parameters based on a limited sample of interest points.

Methods used: analytical review of relevant scientific publications, experiment, algorithmization.

The method for Image Alignment of Urban Infrastructure Images by UAV Shooting to make a digital map was developed to solve a scientific problem; the previously developed technique was enhanced; it reduced the computational complexity of image processing; the basis of the enhancement was the assumption that the transformation parameters range is limited; the advantage of the enhanced methodology were noted in the research.

Results. An enhanced method of image alignment is proposed, which is characterized by shorter processing time than the original one. Experimental testing showed a reduction in time by half (from 50 s to 23 s), as well as a satisfactory result in combining 100 pairs of images.

The work scientific novelty is determined by the author's approach to narrowing the range of the scaling coefficient and rotation angle for fragments matched of the alignment images. The approach is proposed for the first time.

Theoretical significance. The assumption was confirmed that fragments of the image of urban infrastructure taken by UAV have a limited range of transformation of scaling and rotation.

Practical significance. The research results can be used to make a machine vision system for digital map constructions in real-time. It provides a solution to operational problems of objects detecting and tracking the movement.

1. Fedosov V.P., Ibadov R.R., Ibadov S.R. Modified depth map post-processing method for problems of accident-free UAV driving in urban infrastructure. Journal Radioengineering. 2023;87(9):113–123. (in Russ.) DOI:10.18127/j00338486-202309-10. EDN:TTOLWC

2. Vasilyeva D.V., Dvornikov S.V. Structurization of primary features of environmental monitoring systems images. Journal Radioengineering. 2024;88(8):5–17. (in Russ.) DOI:10.18127/j00338486-202408-01. EDN:CXJBDK

3. Naumov I.I., Ibadov R.R., Trekhsvyatsky P.V., Aznabaev M.I. Unmanned aerial vehicles for inspection of power lines. Journal Radioengineering. 2025; 89(3):169–180. (in Russ.) DOI:10.18127/j00338486-202503-15. EDN:OJDJYE

4. Lowe D.G. Object recognition from local scale-invariant features. Proceedings of the 7th International Conference on Computer Vision, ICCV, 20–27 September 1999, Kerkyra, Greece. IEEE; 1999. p.1150–1157. DOI:10.1109/ICCV.1999.790410

5. Bay H., Tuytelaars T., Gool L.V. SURF: Speeded up robust features. Proceedings of the 9th European Conference on Computer Vision, ECCV, 7–13 May 2006, Graz, Austria. Lecture Notes in Computer Science, vol.3951. 2006. p.404–417. DOI:10.1007/ 11744023_32

6. Raguram R., Frahm J.M., Pollefeys M. A comparative analysis of RANSAC techniques leading to adaptive real-time random sample consensus. Proceedings of the 10th European Conference on Computer Vision, ECCV, 12–18 October 2008, Marseille, France. Lecture Notes in Computer Science, vol.5303. Berlin, Heidelberg: Springer; 2008. p.500–513. DOI:10.1007/978-3-540-88688-4_37

7. Efimov A.I., Novikov A.I. An algorithm for multistage projective transformation adjustment for image superimposition. Computer Optics. 2016;40(2):258–265. (in Russ.) DOI:10.18287/2412-6179-2016-40-2-258-265. EDN:VWWCHP

8. Sungatullina D., Krylov A. A fast algorithm for aligning the contours of images related by an isotropic affine transformation. Proceedings of the XXIVth International Conference on Computer Graphics and Vision, Graphicon'2014, 30 September – 03 October 2014, Rostov-on-Don, Russian Federation. Graphicon Publ.; 2014. p.92–95. (in Russ.) EDN:ZBWXUN

9. Volegov D.B., Yurin D.V. Rough image registration via detected straight lines. Proceedings of the 16th International Conference on Computer Graphics and Vision International Conference on Computer Graphics and Vision, GraphiCon 2006, 01–05 July 2006, Novosibirsk, Russian Federation. 2006. p.463–466. (in Russ.) EDN:RLZMQD

10. Goshin Ye.V., Kotov A.P., Fursov V.A. Two-stage formation of a spatial transformation for image matching. Computer Optics. 2014;38(4):886–891. DOI:10.18287/0134-2452-2014-38-4-886-891. (in Russ.) EDN:TCGBNN

11. Osipov O.V., Diyazitdinova A.A. Signal superposition for improving quality of television video surveillance system. Journal Radioengineering. 2020;84(12):72–78. (in Russ.) DOI:10.18127/j00338486-202012(23)-08. EDN:ZVQUIB

12. Diyazitdinova A.A. Improvement of methodology for homography superposition of images. Infokommunicationnye technologii. 2022;20(4);89–96. (in Russ.) DOI:10.18469/ikt.2022.20.4.12. EDN:TDSXFE

13. Tashlinsky A.G., Kovalenko R.O., Ibragimov R.M. Using Mutual Information as a Measure of Similarity in Stochastic Image Matching. Proceedings of the VII International Conference and Youth School on Information Technologies and Nanotechnology, 20–24 September 2021, Samara, Russian Federation. Samara: Samara National Research University Publ.; 2021. p.20882-1–20882-2. (in Russ.) EDN:NXXCXP

14. Diyazitdinova A.A. Improving noise immunity of homography superposition for television signals. Physics of Wave Processes and Radio Systems. 2021;24(1):58–66. (in Russ.) DOI:10.18469/1810-3189.2021.24.1.58-66. EDN:BYZTCS

15. Diyazitdinova A.A. Criteria for image superposition in a two-camera technical vision system. RENSIT: Radioelectronics. Nanosystems. Information technologies. 2024;16(2):307–314. (in Russ.) DOI:10.17725/rensit.2024.16.307. EDN:BBZVWW