V.P. Fedosov1, R.R. Ibadov2, I.I. Naumov3, S.P. Oboymova4

1 Institute for Radiotechnical Systems and Control, SFU (Rostov-on-Don, Russia)

2–4 Don State Technical University (Rostov-on-Don, Russia)

1 vpfed@mail.ru, 2 ragim_ibadov@mail.ru, 3 naumov-85@yandex.ru, 4 svetusja2004@yandex.ru

In this paper, an efficient method for automatic road extraction in rural and suburban areas is presented, aimed at updating GIS starting from color images and using existing vector information. Only RGB bands of high-resolution satellite or aerial imagery are required as input. The system includes four different modules: data pre-processing; binary segmentation based on three levels of statistical texture assessment; automatic vectorization using skeleton extraction; and finally, a module for system evaluation. In the first module, the color image is corrected and georeferenced. The second module uses a new technique called Progressive Texture Analysis (TPA) to obtain a segmented binary image. TPA is developed within the framework of proof theory and consists of combining the information flow from three different sources for the image. In the third module, the obtained binary image is vectorized using an algorithm based on skeleton extraction methods and morphological operations. The result is an extracted road network, which is defined as a structural set of geometrically and topologically correct elements. The fourth module is an evaluation of the procedure using a popular method. The experimental results show that this method is effective in extracting and defining the road network based on high-resolution satellite and aerial photographs. Reducing road extraction error using a three-level statistics algorithm to perform progressive texture analysis. The main features of automatic road extraction are considered. A reliable system of automatic road extraction is presented. The system is aimed at reducing the work performed manually by operators when performing GIS update tasks. An algorithm for automatic detection of the road network by segmentation based on progressive texture analysis is developed. Geometric and topological definition of the road network is developed based on skeleton extraction methods. The obtained graphic elements are evaluated, validated and stored in the GIS. The proposed algorithm for automatic road extraction, namely, the use of three different levels of statistics to perform progressive texture analysis, has shown effective use in terms of quality in rural and suburban conditions. This makes the practical application of the algorithm useful, for example, in the situation of transmitting data from UAVs to clarify GIS information and can significantly reduce the operator's work time.

Fedosov V.P., Ibadov R.R., Naumov I.I., Oboymova S.P. Method for identifying roads in rural and suburban areas using satellite images. Electromagnetic waves and electronic systems. 2025. V. 30. № 6. P. 37−53. DOI: https://doi.org/10.18127/j15604128-202506-03 (in Russian)

1. Yin S., Li H. Hot Region Selection Based on Selective Search and Modified Fuzzy C-Means in Remote Sensing Images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 2020. V. 13. P. 5862–5871. DOI 10.1109/JSTARS. 2020.3025582.
2. Shao Z., Zhou Z., Huang X., Zhang Y. MRENet: Simultaneous extraction of road surface and road centerline in complex urban scenes from very high-resolution images. Remote Sensing. 2021. V. 13. № 2. P. 239. DOI 10.3390/rs13020239.
3. Gao L., Zhang X. Above-ground biomass estimation of plantation with complex forest stand structure using multiple features from airborne laser scanning point cloud data. Forests. 2021. V. 12. №. 12. P. 1713. DOI 10.3390/f12121713.
4. Shahid M., Channappayya S.S. Surveying for man-made objects in photographic images. Target and Background Signatures VII – SPIE. 2021. V. 11865. P. 118–127.
5. Zhao K., Li Li., Chen Z., Sun R., Yuan G., Li J. A survey: Optimization and applications of evidence fusion algorithm based on Dempster-Shafer theory. Applied Soft Computing. 2022. V. 124. P. 109075. DOI 10.1016/j.asoc.2022.109075.
6. Zhong M., Zhang L., Liu Xu., Zhou Ya., Zhang M., Wang Ya., Yang Lu., Wei Di. Wide linear range and highly sensitive flexible pressure sensor based on multistage sensing process for health monitoring and human-machine interfaces. Chemical Engineering Journal. 2021. V. 412. P. 128649. DOI 10.1016/j.cej.2021.128649.
7. Asokan A., Anitha J. Adaptive Cuckoo Search based optimal bilateral filtering for denoising of satellite images. ISA Transactions. 2020. V. 100. P. 308–321. DOI 10.1016/j.isatra.2019.11.008.
8. Alsmadi M.K. Content-Based Image Retrieval Using Color, Shape and Texture Descriptors and Features. Arabian Journal for Science and Engineering. 2020. V. 45. № 4. P. 3317–3330. DOI 10.1007/s13369-020-04384-y.
9. Atay Kaya İ., Kut Görgün E. Land use and land cover change monitoring in Bandırma (Turkey) using remote sensing and geographic information systems. Environmental Monitoring and Assessment. 2020. V. 192. № 7. P. 430. DOI 10.1007/s10661-020-08411-1.
10. Wang C., Wei G., Wei G., Wang W., Zhou Y. Tooth Alignment Network Based on Landmark Constraints and Hierarchical Graph Structure. IEEE Transactions on Visualization and Computer Graphics. 2024. V. 30. № 2. P. 1457–1469. DOI 10.1109/TVCG.2022. 3218028.
11. Lu H., Liu Q., Zhang Y., Liu X. A survey of semantic construction and application of satellite remote sensing images and data. Journal of Organizational and End User Computing. 2021. V. 33. № 6. DOI 10.4018/JOEUC.20211101.oa6.
12. Mekhalfa F., Yacef F. Supervised learning for crop/weed classification based on color and texture features. [Electronic resource] – Access mode: https://arxiv.org/pdf/2106.10581, date of reference 23.04.2025.
13. Andy Lease B., Wong Wk., Gopal L., Chiong W.R. Weed Pixel Level Classification Based on Evolving Feature Selection on Local Binary Pattern with Shallow Network Classifier. IOP Conference Series: Materials Science and Engineering. 2020. V. 943. № 1. P. 012001. DOI 10.1088/1757-899x/943/1/012001.
14. Qi Y., Liu N. Innovation of Clothing Design Element Extraction and CAD System Based on Computer Vision and Multimedia Analysis Technology. 2024.
15. Skepasianos I. Texture kinetics and multiscale texture analysis for predicting breast cancer treatment response. 2020.
16. Schlosser A.D., Szabó G., Bertalan L., Szabó S., Varga Z., Enyedi P. Building extraction using orthophotos and dense point cloud derived from visual band aerial imagery based on machine learning and segmentation. Remote Sensing. 2020. V. 12. № 15. P. 2397. DOI 10.3390/RS12152397.
17. Sara D., Mandava A.K., Kumar A., Duela S., Jude A. Hyperspectral and multispectral image fusion techniques for high resolution applications: a review. Earth Science Informatics. 2021. DOI 10.1007/s12145-021-00621-6.
18. Zhang Ch., Zou K., Pan Yu., Zhang Ch. A Method of Apple Image Segmentation Based on Color-Texture Fusion Feature and Machine Learning. Agronomy. 2020. V. 10. № 7. P. 972. DOI 10.3390/agronomy10070972.
19. Chakraborty S., Chatterjee S., Das A., Mali K. Penalized Fuzzy C-Means Enabled Hybrid Region Growing in Segmenting Medical Images. Hybrid Machine Intelligence for Medical Image Analysis. Studies in Computational Intelligence. 2020. V. 841. DOI 10.1007/978-981-13-8930-6_3.
20. Khryashchev V.V., Priorov A.L., Pavlov V.A., Ivanovskiy L.I. Objects segmentation on satellite images using convolution neural networks. Achievements of Modern Radioelectronics. 2019. № 6. P. 28–34. DOI 10.18127/ j20700784-201906-04. (in Russian)
21. Fedosov V.P., Ibadov R.R., Ibadov S.R. Segmentation algorithm for selecting moving objects based on background reconstruction using noise characteristics parameters. Journal of Radio Electronics. 2023. № 11. DOI 10.30898/1684-1719.2023.11.9. (in Russian)
22. Mena J.B., Malpica J.A. An automatic method for road extraction in rural and semi-urban areas starting from high resolution satellite imagery. Pattern recognition letters. 2005. V. 26. № 9. P. 1201–1220. DOI 10.1016/j.patrec.2004.11.005.