Building Recognition Hybrid Algorithm for Satellite Images Based on the Beetle Method and the Area Exclusion Algorithm
DOI:
https://doi.org/10.14529/cmse240204Keywords:
building recognition, satellite imagery, hybrid method, beetle method, area exclusion method, textural characteristics, building boundaries, potential areas, classificationAbstract
The article proposes a new method for recognizing buildings on satellite images. The proposed method is a hybrid, it is based on the region exclusion algorithm and the beetle method. The region exclusion algorithm is a well-known and effective approach to object detection on the image. Its main idea is to segment an image into regions of similar pixels based on various characteristics: color, texture, brightness, shape, etc. The beetle method is a classic contour analysis method that sequentially draws the boundary between an object and its background. As part of the proposed method, the beetle method first identifies potential areas where buildings may be located. The region exclusion method then eliminates unwanted elements in the image (vegetation, water surfaces and roads) that could be falsely identified as buildings, and accurately determines the location and outline of buildings. The offered algorithm shows good recognition accuracy regardless of image quality and does not require a training sample. The article also describes the software implementation of the proposed method and discusses the results of computational experiments to assess the quality of the method and compare it with three well-known recognition algorithms.References
Gilin S.V. The task of automatic recognition of buildings in water protection zones on satellite images. Information Technologies and Mathematical Modeling (ITMM-2021): Proceedings of the XX International Conference named after A.F. Terpugov, Tomsk, Russia, December 1–5, 2021. Tomsk: National Research Tomsk State University, 2022. P. 6–12. (in Russian)
Zaharov A.A., Tujilkin A.Y. Segmentation of satellite images based on super pixels and graph sections. Software systems and computational methods. 2018. No. 1. P. 7–17. (in Russian) DOI: 10.7256/2454-0714.2018.1.25629.
Fukunaga K. An introduction to the statistical theory of pattern recognition. Moscow: Science, 2009. 368 p. (in Russian)
Gorbachev V.A., Krivorotov I.A., Markelov A.O., Kotlyarova E.V. Semantic segmentation of satellite images of airports using convolutional neural networks. Computer optics. 2020. Vol. 44, no. 4. P. 636–645. (in Russian) DOI: 10.18287/2412-6179-CO-636.
Shahoud А., Shashev D., Shidlovskiy S. Detection of Good Matching Areas Using Convolutional Neural Networks in Scene Matching-Based Navigation Systems. Annual International Conference on Computer Graphics and Machine Vision GraphiCon (GraphiCon-2021): Proceedings of the International Conference on Computer Graphics and Machine Vision “Graphicon”, Tomsk, Russia, September 27–30, 2021. Moscow, M.V. Keldysh Institute of Applied Mathematics of the Russian Academy of Sciences, 2021. P. 443–452. (in Russian)
He W., Li J., Cao W., Zhang L., Zhang H. Building Extraction from Remote Sensing Images via an Uncertainty-Aware Network. URL: https://arxiv.org/pdf/2307.12309 (accessed: 15.02.2024).
Sorokin D.V., Krylov A.S. The active contour method for image segmentation. Moscow: LTD “MAX Press”, 2022. 116 p. (in Russian)
Chernov A.V., Chupshev N.V. Automatic detection of building contours in cartographic images. Computer optics. 2007. Vol. 31, no. 4. P. 636–645. (in Russian)
Panchenko D.S., Putyanin E.P. Comparative analysis of image segmentation methods. Radio electronics and computer science. 1999. Vol. 4. P. 109–114. (in Russian)
Vorontsov K.V. Mathematical methods of teaching by use cases. URL: http://www.machinelearning.ru/wiki/images/6/6d/Voron-ML-1.pdf (accessed: 10.09.2023). (in Russian)
Xu Yu., Wang К., Liu S., Yang S., Yan B. Atmospheric correction of hyperspectral data using MODTRAN model. Remote Sensing of the Environment: 16th National Symposium on Remote Sensing of China. 2008. Vol. 7123. P. 1–7. DOI: 10.1117/12.815552.
Golub Y.I., Starovoytov V.V., Konoplin E.E. Segmentation of areas with approximately uniform brightness. Artificial intelligence. 2008. Vol. 3. P. 332–338. (in Russian)
Furman Y.А., Kreveckiy A.V., Peredreev A.K. An introduction to contour analysis and its applications to image and signal processing. Moscow: PHYSICAL ANALYSIS, 2002. 592 p. (in Russian)
Sakovich I.O., Belov Y.S. Overview of the main methods of contour analysis for highlighting the contours of moving objects. Engineering Journal: Science and Innovation. 2014. Vol. 36, no. 12. P. 1–11. (in Russian)
