Applied software systems

Research Article

Using the Mask R-CNN model for segmentation of real estate objects in aerial photographs

Igor Victorovich Vinokurov

	Financial University under the Government of the Russian Federation, Moscow, Russia
	igvvinokurov@fa.ru

Abstract. The mass appearance of illegal and unregistered in the Unified State Register of Real Estate (USRRE) real estate objects complicates cadastral registration for many entities at the territorial and administrative levels. Traditional methods of identifying objects of this type, based on manual analysis of geospatial data, are labor-intensive and time-consuming.

To improve the efficiency of this process, it is proposed to automate the detection of objects in aerial photographs by solving the instance segmentation problem using the Mask R-CNN deep learning model. The article describes the preparation of a dataset for this model, examines the main quality metrics, and analyzes the results obtained. The efficiency of the Mask R-CNN model in practice is shown for solving the problem of detecting construction projects that are not registered in the USRRE. (Linked article texts in English and in Russian).

Keywords: Cadastral registration, aerial photography analysis, instance segmentation, Mask R-CNN, PyTorch

MSC-2020 68T20; 68T07, 68T45

For citation: Igor V. Vinokurov. Using the Mask R-CNN model for segmentation of real estate objects in aerial photographs. Program Systems: Theory and Applications, 2025, 16:1, pp. 3–44. (in Engl. In Russ.). https://psta.psiras.ru/2025/1_3-44.

Full text of bilingual article (PDF): https://psta.psiras.ru/read/psta2025_1_3-44.pdf (Clicking on the flag in the header switches the page language).

The article was submitted 21.10.2024; approved after reviewing 24.12.2024; accepted for publication 11.01.2025; published online 31.01.2025.