Artificial intelligence and machine learning

Research Article

DOI 10.25209/2079-3316-2025-16-4-217-240

Applying the YOLOv11 model and the adapted LaDD dataset to people detection in sparsely populated areas

Alexander Vladimirovich Smirnov¹, Igor Petrovich Tishchenko², Sergey Alexandrovich Lazarev³

1-3	Ailamazyan Program Systems Institute of RAS, Ves'kovo, Russia
1	asmirnov_1991@mail.ru

Abstract. This study is aimed at developing a neural network method for detecting people in sparsely populated areas using images obtained from an unmanned aerial vehicle (UAV). The YOLOv11m architecture model was used as a neural network detector. As part of the study, an adaptation algorithm for the LaDD training dataset was developed and applied. Experiments were conducted to preliminary train the model on the original and adapted datasets, which demonstrated the advisability of using the adapted dataset. The final accuracy of the model during training reached 98.7% by metric $mAP^{50}$ . Model inference showed a detection accuracy of 0.895 (89.5%) by metric F1 and 0.901 (90.1%) by metric $mAP^{50}$ , which confirms the workability of the presented method. (In Russian).

Keywords: Image analysis, people detection, UAV imagery, YOLOv11, neural networks, dataset, adaptation

MSC-2020

68T10; 68T45

For citation: Alexander V. Smirnov, Igor P. Tishchenko, Sergey A. Lazarev. Applying the YOLOv11 model and the adapted LaDD dataset to people detection in sparsely populated areas. Program Systems: Theory and Applications, 2025, 16:4, pp. 217–240. (In Russ.). https://psta.psiras.ru/2025/4_217-240.

Full text of article (PDF): https://psta.psiras.ru/read/psta2025_4_217-240.pdf.

The article was submitted 28.10.2025; approved after reviewing 09.11.2025; accepted for publication 09.11.2025; published online 12.11.2025.