?
Analysis of Deep Feature Matching Algorithms in UAV Visual Localization
.
Prutyanov V., Тернов М. А., Костров Д. С.
The work presents an analysis of the application of deep learning-based methods for the keypoint extraction and matching in the context of map-aided UAV visual localization. A method for visual localization in three degrees of freedom is proposed, which employs pretrained SuperPoint and LightGlue networks for both short-term optical flow and global frame-to-map matching components. The ability of SuperPoint and LightGlue to refine a prediction of a less accurate location estimator without fine-tuning was estimated. The accuracy of the proposed method was evaluated and a detailed analysis of keypoint-based image matching algorithms was conducted on the AdM_UAV dataset. The performance evaluation of the proposed method was carried out on NVIDIA Jetson Orin Nano and shows acceptable results for real-time visual localization on this hardware platform.
Aleksei Samarin, Nazarenko A., Alexander Savelev et al., Pattern Recognition and Image Analysis 2024 Vol. 34 No. 3 P. 844–854
Improving image quality is becoming an increasingly popular task, especially when working with mobile devices. One common approach to image enhancement is the use of convolutional neural networks. However, to achieve good results, such networks must be large enough, otherwise there is a risk of unwanted artifacts. In addition, large convolutional neural networks require significant ...
Added: September 21, 2026
Aleksei Samarin, Aleksei Toropov, Alexander Savelev et al., , in: Pattern Recognition. ICPR 2024 International Workshops and Challenges.: Cham: Springer, 2025. P. 308–320.
This research explores an innovative approach to enhancing the accuracy of detecting small microorganisms in complex microscopic environments. Our study introduces a streamlined, hybrid image pre-processing model specifically designed to address the challenges of identifying diplococci in live microscopy of dynamic samples. By integrating pre-defined filtering techniques with predictive adjustments for optimal applicability, our method ...
Added: September 21, 2026
Cham: Springer, 2026.
computer vision ...
Added: September 19, 2026
Aleksei Samarin, Aleksei Toropov, Dzestelova A. et al., , in: Proceedings of the 36th Conference of Open Innovations Association FRUCT, Helsinki, Finland, 30 October - 1 November 2024Vol. 36.: FRUCT Oy, 2024. P. 903–911.
In this work, we describe our research aimed at developing classifiers for microbial images (bacilli images) obtained through microscopy of live (non-static) samples. We employed our proposed approach called AutoML, which is based on the automatic generation and analysis of the feature space to create the most optimal descriptors for microscopic images used in their ...
Added: September 19, 2026
FRUCT Oy, 2024.
Added: September 19, 2026
Aleksei Samarin, Aleksei Toropov, Kotenko E. et al., , in: Proceedings of the 37th Conference of Open Innovations Association FRUCT, Helsinki, Finland, 14-16 May 2025, Issue 1 (Full Papers)Vol. 37.: Helsinki: FRUCT Oy, 2025. P. 278–284.
This study introduces an innovative method for recognizing automatically generated images by utilizing adapted descriptors specifically designed to analyze unique structural and morphological features characteristic of artificially created content. The methodology focuses on analyzing features inherent to image generation processes, ensuring the optimization of descriptors for identifying complex and subtle patterns associated with generative algorithms. ...
Added: September 19, 2026
Helsinki: FRUCT Oy, 2025.
Added: September 19, 2026
Helsinki: FRUCT Oy, 2026.
Added: September 19, 2026
Зуенко Д. О., Trofimova E., Хайдарова И., IEEE Access 2026 Vol. 14 P. 121339–121357
Oil spill segmentation in Synthetic Aperture Radar (SAR) images is limited by noisy annotations in publicly available datasets and by architectural choices that interact with label quality in opposing directions. First, we introduce a manually refined version of the Deep-SAR Oil Spill (SOS) dataset, in which 36.25% of masks are corrected for false positives, missed ...
Added: September 7, 2026
Kaznacheev P. A., Indakov G. S., Podymova N. B. et al., Izvestiya - Physics of the Solid Earth 2026 Vol. 61 P. 68–80
The paper discusses methods for estimating the grain size of polycrystalline materials based on the analysis of optical microscopic images, as well as the possibility of applying these methods to the analysis of rock textures. A comparison of the results obtained using several methods on a single sample of metamorphosed sandstone from the Northern Ladoga ...
Added: August 31, 2026
Gamberov T., Safin R., Chebotareva E. et al., , in: 2025 9th International Conference on Information, Control, and Communication Technologies (ICCT-2025).: IEEE, 2025. P. 1–5.
Digital human models (DHM) for virtual environments allow a cost-effective and reproducible evaluation of computer vision algorithms that are employed in robotics, e.g., human detection, tracking and following. Yet, many popular robotics simulators do not achieve a reasonable level of realism and diversity required to rigorously test such algorithms under varying conditions. This paper introduces ...
Added: June 23, 2026
Faizullin R., Mustafin M., Svinin M. et al., , in: 2025 9th International Conference on Information, Control, and Communication Technologies (ICCT-2025).: IEEE, 2025. P. 1–4.
This work addresses the problem of energy-constrained coverage of agricultural fields using a fleet of identical unmanned aerial vehicles (UAVs). Each UAV must complete a spraying mission over a designated area, subject to limited battery capacity. To ensure energy feasibility, static charging stations are deployed along the field’s perimeter. The agricultural field is first partitioned ...
Added: June 23, 2026
Slivnitsin P., Mylnikov L., Engineering Applications of Artificial Intelligence 2026 Vol. 179 Article 115185
The paper describes a applied artificial intelligence task of recognition-by-components method of real objects based on the recognition of a limited set of primitives or components. The recognition-by-components makes it possible to determine the components, that compose an object, and increase the number of recognizable objects without degrading the recognition quality. Training is performed on ...
Added: May 29, 2026
Kondratev S., Yulia Dyrchenkova, Georgiy Nikitin et al., Technologies 2026 Vol. 14 No. 1 Article 69
This paper presents Aerokinesis, an IoT-based software–hardware system for intuitive gesture-driven control of quadcopter unmanned aerial vehicles (UAVs), developed within the Robot Operating System 2 (ROS2) framework. The proposed system addresses the challenge of providing an accessible human–drone interaction interface for operators in scenarios where traditional remote controllers are impractical or unavailable. The architecture comprises ...
Added: May 19, 2026
Vaschenko A., Frolov O., Safin R. et al., , in: 16th International Conference on Intelligent Systems, INTELS 2024, Moscow, Russia, December 2–4, 2024, Proceedings, Part I. Intelligent Systems. (CCIS, volume 2603).: Springer, 2025. P. 311–324.
Swarm robotics is a complex domain within multi-robot systems that encompasses formation control, movement control, and interUAV communication. Coordinates task execution requires effctive swarm control, which relies on robust motion control algorithms and reliable data exchange mechanisms. In this work, we propose an operator-leaderfollowers approach for managing UAV swarms. It comprises the following components: centralized swarm control utilizing ...
Added: March 17, 2026
Frolov O. V., Safin R. N., Tsoy T. G. et al., Ученые записки Казанского университета. Серия: Физико-математические науки 2025 Vol. 167 No. 4 P. 786–805
Advancements in robotics have expanded a use of unmanned aerial vehicle (UAV) swarms in
critical tasks such as disaster response, including search and rescue operations during floods, hurricanes,
landsliding, and earthquakes. Swarm formation control stands as a critical challenge in UAV swarm
control. In this article, a simple and resource-efficient method for addressing collisions within swarm
formations during outdoor ...
Added: March 17, 2026
Myzina A., Safin R., Tsoy T. et al., , in: Proceedings Volume 14073, Fifth International Conference on Artificial Intelligence, Automation, and Algorithms (AI2A 2025).: [б.и.], 2026.
Floods are among the most destructive natural disasters, causing human casualties and severe economic damage. Effective monitoring of flooded areas requires automated systems capable of real-time perception and decision-making. This paper proposes a water surface segmentation model based on the U-Net architecture, trained entirely on synthetic data generated in the Gazebo simulator with variations in ...
Added: March 17, 2026
Pikul A. S., Безопасность информационных технологий 2024 Т. 31 № 4 С. 116–127
This article explores the potential use of modern computer vision architectures for the task of deepfake detection. The following architectures are considered: EfficientNet, Vision Transformer (ViT), VisionLSTM (ViL), Vision KAN, and Mamba Vision. The novelty of the approach lies in the application and comparison of these architectures, as well as their combination into paired ensembles ...
Added: December 12, 2025
[б.и.], 2026.
The Winter Conference on Applications of Computer Vision is the premier international computer vision event comprising the main conference and several co-located workshops and tutorials. With its high quality and low cost, it provides an exceptional value for students, academics and industry researchers. ...
Added: November 24, 2025
Viktor V. Prutyanov, Nikita L. Korolev, Aleksandr Y. Romanov, , in: 2025 International Russian Automation Conference (RusAutoCon).: IEEE, 2025. P. 350–354.
This paper presents a UAV visual localization system that leverages zero-shot deep feature matching to achieve localization in 4 degrees of freedom. The proposed system combines short-term optical flow and long-term map matching techniques, integrated through a Kalman filter for robust measurement fusion. Key contributions include the use of pre-trained deep learning models (SuperPoint, ALIKED, ...
Added: November 6, 2025