Enhancing Drone Detection via Transformer Neural Network and Positive–Negative Momentum Optimizers

The rapid development of unmanned aerial vehicles (UAVs) has had a significant impact on the growth of the economic, industrial, and social welfare of society. The possibility of reaching places that are difficult and dangerous for humans to access with minimal use of third-party resources increases...

Полное описание

Сохранить в:

Библиографические подробности
Главные авторы:	Lyakhov, P. A., Ляхов, П. А., Pismennyy, V. A., Письменный, В. А., Abdulkadirov, R. I., Абдулкадиров, Р. И., Nagornov, N. N., Нагорнов, Н. Н., Kalita, D. I., Калита, Д. И.
Формат:	Статья
Язык:	English
Опубликовано:	Multidisciplinary Digital Publishing Institute (MDPI) 2025
Темы:	Moving object detection Economic welfare Optimization methods Antennas Yolov12 Accidents Drones Network architecture Object recognition System theory Object detection Video cameras Aerial vehicle
Online-ссылка:	https://dspace.ncfu.ru/handle/123456789/31850
Метки:	Добавить метку Нет меток, Требуется 1-ая метка записи!

id	ir-123456789-31850
record_format	dspace
spelling	ir-123456789-318502025-08-13T12:12:48Z Enhancing Drone Detection via Transformer Neural Network and Positive–Negative Momentum Optimizers Lyakhov, P. A. Ляхов, П. А. Pismennyy, V. A. Письменный, В. А. Abdulkadirov, R. I. Абдулкадиров, Р. И. Nagornov, N. N. Нагорнов, Н. Н. Kalita, D. I. Калита, Д. И. Moving object detection Economic welfare Optimization methods Antennas Yolov12 Accidents Drones Network architecture Object recognition System theory Object detection Video cameras Aerial vehicle The rapid development of unmanned aerial vehicles (UAVs) has had a significant impact on the growth of the economic, industrial, and social welfare of society. The possibility of reaching places that are difficult and dangerous for humans to access with minimal use of third-party resources increases the efficiency and quality of maintenance of construction structures, agriculture, and exploration, which are carried out with the help of drones with a predetermined trajectory. The widespread use of UAVs has caused problems with the control of the drones’ correctness following a given route, which leads to emergencies and accidents. Therefore, UAV monitoring with video cameras is of great importance. In this paper, we propose a Yolov12 architecture with positive–negative pulse-based optimization algorithms to solve the problem of drone detection on video data. Self-attention-based mechanisms in transformer neural networks (NNs) improved the quality of drone detection on video. The developed algorithms for training NN architectures improved the accuracy of drone detection by achieving the global extremum of the loss function in fewer epochs using positive–negative pulse-based optimization algorithms. The proposed approach improved object detection accuracy by 2.8 percentage points compared to known state-of-the-art analogs. 2025-08-13T12:09:16Z 2025-08-13T12:09:16Z 2025 Статья Lyakhov, P. A., Butusov, D. N., Pismennyy, V. A., Abdulkadirov, R. I., Nagornov, N. N., Ostrovskii, V. Y., Kalita, D. I. Enhancing Drone Detection via Transformer Neural Network and Positive–Negative Momentum Optimizers // Big Data and Cognitive Computing. - 2025. - 9 (7). - art. no. 167. - DOI: 10.3390/bdcc9070167 https://dspace.ncfu.ru/handle/123456789/31850 en Big Data and Cognitive Computing application/pdf application/pdf Multidisciplinary Digital Publishing Institute (MDPI)
institution	СКФУ
collection	Репозиторий
language	English
topic	Moving object detection Economic welfare Optimization methods Antennas Yolov12 Accidents Drones Network architecture Object recognition System theory Object detection Video cameras Aerial vehicle
spellingShingle	Moving object detection Economic welfare Optimization methods Antennas Yolov12 Accidents Drones Network architecture Object recognition System theory Object detection Video cameras Aerial vehicle Lyakhov, P. A. Ляхов, П. А. Pismennyy, V. A. Письменный, В. А. Abdulkadirov, R. I. Абдулкадиров, Р. И. Nagornov, N. N. Нагорнов, Н. Н. Kalita, D. I. Калита, Д. И. Enhancing Drone Detection via Transformer Neural Network and Positive–Negative Momentum Optimizers
description	The rapid development of unmanned aerial vehicles (UAVs) has had a significant impact on the growth of the economic, industrial, and social welfare of society. The possibility of reaching places that are difficult and dangerous for humans to access with minimal use of third-party resources increases the efficiency and quality of maintenance of construction structures, agriculture, and exploration, which are carried out with the help of drones with a predetermined trajectory. The widespread use of UAVs has caused problems with the control of the drones’ correctness following a given route, which leads to emergencies and accidents. Therefore, UAV monitoring with video cameras is of great importance. In this paper, we propose a Yolov12 architecture with positive–negative pulse-based optimization algorithms to solve the problem of drone detection on video data. Self-attention-based mechanisms in transformer neural networks (NNs) improved the quality of drone detection on video. The developed algorithms for training NN architectures improved the accuracy of drone detection by achieving the global extremum of the loss function in fewer epochs using positive–negative pulse-based optimization algorithms. The proposed approach improved object detection accuracy by 2.8 percentage points compared to known state-of-the-art analogs.
format	Статья
author	Lyakhov, P. A. Ляхов, П. А. Pismennyy, V. A. Письменный, В. А. Abdulkadirov, R. I. Абдулкадиров, Р. И. Nagornov, N. N. Нагорнов, Н. Н. Kalita, D. I. Калита, Д. И.
author_facet	Lyakhov, P. A. Ляхов, П. А. Pismennyy, V. A. Письменный, В. А. Abdulkadirov, R. I. Абдулкадиров, Р. И. Nagornov, N. N. Нагорнов, Н. Н. Kalita, D. I. Калита, Д. И.
author_sort	Lyakhov, P. A.
title	Enhancing Drone Detection via Transformer Neural Network and Positive–Negative Momentum Optimizers
title_short	Enhancing Drone Detection via Transformer Neural Network and Positive–Negative Momentum Optimizers
title_full	Enhancing Drone Detection via Transformer Neural Network and Positive–Negative Momentum Optimizers
title_fullStr	Enhancing Drone Detection via Transformer Neural Network and Positive–Negative Momentum Optimizers
title_full_unstemmed	Enhancing Drone Detection via Transformer Neural Network and Positive–Negative Momentum Optimizers
title_sort	enhancing drone detection via transformer neural network and positive–negative momentum optimizers
publisher	Multidisciplinary Digital Publishing Institute (MDPI)
publishDate	2025
url	https://dspace.ncfu.ru/handle/123456789/31850
work_keys_str_mv	AT lyakhovpa enhancingdronedetectionviatransformerneuralnetworkandpositivenegativemomentumoptimizers AT lâhovpa enhancingdronedetectionviatransformerneuralnetworkandpositivenegativemomentumoptimizers AT pismennyyva enhancingdronedetectionviatransformerneuralnetworkandpositivenegativemomentumoptimizers AT pisʹmennyjva enhancingdronedetectionviatransformerneuralnetworkandpositivenegativemomentumoptimizers AT abdulkadirovri enhancingdronedetectionviatransformerneuralnetworkandpositivenegativemomentumoptimizers AT abdulkadirovri enhancingdronedetectionviatransformerneuralnetworkandpositivenegativemomentumoptimizers AT nagornovnn enhancingdronedetectionviatransformerneuralnetworkandpositivenegativemomentumoptimizers AT nagornovnn enhancingdronedetectionviatransformerneuralnetworkandpositivenegativemomentumoptimizers AT kalitadi enhancingdronedetectionviatransformerneuralnetworkandpositivenegativemomentumoptimizers AT kalitadi enhancingdronedetectionviatransformerneuralnetworkandpositivenegativemomentumoptimizers
_version_	1842245481486352384

Enhancing Drone Detection via Transformer Neural Network and Positive–Negative Momentum Optimizers

Схожие документы