इसे छोड़कर सामग्री पर बढ़ने के लिए

Enhancing Unmanned Aerial Vehicle Object Detection via Tensor Decompositions and Positive–Negative Momentum Optimizers

The current development of machine learning has advanced many fields in applied sciences and industry, including remote sensing. In this area, deep neural networks are used to solve routine object detection problems, satisfying the required rules and conditions. However, the growing number and diffi...

पूर्ण विवरण

में बचाया:
ग्रंथसूची विवरण
मुख्य लेखकों: Abdulkadirov, R. I., Абдулкадиров, Р. И., Lyakhov, P. A., Ляхов, П. А., Nagornov, N. N., Нагорнов, Н. Н., Reznikov, D. K., Резников, Д. К., Bobrov, A. A., Бобров, А. А., Kalita, D. I., Калита, Д. И.
स्वरूप: Статья
भाषा:English
प्रकाशित: Multidisciplinary Digital Publishing Institute (MDPI) 2025
विषय:
ऑनलाइन पहुंच:https://dspace.ncfu.ru/handle/123456789/30391
टैग : टैग जोड़ें
कोई टैग नहीं, इस रिकॉर्ड को टैग करने वाले पहले व्यक्ति बनें!
id ir-123456789-30391
record_format dspace
spelling ir-123456789-303912025-04-03T12:56:38Z Enhancing Unmanned Aerial Vehicle Object Detection via Tensor Decompositions and Positive–Negative Momentum Optimizers Abdulkadirov, R. I. Абдулкадиров, Р. И. Lyakhov, P. A. Ляхов, П. А. Nagornov, N. N. Нагорнов, Н. Н. Reznikov, D. K. Резников, Д. К. Bobrov, A. A. Бобров, А. А. Kalita, D. I. Калита, Д. И. Neural networks Tensor decomposition Optimization Positive–negative moments Remote sensing The current development of machine learning has advanced many fields in applied sciences and industry, including remote sensing. In this area, deep neural networks are used to solve routine object detection problems, satisfying the required rules and conditions. However, the growing number and difficulty of such problems cause the developers to construct machine learning models with higher computational complexities, such as an increased number of hidden layers, epochs, learning rate, and rate decay. In this paper, we propose the Yolov8 architecture with decomposed layers via canonical polyadic and Tucker methods for accelerating the solving of the object detection problem in satellite images. Our positive–negative momentum approaches enabled a reduction in the loss in precision and recall assessments for the proposed neural network. The convolutional layer factorization reduces the shapes and accelerates the computations at kernel nodes in the proposed deep learning models. The advanced optimization algorithms achieve the global minimum of loss functions, which makes the precision and recall metrics superior to the ones for their known counterparts. We examined the proposed Yolov8 with decomposed layers, comparing it with the conventional Yolov8 on the DIOR and VisDrone 2020 datasets containing the UAV images. We verified the performance of the proposed and known neural networks on different optimizers. It is shown that the proposed neural network accelerates the solving object detection problem by 44–52%. The proposed Yolov8 with Tucker and canonical polyadic decompositions has greater precision and recall metrics than the usual Yolov8 with known analogs by 0.84–0.94 and 0.228–1.107 percentage points, respectively. 2025-04-03T12:54:23Z 2025-04-03T12:54:23Z 2025 Статья Abdulkadirov R., Lyakhov P., Butusov D., Nagornov N., Reznikov D., Bobrov A., Kalita D. Enhancing Unmanned Aerial Vehicle Object Detection via Tensor Decompositions and Positive–Negative Momentum Optimizers // Mathematics. - 2025. - 13 (5). - art. no. 828. - DOI: 10.3390/math13050828 https://dspace.ncfu.ru/handle/123456789/30391 en Mathematics application/pdf application/pdf Multidisciplinary Digital Publishing Institute (MDPI)
institution СКФУ
collection Репозиторий
language English
topic Neural networks
Tensor decomposition
Optimization
Positive–negative moments
Remote sensing
spellingShingle Neural networks
Tensor decomposition
Optimization
Positive–negative moments
Remote sensing
Abdulkadirov, R. I.
Абдулкадиров, Р. И.
Lyakhov, P. A.
Ляхов, П. А.
Nagornov, N. N.
Нагорнов, Н. Н.
Reznikov, D. K.
Резников, Д. К.
Bobrov, A. A.
Бобров, А. А.
Kalita, D. I.
Калита, Д. И.
Enhancing Unmanned Aerial Vehicle Object Detection via Tensor Decompositions and Positive–Negative Momentum Optimizers
description The current development of machine learning has advanced many fields in applied sciences and industry, including remote sensing. In this area, deep neural networks are used to solve routine object detection problems, satisfying the required rules and conditions. However, the growing number and difficulty of such problems cause the developers to construct machine learning models with higher computational complexities, such as an increased number of hidden layers, epochs, learning rate, and rate decay. In this paper, we propose the Yolov8 architecture with decomposed layers via canonical polyadic and Tucker methods for accelerating the solving of the object detection problem in satellite images. Our positive–negative momentum approaches enabled a reduction in the loss in precision and recall assessments for the proposed neural network. The convolutional layer factorization reduces the shapes and accelerates the computations at kernel nodes in the proposed deep learning models. The advanced optimization algorithms achieve the global minimum of loss functions, which makes the precision and recall metrics superior to the ones for their known counterparts. We examined the proposed Yolov8 with decomposed layers, comparing it with the conventional Yolov8 on the DIOR and VisDrone 2020 datasets containing the UAV images. We verified the performance of the proposed and known neural networks on different optimizers. It is shown that the proposed neural network accelerates the solving object detection problem by 44–52%. The proposed Yolov8 with Tucker and canonical polyadic decompositions has greater precision and recall metrics than the usual Yolov8 with known analogs by 0.84–0.94 and 0.228–1.107 percentage points, respectively.
format Статья
author Abdulkadirov, R. I.
Абдулкадиров, Р. И.
Lyakhov, P. A.
Ляхов, П. А.
Nagornov, N. N.
Нагорнов, Н. Н.
Reznikov, D. K.
Резников, Д. К.
Bobrov, A. A.
Бобров, А. А.
Kalita, D. I.
Калита, Д. И.
author_facet Abdulkadirov, R. I.
Абдулкадиров, Р. И.
Lyakhov, P. A.
Ляхов, П. А.
Nagornov, N. N.
Нагорнов, Н. Н.
Reznikov, D. K.
Резников, Д. К.
Bobrov, A. A.
Бобров, А. А.
Kalita, D. I.
Калита, Д. И.
author_sort Abdulkadirov, R. I.
title Enhancing Unmanned Aerial Vehicle Object Detection via Tensor Decompositions and Positive–Negative Momentum Optimizers
title_short Enhancing Unmanned Aerial Vehicle Object Detection via Tensor Decompositions and Positive–Negative Momentum Optimizers
title_full Enhancing Unmanned Aerial Vehicle Object Detection via Tensor Decompositions and Positive–Negative Momentum Optimizers
title_fullStr Enhancing Unmanned Aerial Vehicle Object Detection via Tensor Decompositions and Positive–Negative Momentum Optimizers
title_full_unstemmed Enhancing Unmanned Aerial Vehicle Object Detection via Tensor Decompositions and Positive–Negative Momentum Optimizers
title_sort enhancing unmanned aerial vehicle object detection via tensor decompositions and positive–negative momentum optimizers
publisher Multidisciplinary Digital Publishing Institute (MDPI)
publishDate 2025
url https://dspace.ncfu.ru/handle/123456789/30391
work_keys_str_mv AT abdulkadirovri enhancingunmannedaerialvehicleobjectdetectionviatensordecompositionsandpositivenegativemomentumoptimizers
AT abdulkadirovri enhancingunmannedaerialvehicleobjectdetectionviatensordecompositionsandpositivenegativemomentumoptimizers
AT lyakhovpa enhancingunmannedaerialvehicleobjectdetectionviatensordecompositionsandpositivenegativemomentumoptimizers
AT lâhovpa enhancingunmannedaerialvehicleobjectdetectionviatensordecompositionsandpositivenegativemomentumoptimizers
AT nagornovnn enhancingunmannedaerialvehicleobjectdetectionviatensordecompositionsandpositivenegativemomentumoptimizers
AT nagornovnn enhancingunmannedaerialvehicleobjectdetectionviatensordecompositionsandpositivenegativemomentumoptimizers
AT reznikovdk enhancingunmannedaerialvehicleobjectdetectionviatensordecompositionsandpositivenegativemomentumoptimizers
AT reznikovdk enhancingunmannedaerialvehicleobjectdetectionviatensordecompositionsandpositivenegativemomentumoptimizers
AT bobrovaa enhancingunmannedaerialvehicleobjectdetectionviatensordecompositionsandpositivenegativemomentumoptimizers
AT bobrovaa enhancingunmannedaerialvehicleobjectdetectionviatensordecompositionsandpositivenegativemomentumoptimizers
AT kalitadi enhancingunmannedaerialvehicleobjectdetectionviatensordecompositionsandpositivenegativemomentumoptimizers
AT kalitadi enhancingunmannedaerialvehicleobjectdetectionviatensordecompositionsandpositivenegativemomentumoptimizers
_version_ 1842245384070496256