Improvement of the model of object recognition in aero photographs using deep convolutional neural networks

Detection and recognition of objects in images is the main problem to be solved by computer vision systems. As part of solving this problem, the model of object recognition in aerial photographs taken from unmanned aerial vehicles has been improved. A study of object recognition in aerial photograph...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Vadym Slyusar, Mykhailo Protsenko, Anton Chernukha, Pavlo Kovalov, Pavlo Borodych, Serhii Shevchenko, Oleksandr Chernikov, Serhii Vazhynskyi, Oleg Bogatov, Kirill Khrustalev
Formato: article
Lenguaje:EN
RU
UK
Publicado: PC Technology Center 2021
Materias:
Acceso en línea:https://doaj.org/article/6c4c7508553e4bbb984c5cc72423bf2b
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:6c4c7508553e4bbb984c5cc72423bf2b
record_format dspace
spelling oai:doaj.org-article:6c4c7508553e4bbb984c5cc72423bf2b2021-11-04T14:06:13ZImprovement of the model of object recognition in aero photographs using deep convolutional neural networks1729-37741729-406110.15587/1729-4061.2021.243094https://doaj.org/article/6c4c7508553e4bbb984c5cc72423bf2b2021-10-01T00:00:00Zhttp://journals.uran.ua/eejet/article/view/243094https://doaj.org/toc/1729-3774https://doaj.org/toc/1729-4061Detection and recognition of objects in images is the main problem to be solved by computer vision systems. As part of solving this problem, the model of object recognition in aerial photographs taken from unmanned aerial vehicles has been improved. A study of object recognition in aerial photographs using deep convolutional neural networks has been carried out. Analysis of possible implementations showed that the AlexNet 2012 model (Canada) trained on the ImageNet image set (China) is most suitable for this problem solution. This model was used as a basic one. The object recognition error for this model with the use of the ImageNet test set of images amounted to 15 %. To solve the problem of improving the effectiveness of object recognition in aerial photographs for 10 classes of images, the final fully connected layer was modified by rejection from 1,000 to 10 neurons and additional two-stage training of the resulting model. Additional training was carried out with a set of images prepared from aerial photographs at stage 1 and with a set of VisDrone 2021 (China) images at stage 2. Optimal training parameters were selected: speed (step) (0.0001), number of epochs (100). As a result, a new model under the proposed name of AlexVisDrone was obtained. The effectiveness of the proposed model was checked with a test set of 100 images for each class (the total number of classes was 10). Accuracy and sensitivity were chosen as the main indicators of the model effectiveness. As a result, an increase in recognition accuracy from 7 % (for images from aerial photographs) to 9 % (for the VisDrone 2021 set) was obtained which has indicated that the choice of neural network architecture and training parameters was correct. The use of the proposed model makes it possible to automate the process of object recognition in aerial photographs. In the future, it is advisable to use this model at ground stations of unmanned aerial vehicle complex control when processing aerial photographs taken from unmanned aerial vehicles, in robotic systems, in video surveillance complexes and when designing unmanned vehicle systemsVadym SlyusarMykhailo ProtsenkoAnton ChernukhaPavlo KovalovPavlo BorodychSerhii ShevchenkoOleksandr ChernikovSerhii VazhynskyiOleg BogatovKirill KhrustalevPC Technology Centerarticleobject recognitiondeep convolutional neural networkaerial photographunmanned aerial vehicleTechnology (General)T1-995IndustryHD2321-4730.9ENRUUKEastern-European Journal of Enterprise Technologies, Vol 5, Iss 2 (113), Pp 6-21 (2021)
institution DOAJ
collection DOAJ
language EN
RU
UK
topic object recognition
deep convolutional neural network
aerial photograph
unmanned aerial vehicle
Technology (General)
T1-995
Industry
HD2321-4730.9
spellingShingle object recognition
deep convolutional neural network
aerial photograph
unmanned aerial vehicle
Technology (General)
T1-995
Industry
HD2321-4730.9
Vadym Slyusar
Mykhailo Protsenko
Anton Chernukha
Pavlo Kovalov
Pavlo Borodych
Serhii Shevchenko
Oleksandr Chernikov
Serhii Vazhynskyi
Oleg Bogatov
Kirill Khrustalev
Improvement of the model of object recognition in aero photographs using deep convolutional neural networks
description Detection and recognition of objects in images is the main problem to be solved by computer vision systems. As part of solving this problem, the model of object recognition in aerial photographs taken from unmanned aerial vehicles has been improved. A study of object recognition in aerial photographs using deep convolutional neural networks has been carried out. Analysis of possible implementations showed that the AlexNet 2012 model (Canada) trained on the ImageNet image set (China) is most suitable for this problem solution. This model was used as a basic one. The object recognition error for this model with the use of the ImageNet test set of images amounted to 15 %. To solve the problem of improving the effectiveness of object recognition in aerial photographs for 10 classes of images, the final fully connected layer was modified by rejection from 1,000 to 10 neurons and additional two-stage training of the resulting model. Additional training was carried out with a set of images prepared from aerial photographs at stage 1 and with a set of VisDrone 2021 (China) images at stage 2. Optimal training parameters were selected: speed (step) (0.0001), number of epochs (100). As a result, a new model under the proposed name of AlexVisDrone was obtained. The effectiveness of the proposed model was checked with a test set of 100 images for each class (the total number of classes was 10). Accuracy and sensitivity were chosen as the main indicators of the model effectiveness. As a result, an increase in recognition accuracy from 7 % (for images from aerial photographs) to 9 % (for the VisDrone 2021 set) was obtained which has indicated that the choice of neural network architecture and training parameters was correct. The use of the proposed model makes it possible to automate the process of object recognition in aerial photographs. In the future, it is advisable to use this model at ground stations of unmanned aerial vehicle complex control when processing aerial photographs taken from unmanned aerial vehicles, in robotic systems, in video surveillance complexes and when designing unmanned vehicle systems
format article
author Vadym Slyusar
Mykhailo Protsenko
Anton Chernukha
Pavlo Kovalov
Pavlo Borodych
Serhii Shevchenko
Oleksandr Chernikov
Serhii Vazhynskyi
Oleg Bogatov
Kirill Khrustalev
author_facet Vadym Slyusar
Mykhailo Protsenko
Anton Chernukha
Pavlo Kovalov
Pavlo Borodych
Serhii Shevchenko
Oleksandr Chernikov
Serhii Vazhynskyi
Oleg Bogatov
Kirill Khrustalev
author_sort Vadym Slyusar
title Improvement of the model of object recognition in aero photographs using deep convolutional neural networks
title_short Improvement of the model of object recognition in aero photographs using deep convolutional neural networks
title_full Improvement of the model of object recognition in aero photographs using deep convolutional neural networks
title_fullStr Improvement of the model of object recognition in aero photographs using deep convolutional neural networks
title_full_unstemmed Improvement of the model of object recognition in aero photographs using deep convolutional neural networks
title_sort improvement of the model of object recognition in aero photographs using deep convolutional neural networks
publisher PC Technology Center
publishDate 2021
url https://doaj.org/article/6c4c7508553e4bbb984c5cc72423bf2b
work_keys_str_mv AT vadymslyusar improvementofthemodelofobjectrecognitioninaerophotographsusingdeepconvolutionalneuralnetworks
AT mykhailoprotsenko improvementofthemodelofobjectrecognitioninaerophotographsusingdeepconvolutionalneuralnetworks
AT antonchernukha improvementofthemodelofobjectrecognitioninaerophotographsusingdeepconvolutionalneuralnetworks
AT pavlokovalov improvementofthemodelofobjectrecognitioninaerophotographsusingdeepconvolutionalneuralnetworks
AT pavloborodych improvementofthemodelofobjectrecognitioninaerophotographsusingdeepconvolutionalneuralnetworks
AT serhiishevchenko improvementofthemodelofobjectrecognitioninaerophotographsusingdeepconvolutionalneuralnetworks
AT oleksandrchernikov improvementofthemodelofobjectrecognitioninaerophotographsusingdeepconvolutionalneuralnetworks
AT serhiivazhynskyi improvementofthemodelofobjectrecognitioninaerophotographsusingdeepconvolutionalneuralnetworks
AT olegbogatov improvementofthemodelofobjectrecognitioninaerophotographsusingdeepconvolutionalneuralnetworks
AT kirillkhrustalev improvementofthemodelofobjectrecognitioninaerophotographsusingdeepconvolutionalneuralnetworks
_version_ 1718444844224872448