Deep learning-based oriented object detection in remote sensing imagery: YOLOv7-OBB

Bibliographic Details
Main Author: Santos, Pietro Terra Pizzutti dos
Publication Date: 2023
Language: eng
Source: Manancial - Repositório Digital da UFSM
dARK ID: ark:/26339/001300000w0x6
Download full: http://repositorio.ufsm.br/handle/1/27722
Summary: Trabalho de conclusão de curso (graduação) - Universidade Federal de Santa Maria, Centro de Tecnologia, Curso de Engenharia de Telecomunicações, RS, 2023.
id UFSM_1823ac361dbf5abea7dda6116a0edea5
oai_identifier_str oai:repositorio.ufsm.br:1/27722
network_acronym_str UFSM
network_name_str Manancial - Repositório Digital da UFSM
repository_id_str
spelling Deep learning-based oriented object detection in remote sensing imagery: YOLOv7-OBBDeep learning-based oriented object detection in remote sensing imagery: YOLOv7-OBBMachine learningDeep learningRemote sensing imageryObject detectionOriented bounding-boxYOLOv7DOTA datasetCNPQ::ENGENHARIAS::ENGENHARIA ELETRICA::TELECOMUNICACOESTrabalho de conclusão de curso (graduação) - Universidade Federal de Santa Maria, Centro de Tecnologia, Curso de Engenharia de Telecomunicações, RS, 2023.Remote sensing (RS) is the act of processing and extracting meaningful features about the ground and objects observed at a distance, usually from a much higher position from aircraft and satellites. Due to the large field of coverage in RS imagery, object detection in these images can be really useful, gathering a broad and concise notion of the objects present in certain areas. Due to their great capability of assimilating intricate patterns, Deep Learning (DL) models have achieved state-of-the-art (SOTA) performance in computer vision tasks. In this project, an extensive research is conducted on current DL-based object detection models and a suitable model, YOLOv7, is chosen to serve as a baseline for modifications to enable a high performance oriented bounding-box (OBB) detector in RS imagery. In supervised DL models, their final performance is very dependent on the quality of their training. To improve it, large datasets covering the specific task are pursued, converging to the use of DOTA dataset. Moreover, the concept of transfer learning is employed to allow the use of a pre-trained model on a very large dataset with different tasks. The final model is evaluated on common object detection metrics, such as the confusion matrix, precision, and recall curves. They validate the detector, capable of identifying 16 object classes with SOTA performance: high accuracy, fast and with the latest oriented bounding-box. Comparing the confusion matrices of the developed model and YOLOv5-OBB (KAIXUAN, 2022), for instance, it correctly identifies with a probability of 0.97, 0.89, 0.67 and 0.67% the following classes: plane, baseball diamond, bridge and ground track field. Meanwhile the YOLOv5-OBB obtains 0.96, 0.83, 0.6 and 0.6% for the same respective classes. Another interesting point is the reduction from 0.73 to 0.69% in the probability of mistaking the background for a small-vehicle. The model can further be trained on custom datasets for detection in agriculture, livestock, militarily, etc., bringing implications for many areas and activities. The repository containing all the codes used and developed in this project is available at (SANTOS, 2022).Remote sensing (RS) is the act of processing and extracting meaningful features about the ground and objects observed at a distance, usually from a much higher position from aircraft and satellites. Due to the large field of coverage in RS imagery, object detection in these images can be really useful, gathering a broad and concise notion of the objects present in certain areas. Due to their great capability of assimilating intricate patterns, Deep Learning (DL) models have achieved state-of-the-art (SOTA) performance in computer vision tasks. In this project, an extensive research is conducted on current DL-based object detection models and a suitable model, YOLOv7, is chosen to serve as a baseline for modifications to enable a high performance oriented bounding-box (OBB) detector in RS imagery. In supervised DL models, their final performance is very dependent on the quality of their training. To improve it, large datasets covering the specific task are pursued, converging to the use of DOTA dataset. Moreover, the concept of transfer learning is employed to allow the use of a pre-trained model on a very large dataset with different tasks. The final model is evaluated on common object detection metrics, such as the confusion matrix, precision, and recall curves. They validate the detector, capable of identifying 16 object classes with SOTA performance: high accuracy, fast and with the latest oriented bounding-box. Comparing the confusion matrices of the developed model and YOLOv5-OBB (KAIXUAN, 2022), for instance, it correctly identifies with a probability of 0.97, 0.89, 0.67 and 0.67% the following classes: plane, baseball diamond, bridge and ground track field. Meanwhile the YOLOv5-OBB obtains 0.96, 0.83, 0.6 and 0.6% for the same respective classes. Another interesting point is the reduction from 0.73 to 0.69% in the probability of mistaking the background for a small-vehicle. The model can further be trained on custom datasets for detection in agriculture, livestock, militarily, etc., bringing implications for many areas and activities. The repository containing all the codes used and developed in this project is available at (SANTOS, 2022).Universidade Federal de Santa MariaBrasilUFSMCentro de TecnologiaGomes, Natanael RodriguesSantos, Pietro Terra Pizzutti dos2023-02-03T16:00:40Z2023-02-03T16:00:40Z2023-01-252023Trabalho de Conclusão de Curso de Graduaçãoinfo:eu-repo/semantics/publishedVersionapplication/pdfSANTOS, P. T. P. dos. Deep Learning-Based Oriented Object Detection in Remote Sensing Imagery: YOLOv7-OBB. 2023. 86 p. Trabalho de Conclusão de Curso (Graduação em Engenharia de Telecomunicações) - Universidade Federal de Santa Maria, Santa Maria, RS, 2023.http://repositorio.ufsm.br/handle/1/27722ark:/26339/001300000w0x6engAttribution-NonCommercial-NoDerivatives 4.0 Internationalhttp://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccessreponame:Manancial - Repositório Digital da UFSMinstname:Universidade Federal de Santa Maria (UFSM)instacron:UFSM2023-02-03T16:00:40Zoai:repositorio.ufsm.br:1/27722Biblioteca Digital de Teses e Dissertaçõeshttps://repositorio.ufsm.br/PUBhttps://repositorio.ufsm.br/oai/requestatendimento.sib@ufsm.br||tedebc@gmail.com||manancial@ufsm.bropendoar:2023-02-03T16:00:40Manancial - Repositório Digital da UFSM - Universidade Federal de Santa Maria (UFSM)false
dc.title.none.fl_str_mv Deep learning-based oriented object detection in remote sensing imagery: YOLOv7-OBB
Deep learning-based oriented object detection in remote sensing imagery: YOLOv7-OBB
title Deep learning-based oriented object detection in remote sensing imagery: YOLOv7-OBB
spellingShingle Deep learning-based oriented object detection in remote sensing imagery: YOLOv7-OBB
Santos, Pietro Terra Pizzutti dos
Machine learning
Deep learning
Remote sensing imagery
Object detection
Oriented bounding-box
YOLOv7
DOTA dataset
CNPQ::ENGENHARIAS::ENGENHARIA ELETRICA::TELECOMUNICACOES
title_short Deep learning-based oriented object detection in remote sensing imagery: YOLOv7-OBB
title_full Deep learning-based oriented object detection in remote sensing imagery: YOLOv7-OBB
title_fullStr Deep learning-based oriented object detection in remote sensing imagery: YOLOv7-OBB
title_full_unstemmed Deep learning-based oriented object detection in remote sensing imagery: YOLOv7-OBB
title_sort Deep learning-based oriented object detection in remote sensing imagery: YOLOv7-OBB
author Santos, Pietro Terra Pizzutti dos
author_facet Santos, Pietro Terra Pizzutti dos
author_role author
dc.contributor.none.fl_str_mv Gomes, Natanael Rodrigues
dc.contributor.author.fl_str_mv Santos, Pietro Terra Pizzutti dos
dc.subject.por.fl_str_mv Machine learning
Deep learning
Remote sensing imagery
Object detection
Oriented bounding-box
YOLOv7
DOTA dataset
CNPQ::ENGENHARIAS::ENGENHARIA ELETRICA::TELECOMUNICACOES
topic Machine learning
Deep learning
Remote sensing imagery
Object detection
Oriented bounding-box
YOLOv7
DOTA dataset
CNPQ::ENGENHARIAS::ENGENHARIA ELETRICA::TELECOMUNICACOES
description Trabalho de conclusão de curso (graduação) - Universidade Federal de Santa Maria, Centro de Tecnologia, Curso de Engenharia de Telecomunicações, RS, 2023.
publishDate 2023
dc.date.none.fl_str_mv 2023-02-03T16:00:40Z
2023-02-03T16:00:40Z
2023-01-25
2023
dc.type.driver.fl_str_mv Trabalho de Conclusão de Curso de Graduação
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
status_str publishedVersion
dc.identifier.uri.fl_str_mv SANTOS, P. T. P. dos. Deep Learning-Based Oriented Object Detection in Remote Sensing Imagery: YOLOv7-OBB. 2023. 86 p. Trabalho de Conclusão de Curso (Graduação em Engenharia de Telecomunicações) - Universidade Federal de Santa Maria, Santa Maria, RS, 2023.
http://repositorio.ufsm.br/handle/1/27722
dc.identifier.dark.fl_str_mv ark:/26339/001300000w0x6
identifier_str_mv SANTOS, P. T. P. dos. Deep Learning-Based Oriented Object Detection in Remote Sensing Imagery: YOLOv7-OBB. 2023. 86 p. Trabalho de Conclusão de Curso (Graduação em Engenharia de Telecomunicações) - Universidade Federal de Santa Maria, Santa Maria, RS, 2023.
ark:/26339/001300000w0x6
url http://repositorio.ufsm.br/handle/1/27722
dc.language.iso.fl_str_mv eng
language eng
dc.rights.driver.fl_str_mv Attribution-NonCommercial-NoDerivatives 4.0 International
http://creativecommons.org/licenses/by-nc-nd/4.0/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv Attribution-NonCommercial-NoDerivatives 4.0 International
http://creativecommons.org/licenses/by-nc-nd/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Universidade Federal de Santa Maria
Brasil
UFSM
Centro de Tecnologia
publisher.none.fl_str_mv Universidade Federal de Santa Maria
Brasil
UFSM
Centro de Tecnologia
dc.source.none.fl_str_mv reponame:Manancial - Repositório Digital da UFSM
instname:Universidade Federal de Santa Maria (UFSM)
instacron:UFSM
instname_str Universidade Federal de Santa Maria (UFSM)
instacron_str UFSM
institution UFSM
reponame_str Manancial - Repositório Digital da UFSM
collection Manancial - Repositório Digital da UFSM
repository.name.fl_str_mv Manancial - Repositório Digital da UFSM - Universidade Federal de Santa Maria (UFSM)
repository.mail.fl_str_mv atendimento.sib@ufsm.br||tedebc@gmail.com||manancial@ufsm.br
_version_ 1847103586577678336

Similar Items