Automated Bale Mapping Using Machine Learning and Photogrammetry

An automatic method of obtaining geographic coordinates of bales using monovision un-crewed aerial vehicle imagery was developed utilizing a data set of 300 images with a 20-megapixel resolution containing a total of 783 labeled bales of corn stover and soybean stubble. The relative performance of i...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	William Yamada, Wei Zhao, Matthew Digman
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	computer vision image processing machine learning photogrammetry Science Q
Acceso en línea:	https://doaj.org/article/25079bd64b26463a8e819fa61495f003
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:25079bd64b26463a8e819fa61495f003
record_format	dspace
spelling	oai:doaj.org-article:25079bd64b26463a8e819fa61495f0032021-11-25T18:55:18ZAutomated Bale Mapping Using Machine Learning and Photogrammetry10.3390/rs132246752072-4292https://doaj.org/article/25079bd64b26463a8e819fa61495f0032021-11-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/22/4675https://doaj.org/toc/2072-4292An automatic method of obtaining geographic coordinates of bales using monovision un-crewed aerial vehicle imagery was developed utilizing a data set of 300 images with a 20-megapixel resolution containing a total of 783 labeled bales of corn stover and soybean stubble. The relative performance of image processing with Otsu’s segmentation, you only look once version three (YOLOv3), and region-based convolutional neural networks was assessed. As a result, the best option in terms of accuracy and speed was determined to be YOLOv3, with 80% precision, 99% recall, 89% F1 score, 97% mean average precision, and a 0.38 s inference time. Next, the impact of using lower-cost cameras was evaluated by reducing image quality to one megapixel. The lower-resolution images resulted in decreased performance, with 79% precision, 97% recall, 88% F1 score, 96% mean average precision, and 0.40 s inference time. Finally, the output of the YOLOv3 trained model, density-based spatial clustering, photogrammetry, and map projection were utilized to predict the geocoordinates of the bales with a root mean squared error of 2.41 m.William YamadaWei ZhaoMatthew DigmanMDPI AGarticlecomputer visionimage processingmachine learningphotogrammetryScienceQENRemote Sensing, Vol 13, Iss 4675, p 4675 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	computer vision image processing machine learning photogrammetry Science Q
spellingShingle	computer vision image processing machine learning photogrammetry Science Q William Yamada Wei Zhao Matthew Digman Automated Bale Mapping Using Machine Learning and Photogrammetry
description	An automatic method of obtaining geographic coordinates of bales using monovision un-crewed aerial vehicle imagery was developed utilizing a data set of 300 images with a 20-megapixel resolution containing a total of 783 labeled bales of corn stover and soybean stubble. The relative performance of image processing with Otsu’s segmentation, you only look once version three (YOLOv3), and region-based convolutional neural networks was assessed. As a result, the best option in terms of accuracy and speed was determined to be YOLOv3, with 80% precision, 99% recall, 89% F1 score, 97% mean average precision, and a 0.38 s inference time. Next, the impact of using lower-cost cameras was evaluated by reducing image quality to one megapixel. The lower-resolution images resulted in decreased performance, with 79% precision, 97% recall, 88% F1 score, 96% mean average precision, and 0.40 s inference time. Finally, the output of the YOLOv3 trained model, density-based spatial clustering, photogrammetry, and map projection were utilized to predict the geocoordinates of the bales with a root mean squared error of 2.41 m.
format	article
author	William Yamada Wei Zhao Matthew Digman
author_facet	William Yamada Wei Zhao Matthew Digman
author_sort	William Yamada
title	Automated Bale Mapping Using Machine Learning and Photogrammetry
title_short	Automated Bale Mapping Using Machine Learning and Photogrammetry
title_full	Automated Bale Mapping Using Machine Learning and Photogrammetry
title_fullStr	Automated Bale Mapping Using Machine Learning and Photogrammetry
title_full_unstemmed	Automated Bale Mapping Using Machine Learning and Photogrammetry
title_sort	automated bale mapping using machine learning and photogrammetry
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/25079bd64b26463a8e819fa61495f003
work_keys_str_mv	AT williamyamada automatedbalemappingusingmachinelearningandphotogrammetry AT weizhao automatedbalemappingusingmachinelearningandphotogrammetry AT matthewdigman automatedbalemappingusingmachinelearningandphotogrammetry
_version_	1718410511725363200

Automated Bale Mapping Using Machine Learning and Photogrammetry

Ejemplares similares