Cover Image

Automatic detection and counting of stacked eucalypt timber using the YOLOv8 model

The objective of this project was to automate the detection and counting process of stacked eucalypt (hybrid Eucalyptus urophylla x Eucalyptus grandis) timber in the forestry industry using the YOLOv8 model. The dataset consists of 230 diverse images of eucalypt roundwood, including images of roundw...

Full description

Saved in:
Bibliographic Details
Main Authors: Casas, Gianmarco Goycochea, Ismail, Zool Hilmi, Limeira, Mathaus Messias Coimbra, Lopes da Silva, Antonilmar Araújo, Leite, Helio Garcia
Format: Article
Language:English
Published: Multidisciplinary Digital Publishing Institute (MDPI) 2023
Subjects:
T Technology (General)
Online Access:http://eprints.utm.my/107162/1/ZoolHilmiIsmail2023_AutomaticDetectionandCountingofStackedEucalypt.pdf
http://eprints.utm.my/107162/
http://dx.doi.org/10.3390/f14122369
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utm.107162
record_format eprints
spelling my.utm.1071622024-08-27T08:22:04Z http://eprints.utm.my/107162/ Automatic detection and counting of stacked eucalypt timber using the YOLOv8 model Casas, Gianmarco Goycochea Ismail, Zool Hilmi Limeira, Mathaus Messias Coimbra Lopes da Silva, Antonilmar Araújo Leite, Helio Garcia T Technology (General) The objective of this project was to automate the detection and counting process of stacked eucalypt (hybrid Eucalyptus urophylla x Eucalyptus grandis) timber in the forestry industry using the YOLOv8 model. The dataset consists of 230 diverse images of eucalypt roundwood, including images of roundwood separated on a rail and stacked timber. The annotations were made using LabelImg, ensuring accurate delineation of target objects on the log surfaces. The YOLOv8 model is customized with a CSPDarknet53 backbone, C2f module, and SPPF layer for efficient computation. The model was trained using an AdamW optimizer and implemented using Ultralytics YOLOv8.0.137, Python-3.10.12, and torch-2.0.1 + cu118 with CUDA support on NVIDIA T1000 (4096MiB). For model evaluation, the precision, recall, and mean Average Precision at a 50% confidence threshold (mAP50) were calculated. The best results were achieved at epoch 261, with a precision of 0.814, recall of 0.812, and mAP50 of 0.844 on the training set and a precision of 0.778, recall of 0.798, and mAP50 of 0.839 on the validation set. The model’s generalization was tested on separate images, demonstrating robust detection and accurate counting. The model effectively identified roundwood that was widely spaced, scattered, and overlapping. However, when applied to stacked timber, the automatic counting was not very accurate, especially when using images. In contrast, when using video, the relative percentage error for automatic counting significantly decreased to -12.442%. In conclusion, video proved to be more effective than images for counting stacked timber, while photographs should be reserved for the counting of individual roundwood pieces. Multidisciplinary Digital Publishing Institute (MDPI) 2023 Article PeerReviewed application/pdf en http://eprints.utm.my/107162/1/ZoolHilmiIsmail2023_AutomaticDetectionandCountingofStackedEucalypt.pdf Casas, Gianmarco Goycochea and Ismail, Zool Hilmi and Limeira, Mathaus Messias Coimbra and Lopes da Silva, Antonilmar Araújo and Leite, Helio Garcia (2023) Automatic detection and counting of stacked eucalypt timber using the YOLOv8 model. Forests, 14 (12). pp. 1-13. ISSN 1999-4907 http://dx.doi.org/10.3390/f14122369 DOI : 10.3390/f14122369
institution Universiti Teknologi Malaysia
building UTM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Malaysia
content_source UTM Institutional Repository
url_provider http://eprints.utm.my/
language English
topic T Technology (General)
spellingShingle T Technology (General)
Casas, Gianmarco Goycochea
Ismail, Zool Hilmi
Limeira, Mathaus Messias Coimbra
Lopes da Silva, Antonilmar Araújo
Leite, Helio Garcia
Automatic detection and counting of stacked eucalypt timber using the YOLOv8 model
description The objective of this project was to automate the detection and counting process of stacked eucalypt (hybrid Eucalyptus urophylla x Eucalyptus grandis) timber in the forestry industry using the YOLOv8 model. The dataset consists of 230 diverse images of eucalypt roundwood, including images of roundwood separated on a rail and stacked timber. The annotations were made using LabelImg, ensuring accurate delineation of target objects on the log surfaces. The YOLOv8 model is customized with a CSPDarknet53 backbone, C2f module, and SPPF layer for efficient computation. The model was trained using an AdamW optimizer and implemented using Ultralytics YOLOv8.0.137, Python-3.10.12, and torch-2.0.1 + cu118 with CUDA support on NVIDIA T1000 (4096MiB). For model evaluation, the precision, recall, and mean Average Precision at a 50% confidence threshold (mAP50) were calculated. The best results were achieved at epoch 261, with a precision of 0.814, recall of 0.812, and mAP50 of 0.844 on the training set and a precision of 0.778, recall of 0.798, and mAP50 of 0.839 on the validation set. The model’s generalization was tested on separate images, demonstrating robust detection and accurate counting. The model effectively identified roundwood that was widely spaced, scattered, and overlapping. However, when applied to stacked timber, the automatic counting was not very accurate, especially when using images. In contrast, when using video, the relative percentage error for automatic counting significantly decreased to -12.442%. In conclusion, video proved to be more effective than images for counting stacked timber, while photographs should be reserved for the counting of individual roundwood pieces.
format Article
author Casas, Gianmarco Goycochea
Ismail, Zool Hilmi
Limeira, Mathaus Messias Coimbra
Lopes da Silva, Antonilmar Araújo
Leite, Helio Garcia
author_facet Casas, Gianmarco Goycochea
Ismail, Zool Hilmi
Limeira, Mathaus Messias Coimbra
Lopes da Silva, Antonilmar Araújo
Leite, Helio Garcia
author_sort Casas, Gianmarco Goycochea
title Automatic detection and counting of stacked eucalypt timber using the YOLOv8 model
title_short Automatic detection and counting of stacked eucalypt timber using the YOLOv8 model
title_full Automatic detection and counting of stacked eucalypt timber using the YOLOv8 model
title_fullStr Automatic detection and counting of stacked eucalypt timber using the YOLOv8 model
title_full_unstemmed Automatic detection and counting of stacked eucalypt timber using the YOLOv8 model
title_sort automatic detection and counting of stacked eucalypt timber using the yolov8 model
publisher Multidisciplinary Digital Publishing Institute (MDPI)
publishDate 2023
url http://eprints.utm.my/107162/1/ZoolHilmiIsmail2023_AutomaticDetectionandCountingofStackedEucalypt.pdf
http://eprints.utm.my/107162/
http://dx.doi.org/10.3390/f14122369
_version_ 1809136635005108224
score 13.211869

Similar Items