Enhancing Semantic Forestry Segmentation Through Advanced Preprocessing With ML Models

This study explores the application of advanced artificial intelligence based preprocessing techniques to improve semantic forestry segmentation. The research investigates the performance of You Only Look Once version 8 (YOLOv8) from Ultralytics, Detectron2 from Meta, and the Segment Anything Model...

Full description

Saved in:
Bibliographic Details
Main Authors: Krzysztof Wolk, Jacek Niklewski, Michal Kopczynski, Marek S. Tatara, Oleg Zero
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11020665/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849691467205836800
author Krzysztof Wolk
Jacek Niklewski
Michal Kopczynski
Marek S. Tatara
Oleg Zero
author_facet Krzysztof Wolk
Jacek Niklewski
Michal Kopczynski
Marek S. Tatara
Oleg Zero
author_sort Krzysztof Wolk
collection DOAJ
description This study explores the application of advanced artificial intelligence based preprocessing techniques to improve semantic forestry segmentation. The research investigates the performance of You Only Look Once version 8 (YOLOv8) from Ultralytics, Detectron2 from Meta, and the Segment Anything Model (SAM) from Meta, with the goal of enhancing segmentation accuracy and detail in forest environments. Goal is accomplished by combining models into a pipeline along with machine-larning-based preprocessing models. The integration of SAM and pre-processing steps significantly enhanced the quality and number of segmentation masks, resulting in more accurate and detailed representations of complex forest structures compared to the ground truth. The findings highlight the importance of combining AI models with effective preprocessing strategies to navigate the complexities of forest environments, offering valuable insights for future advancements in semantic forestry segmentation.
format Article
id doaj-art-4068fb28662a48fb8e00e5a1be7a583f
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-4068fb28662a48fb8e00e5a1be7a583f2025-08-20T03:21:00ZengIEEEIEEE Access2169-35362025-01-0113986029862110.1109/ACCESS.2025.357571311020665Enhancing Semantic Forestry Segmentation Through Advanced Preprocessing With ML ModelsKrzysztof Wolk0https://orcid.org/0000-0001-5030-334XJacek Niklewski1Michal Kopczynski2Marek S. Tatara3Oleg Zero4DAC.digital SA, Gdańsk, PolandDAC.digital SA, Gdańsk, PolandDAC.digital SA, Gdańsk, PolandDAC.digital SA, Gdańsk, PolandDAC.digital SA, Gdańsk, PolandThis study explores the application of advanced artificial intelligence based preprocessing techniques to improve semantic forestry segmentation. The research investigates the performance of You Only Look Once version 8 (YOLOv8) from Ultralytics, Detectron2 from Meta, and the Segment Anything Model (SAM) from Meta, with the goal of enhancing segmentation accuracy and detail in forest environments. Goal is accomplished by combining models into a pipeline along with machine-larning-based preprocessing models. The integration of SAM and pre-processing steps significantly enhanced the quality and number of segmentation masks, resulting in more accurate and detailed representations of complex forest structures compared to the ground truth. The findings highlight the importance of combining AI models with effective preprocessing strategies to navigate the complexities of forest environments, offering valuable insights for future advancements in semantic forestry segmentation.https://ieeexplore.ieee.org/document/11020665/Convolutional neural networksforestrymachine learningobject detectionpreprocessingsemantic segmentation
spellingShingle Krzysztof Wolk
Jacek Niklewski
Michal Kopczynski
Marek S. Tatara
Oleg Zero
Enhancing Semantic Forestry Segmentation Through Advanced Preprocessing With ML Models
IEEE Access
Convolutional neural networks
forestry
machine learning
object detection
preprocessing
semantic segmentation
title Enhancing Semantic Forestry Segmentation Through Advanced Preprocessing With ML Models
title_full Enhancing Semantic Forestry Segmentation Through Advanced Preprocessing With ML Models
title_fullStr Enhancing Semantic Forestry Segmentation Through Advanced Preprocessing With ML Models
title_full_unstemmed Enhancing Semantic Forestry Segmentation Through Advanced Preprocessing With ML Models
title_short Enhancing Semantic Forestry Segmentation Through Advanced Preprocessing With ML Models
title_sort enhancing semantic forestry segmentation through advanced preprocessing with ml models
topic Convolutional neural networks
forestry
machine learning
object detection
preprocessing
semantic segmentation
url https://ieeexplore.ieee.org/document/11020665/
work_keys_str_mv AT krzysztofwolk enhancingsemanticforestrysegmentationthroughadvancedpreprocessingwithmlmodels
AT jacekniklewski enhancingsemanticforestrysegmentationthroughadvancedpreprocessingwithmlmodels
AT michalkopczynski enhancingsemanticforestrysegmentationthroughadvancedpreprocessingwithmlmodels
AT marekstatara enhancingsemanticforestrysegmentationthroughadvancedpreprocessingwithmlmodels
AT olegzero enhancingsemanticforestrysegmentationthroughadvancedpreprocessingwithmlmodels