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 (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.

• Publication year

  2025

• Venue

  IEEE Access

• Publication date

  Unknown publication date

• Fields of study

  Computer Science, Environmental Science

• Identifiers
  DOI 10.1109/ACCESS.2025.3575713
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• YOLOv5, YOLOv8 and YOLOv10: The Go-To Detectors for Real-time Vision

  2024influential reference
• Enhancing automated vehicle identification by integrating YOLO v8 and OCR techniques for high-precision license plate detection and recognition

  2024cited by this paper
• YOLOv1 to YOLOv10: A comprehensive review of YOLO variants and their application in the agricultural domain

  2024influential reference
• MMPOI: A Multi-Modal Content-Aware Framework for POI Recommendations

  2024cited by this paper
• On the Opportunities and Challenges of Foundation Models for GeoAI (Vision Paper)

  2024cited by this paper
• Faster Image Deblurring for Unmanned Aerial Vehicles

  2024cited by this paper
• Optimizing Convolutional Networks Using a Modified Metaheuristic for Apple Tree Leaf Disease Detection

  2024cited by this paper
• Exploring Power Line Arc Detection Using YOLOv8 Computer Vision Models

  2024cited by this paper
• FinnWoodlands Dataset

  2023influential reference
• BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models

  2023cited by this paper
• Tree mortality during long-term droughts is lower in structurally complex forest stands

  2023cited by this paper
• Wall segmentation in 2D images using convolutional neural networks

  2023cited by this paper
• A Novel Framework for QR Code Detection and Decoding from Obscure Images using YOLO Object Detection and Real-ESRGAN Image Enhancement Technique

  2023cited by this paper
• Carrot grading system using computer vision feature parameters and a cascaded graph convolutional neural network

  2022cited by this paper
• A Parallel Implementation of Computing Mean Average Precision

  2022cited by this paper
• Instance Segmentation for Autonomous Log Grasping in Forestry Operations

  2022cited by this paper
• Root-mean-square error (RMSE) or mean absolute error (MAE): when to use them or not

  2022cited by this paper
• Individual tree segmentation and tree species classification in subtropical broadleaf forests using UAV-based LiDAR, hyperspectral, and ultrahigh-resolution RGB data

  2022influential reference
• Accuracy and Efficiency Comparison of Object Detection Open-Source Models

  2021cited by this paper
• Single Tree Segmentation and Diameter at Breast Height Estimation With Mobile LiDAR

  2021cited by this paper
• Extending deep learning approaches for forest disturbance segmentation on very high‐resolution satellite images

  2021cited by this paper
• Individual Tree Crown Segmentation Directly from UAV-Borne LiDAR Data Using the PointNet of Deep Learning

  2021influential reference
• The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation

  2021cited by this paper
• Deep Learning in Forestry Using UAV-Acquired RGB Data: A Practical Review

  2021cited by this paper
• Individual tree detection and crown segmentation based on metabolic theory from airborne laser scanning data

  2021cited by this paper
• A self-adaptive mean shift tree-segmentation method Using UAV LiDAR data

  2020cited by this paper
• CNN-Based Tree Species Classification Using High Resolution RGB Image Data from Automated UAV Observations

  2020cited by this paper
• Tree species classification using UAS-based digital aerial photogrammetry point clouds and multispectral imageries in subtropical natural forests

  2020cited by this paper
• Height variation hypothesis: A new approach for estimating forest species diversity with CHM LiDAR data

  2020cited by this paper
• Individual Tree Parameters Estimation for Plantation Forests Based on UAV Oblique Photography

  2020cited by this paper
• Detection, Segmentation, and Model Fitting of Individual Tree Stems from Airborne Laser Scanning of Forests Using Deep Learning

  2020influential reference
• 3D Segmentation of Trees Through a Flexible Multiclass Graph Cut Algorithm

  2019cited by this paper
• The Influence of Vegetation Characteristics on Individual Tree Segmentation Methods with Airborne LiDAR Data

  2019cited by this paper
• Classification of tree species and stock volume estimation in ground forest images using Deep Learning

  2019cited by this paper
• An Approach to Tree Detection Based on the Fusion of Multitemporal LiDAR Data

  2019cited by this paper
• Estimation of canopy cover in dense mixed-species forests using airborne lidar data

  2018cited by this paper
• Feature Pyramid Networks for Object Detection

  2016cited by this paper
• You Only Look Once: Unified, Real-Time Object Detection

  2015cited by this paper
• Exploiting machine learning algorithms for tree species classification in a semiarid woodland using RapidEye image

  2013cited by this paper
• Tree Detection in Urban Regions Using Aerial Lidar and Image Data

  2007cited by this paper
• The costs of reproduction in plants.

  2002cited by this paper

• SilvaScenes: Tree Segmentation and Species Classification from Under-Canopy Images in Natural Forests

  2025cites this paper