Bamboo Forest Area Extraction and Clump Identification Using Semantic Segmentation and Instance Segmentation Models

This study addresses the need for effective bamboo monitoring in smart forestry as UAV imagery and AI-based methods continue to advance. Bambusa stenostachya (thorny bamboo), commonly found in the badland regions of southern Taiwan, spreads rapidly due to its strong reproductive capacity and extensive rhizome system, often causing forestland degradation and challenges to sustainable management. An automated detection approach is therefore required to capture bamboo dynamics and support forest resource assessment. We use a dual-component framework for detecting bamboo forests and individual bamboo clumps from high-resolution UAV orthomosaic imagery. The first component performs semantic segmentation using U-Net or SegFormer to extract bamboo forest areas and generate a corresponding forest mask. The second component independently applies instance segmentation using YOLOv8-Seg and Mask R-CNN to delineate and localize individual bamboo clumps. The dataset was collected from Compartment 43 of the Qishan Working Circle in Kaohsiung, Taiwan. Experimental results show strong model performance: bamboo forest segmentation achieved an F1-score of 0.9569, while bamboo clump instance segmentation reached a precision of 0.8232. These findings demonstrate the promising potential of deep learning-based segmentation techniques for improving bamboo detection and supporting operational forest monitoring.

• Publication year

  2026

• Venue

  Forests

• Publication date

  2026-02-01

• Fields of study

  Not labeled

• Identifiers
  DOI 10.3390/f17020191
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Efficient tree species classification using machine and deep learning algorithms based on UAV-LiDAR data in North China

  2025cited by this paper
• Applying a Four-Way Factorial Experimental Model to Diagnose Optimum kNN Parameters for Precise Aboveground Biomass Mapping

  2025cited by this paper
• Monitoring Forest Diversity under Moso Bamboo Invasion: A Random Forest Approach

  2024cited by this paper
• Rapid Forest Change Detection Using Unmanned Aerial Vehicles and Artificial Intelligence

  2024cited by this paper
• UAV-Based Intelligent Detection of Individual Trees in Moso Bamboo Forests With Complex Canopy Structure

  2024cited by this paper
• Improved YOLOv8-Seg Network for Instance Segmentation of Healthy and Diseased Tomato Plants in the Growth Stage

  2023cited by this paper
• Bamboo Mapping Using Earth Observation Data: A Systematic Review

  2022cited by this paper
• UNetFormer: A UNet-like transformer for efficient semantic segmentation of remote sensing urban scene imagery

  2021cited by this paper
• Explainable identification and mapping of trees using UAV RGB image and deep learning

  2021cited by this paper
• SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers

  2021cited by this paper
• Remote Sensing Estimation of Bamboo Forest Aboveground Biomass Based on Geographically Weighted Regression

  2021cited by this paper
• H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation From CT Volumes

  2018cited by this paper
• Individual tree detection from Unmanned Aerial Vehicle (UAV) derived canopy height model in an open canopy mixed conifer forest

  2017cited by this paper
• Road Extraction by Deep Residual U-Net

  2017cited by this paper
• A decompositional stand structure analysis for exploring stand dynamics of multiple attributes of a mixed-species forest

  2016cited by this paper
• SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation

  2015cited by this paper

• No citing papers are available for this paper.