Feature Fusion to Improve YOLOv8 for Segmenting and Classifying Aerial Images of Tree Crowns
Open Access
- 5 June 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 18 (19391404) , 14752-14765
Abstract
Instance segmentation techniques based on Convolutional Neural Networks (CNNs) is a vital tool for accurately identifying and segmenting individual tree crowns, which plays an essential role in environmental monitoring and forest management. In varied rural landscapes, canopy imagery often includes a mix of tiny, small, and medium tree objects scattered across diverse terrains, from standalone trees to densely clustered forest stands. This variability poses significant challenges to traditional instance segmentation methods. To achieve this, we introduce a new method named YOLOv8-FF, which incorporates a feature fusion (FF) technique based on the YOLOv8 architecture. We first design a network architecture based on YOLOv8 that is optimized for the characteristics of our dataset, enabling effective segmentation of densely distributed tiny and small tree crowns. Moreover, YOLOv8-FF incorporates a feature fusion mechanism that includes both cross-scale and same-scale fusion methods, enhancing the model's ability to integrate information across different layers and scales, thereby improving segmentation performance. We incorporate Sparse Large Kernel Network (SLaK), whose large convolution kernel can effectively extract key features, helping the model capture richer and deeper global information in the image. Experimental results on the tree crown dataset demonstrate that YOLOv8-FF outperforms several recent peer competitors, making it a promising tool for accurate and efficient tree crown instance segmentation.Keywords
Funding Information
- New Zealand Ministry of Business, Innovation and Employment (C09X1923)
This publication has 58 references indexed in Scilit:
- YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information2024
- Comparing physical and statistical landslide susceptibility models at the scale of individual treesGeomorphology, 2023
- A Systematic Review of Individual Tree Crown Detection and Delineation with Convolutional Neural Networks (CNN)Current Forestry Reports, 2023
- Counting trees in a subtropical mega city using the instance segmentation methodInternational Journal of Applied Earth Observation and Geoinformation, 2022
- Quantifying the influence of individual trees on slope stability at landscape scaleJournal of Environmental Management, 2021
- SOLO: Segmenting Objects by Locations2020
- Conditional Convolutions for Instance Segmentation2020
- End-to-End Object Detection with Transformers2020
- Microsoft COCO: Common Objects in Context2014
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009