Transfer Learning-Based Accurate Detection of Shrub Crown Boundaries Using UAS Imagery

The accurate delineation of shrub crown boundaries is critical for ecological monitoring, land management, and understanding vegetation dynamics in fragile ecosystems such as semi-arid shrublands. While traditional image processing techniques often struggle with overlapping canopies, deep learning m...

Full description

Saved in:
Bibliographic Details
Main Authors: Jiawei Li, Huihui Zhang, David Barnard
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/13/2275
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849319944890613760
author Jiawei Li
Huihui Zhang
David Barnard
author_facet Jiawei Li
Huihui Zhang
David Barnard
author_sort Jiawei Li
collection DOAJ
description The accurate delineation of shrub crown boundaries is critical for ecological monitoring, land management, and understanding vegetation dynamics in fragile ecosystems such as semi-arid shrublands. While traditional image processing techniques often struggle with overlapping canopies, deep learning methods, such as convolutional neural networks (CNNs), offer promising solutions for precise segmentation. This study employed high-resolution imagery captured by unmanned aircraft systems (UASs) throughout the shrub growing season and explored the effectiveness of transfer learning for both semantic segmentation (Attention U-Net) and instance segmentation (Mask R-CNN). It utilized pre-trained model weights from two previous studies that originally focused on tree crown delineation to improve shrub crown segmentation in non-forested areas. Results showed that transfer learning alone did not achieve satisfactory performance due to differences in object characteristics and environmental conditions. However, fine-tuning the pre-trained models by unfreezing additional layers improved segmentation accuracy by around 30%. Fine-tuned pre-trained models show limited sensitivity to shrubs in the early growing season (April to June) and improved performance when shrub crowns become more spectrally unique in late summer (July to September). These findings highlight the value of combining pre-trained models with targeted fine-tuning to enhance model adaptability in complex remote sensing environments. The proposed framework demonstrates a scalable solution for ecological monitoring in data-scarce regions, supporting informed land management decisions and advancing the use of deep learning for long-term environmental monitoring.
format Article
id doaj-art-9f934876db0b4ecea8e980cba0fa92ab
institution Kabale University
issn 2072-4292
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-9f934876db0b4ecea8e980cba0fa92ab2025-08-20T03:50:16ZengMDPI AGRemote Sensing2072-42922025-07-011713227510.3390/rs17132275Transfer Learning-Based Accurate Detection of Shrub Crown Boundaries Using UAS ImageryJiawei Li0Huihui Zhang1David Barnard2Water Management and Systems Research Unit, United States Department of Agriculture, Agricultural Research Service, 2150 Centre Avenue, Building D, Fort Collins, CO 80526, USAWater Management and Systems Research Unit, United States Department of Agriculture, Agricultural Research Service, 2150 Centre Avenue, Building D, Fort Collins, CO 80526, USAWater Management and Systems Research Unit, United States Department of Agriculture, Agricultural Research Service, 2150 Centre Avenue, Building D, Fort Collins, CO 80526, USAThe accurate delineation of shrub crown boundaries is critical for ecological monitoring, land management, and understanding vegetation dynamics in fragile ecosystems such as semi-arid shrublands. While traditional image processing techniques often struggle with overlapping canopies, deep learning methods, such as convolutional neural networks (CNNs), offer promising solutions for precise segmentation. This study employed high-resolution imagery captured by unmanned aircraft systems (UASs) throughout the shrub growing season and explored the effectiveness of transfer learning for both semantic segmentation (Attention U-Net) and instance segmentation (Mask R-CNN). It utilized pre-trained model weights from two previous studies that originally focused on tree crown delineation to improve shrub crown segmentation in non-forested areas. Results showed that transfer learning alone did not achieve satisfactory performance due to differences in object characteristics and environmental conditions. However, fine-tuning the pre-trained models by unfreezing additional layers improved segmentation accuracy by around 30%. Fine-tuned pre-trained models show limited sensitivity to shrubs in the early growing season (April to June) and improved performance when shrub crowns become more spectrally unique in late summer (July to September). These findings highlight the value of combining pre-trained models with targeted fine-tuning to enhance model adaptability in complex remote sensing environments. The proposed framework demonstrates a scalable solution for ecological monitoring in data-scarce regions, supporting informed land management decisions and advancing the use of deep learning for long-term environmental monitoring.https://www.mdpi.com/2072-4292/17/13/2275deep learningshrub segmentationUASattention U-NetMask R-CNN
spellingShingle Jiawei Li
Huihui Zhang
David Barnard
Transfer Learning-Based Accurate Detection of Shrub Crown Boundaries Using UAS Imagery
Remote Sensing
deep learning
shrub segmentation
UAS
attention U-Net
Mask R-CNN
title Transfer Learning-Based Accurate Detection of Shrub Crown Boundaries Using UAS Imagery
title_full Transfer Learning-Based Accurate Detection of Shrub Crown Boundaries Using UAS Imagery
title_fullStr Transfer Learning-Based Accurate Detection of Shrub Crown Boundaries Using UAS Imagery
title_full_unstemmed Transfer Learning-Based Accurate Detection of Shrub Crown Boundaries Using UAS Imagery
title_short Transfer Learning-Based Accurate Detection of Shrub Crown Boundaries Using UAS Imagery
title_sort transfer learning based accurate detection of shrub crown boundaries using uas imagery
topic deep learning
shrub segmentation
UAS
attention U-Net
Mask R-CNN
url https://www.mdpi.com/2072-4292/17/13/2275
work_keys_str_mv AT jiaweili transferlearningbasedaccuratedetectionofshrubcrownboundariesusinguasimagery
AT huihuizhang transferlearningbasedaccuratedetectionofshrubcrownboundariesusinguasimagery
AT davidbarnard transferlearningbasedaccuratedetectionofshrubcrownboundariesusinguasimagery