Spatial Localization of Broadleaf Species in Mixed Forests in Northern Japan Using UAV Multi-Spectral Imagery and Mask R-CNN Model

Precise spatial localization of broadleaf species is crucial for efficient forest management and ecological studies. This study presents an advanced approach for segmenting and classifying broadleaf tree species, including Japanese oak (<i>Quercus crispula</i>), in mixed forests using mu...

Full description

Saved in:
Bibliographic Details
Main Authors: Nyo Me Htun, Toshiaki Owari, Satoshi N. Suzuki, Kenji Fukushi, Yuuta Ishizaki, Manato Fushimi, Yamato Unno, Ryota Konda, Satoshi Kita
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/13/2111
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849319805249650688
author Nyo Me Htun
Toshiaki Owari
Satoshi N. Suzuki
Kenji Fukushi
Yuuta Ishizaki
Manato Fushimi
Yamato Unno
Ryota Konda
Satoshi Kita
author_facet Nyo Me Htun
Toshiaki Owari
Satoshi N. Suzuki
Kenji Fukushi
Yuuta Ishizaki
Manato Fushimi
Yamato Unno
Ryota Konda
Satoshi Kita
author_sort Nyo Me Htun
collection DOAJ
description Precise spatial localization of broadleaf species is crucial for efficient forest management and ecological studies. This study presents an advanced approach for segmenting and classifying broadleaf tree species, including Japanese oak (<i>Quercus crispula</i>), in mixed forests using multi-spectral imagery captured by unmanned aerial vehicles (UAVs) and deep learning. High-resolution UAV images, including RGB and NIR bands, were collected from two study sites in Hokkaido, Japan: Sub-compartment 97g in the eastern region and Sub-compartment 68E in the central region. A Mask Region-based Convolutional Neural Network (Mask R-CNN) framework was employed to recognize and classify single tree crowns based on annotated training data. The workflow incorporated UAV-derived imagery and crown annotations, supporting reliable model development and evaluation. Results showed that combining multi-spectral bands (RGB and NIR) with canopy height model (CHM) data significantly improved classification performance at both study sites. In Sub-compartment 97g, the RGB + NIR + CHM achieved a precision of 0.76, recall of 0.74, and F1-score of 0.75, compared to 0.73, 0.74, and 0.73 using RGB alone; 0.68, 0.70, and 0.66 with RGB + NIR; and 0.63, 0.67, and 0.63 with RGB + CHM. Similarly, at Sub-compartment 68E, the RGB + NIR + CHM attained a precision of 0.81, recall of 0.78, and F1-score of 0.80, outperforming RGB alone (0.79, 0.79, 0.78), RGB + NIR (0.75, 0.74, 0.72), and RGB + CHM (0.76, 0.75, 0.74). These consistent improvements across diverse forest conditions highlight the effectiveness of integrating spectral (RGB and NIR) and structural (CHM) data. These findings underscore the value of integrating UAV multi-spectral imagery with deep learning techniques for reliable, large-scale identification of tree species and forest monitoring.
format Article
id doaj-art-d0972edf3d3a43539e28b78db2c189a8
institution Kabale University
issn 2072-4292
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-d0972edf3d3a43539e28b78db2c189a82025-08-20T03:50:20ZengMDPI AGRemote Sensing2072-42922025-06-011713211110.3390/rs17132111Spatial Localization of Broadleaf Species in Mixed Forests in Northern Japan Using UAV Multi-Spectral Imagery and Mask R-CNN ModelNyo Me Htun0Toshiaki Owari1Satoshi N. Suzuki2Kenji Fukushi3Yuuta Ishizaki4Manato Fushimi5Yamato Unno6Ryota Konda7Satoshi Kita8Forest GX/DX Co-Creation Center, The University of Tokyo Forests, Graduate School of Agricultural and Life Sciences, The University of Tokyo, Tokyo 113-8657, JapanThe University of Tokyo Hokkaido Forest, The University of Tokyo Forests, Graduate School of Agricultural and Life Sciences, The University of Tokyo, Furano 079-1563, Hokkaido, JapanNakagawa Experimental Forest, Field Science Center for Northern Biosphere, Hokkaido University, Otoineppu 098-2501, Hokkaido, JapanThe University of Tokyo Hokkaido Forest, The University of Tokyo Forests, Graduate School of Agricultural and Life Sciences, The University of Tokyo, Furano 079-1563, Hokkaido, JapanThe University of Tokyo Hokkaido Forest, The University of Tokyo Forests, Graduate School of Agricultural and Life Sciences, The University of Tokyo, Furano 079-1563, Hokkaido, JapanTsukuba Research Institute, Sumitomo Forestry Co., Ltd., Tsukuba 300-2646, Ibaraki, JapanTsukuba Research Institute, Sumitomo Forestry Co., Ltd., Tsukuba 300-2646, Ibaraki, JapanTsukuba Research Institute, Sumitomo Forestry Co., Ltd., Tsukuba 300-2646, Ibaraki, JapanForest and Landscape Research Center, Sumitomo Forestry Co., Ltd., Tokyo 100-8270, JapanPrecise spatial localization of broadleaf species is crucial for efficient forest management and ecological studies. This study presents an advanced approach for segmenting and classifying broadleaf tree species, including Japanese oak (<i>Quercus crispula</i>), in mixed forests using multi-spectral imagery captured by unmanned aerial vehicles (UAVs) and deep learning. High-resolution UAV images, including RGB and NIR bands, were collected from two study sites in Hokkaido, Japan: Sub-compartment 97g in the eastern region and Sub-compartment 68E in the central region. A Mask Region-based Convolutional Neural Network (Mask R-CNN) framework was employed to recognize and classify single tree crowns based on annotated training data. The workflow incorporated UAV-derived imagery and crown annotations, supporting reliable model development and evaluation. Results showed that combining multi-spectral bands (RGB and NIR) with canopy height model (CHM) data significantly improved classification performance at both study sites. In Sub-compartment 97g, the RGB + NIR + CHM achieved a precision of 0.76, recall of 0.74, and F1-score of 0.75, compared to 0.73, 0.74, and 0.73 using RGB alone; 0.68, 0.70, and 0.66 with RGB + NIR; and 0.63, 0.67, and 0.63 with RGB + CHM. Similarly, at Sub-compartment 68E, the RGB + NIR + CHM attained a precision of 0.81, recall of 0.78, and F1-score of 0.80, outperforming RGB alone (0.79, 0.79, 0.78), RGB + NIR (0.75, 0.74, 0.72), and RGB + CHM (0.76, 0.75, 0.74). These consistent improvements across diverse forest conditions highlight the effectiveness of integrating spectral (RGB and NIR) and structural (CHM) data. These findings underscore the value of integrating UAV multi-spectral imagery with deep learning techniques for reliable, large-scale identification of tree species and forest monitoring.https://www.mdpi.com/2072-4292/17/13/2111broadleaf speciesmixed forestUAV multi-spectral imageryMask R-CNN model
spellingShingle Nyo Me Htun
Toshiaki Owari
Satoshi N. Suzuki
Kenji Fukushi
Yuuta Ishizaki
Manato Fushimi
Yamato Unno
Ryota Konda
Satoshi Kita
Spatial Localization of Broadleaf Species in Mixed Forests in Northern Japan Using UAV Multi-Spectral Imagery and Mask R-CNN Model
Remote Sensing
broadleaf species
mixed forest
UAV multi-spectral imagery
Mask R-CNN model
title Spatial Localization of Broadleaf Species in Mixed Forests in Northern Japan Using UAV Multi-Spectral Imagery and Mask R-CNN Model
title_full Spatial Localization of Broadleaf Species in Mixed Forests in Northern Japan Using UAV Multi-Spectral Imagery and Mask R-CNN Model
title_fullStr Spatial Localization of Broadleaf Species in Mixed Forests in Northern Japan Using UAV Multi-Spectral Imagery and Mask R-CNN Model
title_full_unstemmed Spatial Localization of Broadleaf Species in Mixed Forests in Northern Japan Using UAV Multi-Spectral Imagery and Mask R-CNN Model
title_short Spatial Localization of Broadleaf Species in Mixed Forests in Northern Japan Using UAV Multi-Spectral Imagery and Mask R-CNN Model
title_sort spatial localization of broadleaf species in mixed forests in northern japan using uav multi spectral imagery and mask r cnn model
topic broadleaf species
mixed forest
UAV multi-spectral imagery
Mask R-CNN model
url https://www.mdpi.com/2072-4292/17/13/2111
work_keys_str_mv AT nyomehtun spatiallocalizationofbroadleafspeciesinmixedforestsinnorthernjapanusinguavmultispectralimageryandmaskrcnnmodel
AT toshiakiowari spatiallocalizationofbroadleafspeciesinmixedforestsinnorthernjapanusinguavmultispectralimageryandmaskrcnnmodel
AT satoshinsuzuki spatiallocalizationofbroadleafspeciesinmixedforestsinnorthernjapanusinguavmultispectralimageryandmaskrcnnmodel
AT kenjifukushi spatiallocalizationofbroadleafspeciesinmixedforestsinnorthernjapanusinguavmultispectralimageryandmaskrcnnmodel
AT yuutaishizaki spatiallocalizationofbroadleafspeciesinmixedforestsinnorthernjapanusinguavmultispectralimageryandmaskrcnnmodel
AT manatofushimi spatiallocalizationofbroadleafspeciesinmixedforestsinnorthernjapanusinguavmultispectralimageryandmaskrcnnmodel
AT yamatounno spatiallocalizationofbroadleafspeciesinmixedforestsinnorthernjapanusinguavmultispectralimageryandmaskrcnnmodel
AT ryotakonda spatiallocalizationofbroadleafspeciesinmixedforestsinnorthernjapanusinguavmultispectralimageryandmaskrcnnmodel
AT satoshikita spatiallocalizationofbroadleafspeciesinmixedforestsinnorthernjapanusinguavmultispectralimageryandmaskrcnnmodel