Urban Tree Canopy Mapping and Analysis Using Iterative Annotation Method and Deep Learning: A Case Study in Beijing

Urban trees have significant ecological and social functions, and generating urban tree canopy (UTC) maps is an effective method for understanding their distribution. However, existing studies primarily rely on medium-resolution to low-resolution imagery for large-scale extraction or high-resolution...

Full description

Saved in:
Bibliographic Details
Main Authors: Yulong Ding, Ximin Cui, Zhengchao Chen, Zeqing Wang, Debao Yuan, Xiang Meng, Xuan Yang, Yue Xu, Xiangyu Tian
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10969522/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849328621938802688
author Yulong Ding
Ximin Cui
Zhengchao Chen
Zeqing Wang
Debao Yuan
Xiang Meng
Xuan Yang
Yue Xu
Xiangyu Tian
author_facet Yulong Ding
Ximin Cui
Zhengchao Chen
Zeqing Wang
Debao Yuan
Xiang Meng
Xuan Yang
Yue Xu
Xiangyu Tian
author_sort Yulong Ding
collection DOAJ
description Urban trees have significant ecological and social functions, and generating urban tree canopy (UTC) maps is an effective method for understanding their distribution. However, existing studies primarily rely on medium-resolution to low-resolution imagery for large-scale extraction or high-resolution imagery for small-scale extraction, making it challenging to balance spatial coverage and accuracy. To comprehensively analyze the tree canopy characteristics of urban trees across large areas, this study selects Beijing as the research area, and employs high-resolution remote sensing imagery with deep learning techniques to construct the UTC map of Beijing. Deep learning models typically require large amounts of labeled data for training, but manually annotating pixel-level labels is time-consuming and costly. To address this, we propose an iterative method based on intersection over union (IoU), integrating multiscale segmentation and nearest-neighbor classification algorithms. By leveraging a limited number of labeled pixels, this approach efficiently generates a extensive labeled data, enabling the rapid construction of a high-precision dataset. Using this method, we established the Beijing Urban Tree Canopy Dataset (BUTCD). By employing BUTCD and InternImage_T+UPerNet as the tree canopy segmentation network, we generated the UTC map for Beijing. Accuracy assessments demonstrated an accuracy of 0.9806, precision of 0.9569, recall of 0.9702, mean IoU of 0.9296, and F1-score of 0.9635. We analyzed the results of Beijing's UTC, revealing that the tree canopy coverage rate is approximately 43.99&#x0025;, with higher coverage in the northwest and lower coverage in the southeast. The per capita tree canopy area in Beijing was calculated as 330.29 m<inline-formula><tex-math notation="LaTeX">$^{2}$</tex-math></inline-formula>. Within Beijing's central urban area, trees outside forests account for 26.54&#x0025; of the the total urban tree population, indicating that conventional statistics on tree-related data in this area tend to underestimate the true value by about one-fourth. This underestimation may originate from the substantial contributions of trees outside forest areas being neglected during the statistical process, especially in the central urbanized districts. We anticipate that the UTC map of Beijing will facilitate research on the city's ecosystem services, advance sustainable urban development, and improve the quality of life for residents.
format Article
id doaj-art-a6b87dbc5f0943239d940a5a8a7f6778
institution Kabale University
issn 1939-1404
2151-1535
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj-art-a6b87dbc5f0943239d940a5a8a7f67782025-08-20T03:47:33ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-0118126451265910.1109/JSTARS.2025.356224010969522Urban Tree Canopy Mapping and Analysis Using Iterative Annotation Method and Deep Learning: A Case Study in BeijingYulong Ding0https://orcid.org/0009-0003-0164-2494Ximin Cui1https://orcid.org/0000-0002-2736-9102Zhengchao Chen2https://orcid.org/0000-0003-4293-6459Zeqing Wang3https://orcid.org/0009-0001-0500-2596Debao Yuan4Xiang Meng5Xuan Yang6https://orcid.org/0000-0002-2938-7419Yue Xu7https://orcid.org/0000-0001-6683-2107Xiangyu Tian8College of Geoscience and Surveying Engineering, China University of Mining and Technology-Beijing, Beijing, ChinaCollege of Geoscience and Surveying Engineering, China University of Mining and Technology-Beijing, Beijing, ChinaKey Laboratory of Remote Sensing and Digital Earth, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaKey Laboratory of Remote Sensing and Digital Earth, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaCollege of Geoscience and Surveying Engineering, China University of Mining and Technology-Beijing, Beijing, ChinaChina Aerospace Academy of Systems Science and Engineering, Beijing, ChinaChina Remote Sensing Satellite Ground Station, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaKey Laboratory of Remote Sensing and Digital Earth, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaInstitute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing, ChinaUrban trees have significant ecological and social functions, and generating urban tree canopy (UTC) maps is an effective method for understanding their distribution. However, existing studies primarily rely on medium-resolution to low-resolution imagery for large-scale extraction or high-resolution imagery for small-scale extraction, making it challenging to balance spatial coverage and accuracy. To comprehensively analyze the tree canopy characteristics of urban trees across large areas, this study selects Beijing as the research area, and employs high-resolution remote sensing imagery with deep learning techniques to construct the UTC map of Beijing. Deep learning models typically require large amounts of labeled data for training, but manually annotating pixel-level labels is time-consuming and costly. To address this, we propose an iterative method based on intersection over union (IoU), integrating multiscale segmentation and nearest-neighbor classification algorithms. By leveraging a limited number of labeled pixels, this approach efficiently generates a extensive labeled data, enabling the rapid construction of a high-precision dataset. Using this method, we established the Beijing Urban Tree Canopy Dataset (BUTCD). By employing BUTCD and InternImage_T+UPerNet as the tree canopy segmentation network, we generated the UTC map for Beijing. Accuracy assessments demonstrated an accuracy of 0.9806, precision of 0.9569, recall of 0.9702, mean IoU of 0.9296, and F1-score of 0.9635. We analyzed the results of Beijing's UTC, revealing that the tree canopy coverage rate is approximately 43.99&#x0025;, with higher coverage in the northwest and lower coverage in the southeast. The per capita tree canopy area in Beijing was calculated as 330.29 m<inline-formula><tex-math notation="LaTeX">$^{2}$</tex-math></inline-formula>. Within Beijing's central urban area, trees outside forests account for 26.54&#x0025; of the the total urban tree population, indicating that conventional statistics on tree-related data in this area tend to underestimate the true value by about one-fourth. This underestimation may originate from the substantial contributions of trees outside forest areas being neglected during the statistical process, especially in the central urbanized districts. We anticipate that the UTC map of Beijing will facilitate research on the city's ecosystem services, advance sustainable urban development, and improve the quality of life for residents.https://ieeexplore.ieee.org/document/10969522/Dataset productiondeep learninghigh-resolution imagesremote sensingurban tree canopy (UTC)
spellingShingle Yulong Ding
Ximin Cui
Zhengchao Chen
Zeqing Wang
Debao Yuan
Xiang Meng
Xuan Yang
Yue Xu
Xiangyu Tian
Urban Tree Canopy Mapping and Analysis Using Iterative Annotation Method and Deep Learning: A Case Study in Beijing
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Dataset production
deep learning
high-resolution images
remote sensing
urban tree canopy (UTC)
title Urban Tree Canopy Mapping and Analysis Using Iterative Annotation Method and Deep Learning: A Case Study in Beijing
title_full Urban Tree Canopy Mapping and Analysis Using Iterative Annotation Method and Deep Learning: A Case Study in Beijing
title_fullStr Urban Tree Canopy Mapping and Analysis Using Iterative Annotation Method and Deep Learning: A Case Study in Beijing
title_full_unstemmed Urban Tree Canopy Mapping and Analysis Using Iterative Annotation Method and Deep Learning: A Case Study in Beijing
title_short Urban Tree Canopy Mapping and Analysis Using Iterative Annotation Method and Deep Learning: A Case Study in Beijing
title_sort urban tree canopy mapping and analysis using iterative annotation method and deep learning a case study in beijing
topic Dataset production
deep learning
high-resolution images
remote sensing
urban tree canopy (UTC)
url https://ieeexplore.ieee.org/document/10969522/
work_keys_str_mv AT yulongding urbantreecanopymappingandanalysisusingiterativeannotationmethodanddeeplearningacasestudyinbeijing
AT ximincui urbantreecanopymappingandanalysisusingiterativeannotationmethodanddeeplearningacasestudyinbeijing
AT zhengchaochen urbantreecanopymappingandanalysisusingiterativeannotationmethodanddeeplearningacasestudyinbeijing
AT zeqingwang urbantreecanopymappingandanalysisusingiterativeannotationmethodanddeeplearningacasestudyinbeijing
AT debaoyuan urbantreecanopymappingandanalysisusingiterativeannotationmethodanddeeplearningacasestudyinbeijing
AT xiangmeng urbantreecanopymappingandanalysisusingiterativeannotationmethodanddeeplearningacasestudyinbeijing
AT xuanyang urbantreecanopymappingandanalysisusingiterativeannotationmethodanddeeplearningacasestudyinbeijing
AT yuexu urbantreecanopymappingandanalysisusingiterativeannotationmethodanddeeplearningacasestudyinbeijing
AT xiangyutian urbantreecanopymappingandanalysisusingiterativeannotationmethodanddeeplearningacasestudyinbeijing