TY - JOUR
T1 - Urban Treetop Detection and Tree-Height Estimation from Unmanned-Aerial-Vehicle Images
AU - Wu, Hui
AU - Zhuang, Minghao
AU - Chen, Yuanchi
AU - Meng, Chen
AU - Wu, Caiyan
AU - Ouyang, Linke
AU - Liu, Yuhan
AU - Shu, Yi
AU - Tao, Yuzhong
AU - Qiu, Tong
AU - Li, Junxiang
N1 - Publisher Copyright:
© 2023 by the authors.
PY - 2023/8
Y1 - 2023/8
N2 - Individual tree detection for urban forests in subtropical environments remains a great challenge due to the various types of forest structures, high canopy closures, and the mixture of evergreen and deciduous broadleaved trees. Existing treetop detection methods based on the canopy-height model (CHM) from UAV images cannot resolve commission errors in heterogeneous urban forests with multiple trunks or strong lateral branches. In this study, we improved the traditional local-maximum (LM) algorithm using a dual Gaussian filter, variable window size, and local normalized correlation coefficient (NCC). Specifically, we adapted a crown model of maximum/minimum tree-crown radii and an angle strategy to detect treetops. We then removed and merged the pending tree vertices. Our results showed that our improved LM algorithm had an average user accuracy (UA) of 87.3% (SD± 4.6), an average producer accuracy (PA) of 82.8% (SD± 4.1), and an overall accuracy of 93.3% (SD± 3.9) for sample plots with canopy closures less than 0.5. As for the sample plots with canopy closures from 0.5 to 1, the accuracies were 78.6% (SD± 31.5), 73.8% (SD± 10.3), and 68.1% (SD± 12.7), respectively. The tree-height estimation accuracy reached more than 0.96, with an average RMSE of 0.61 m. Our results show that the UAV-image-derived CHM can be used to accurately detect individual trees in mixed forests in subtropical cities like Shanghai, China, to provide vital tree-structure parameters for precise and sustainable forest management.
AB - Individual tree detection for urban forests in subtropical environments remains a great challenge due to the various types of forest structures, high canopy closures, and the mixture of evergreen and deciduous broadleaved trees. Existing treetop detection methods based on the canopy-height model (CHM) from UAV images cannot resolve commission errors in heterogeneous urban forests with multiple trunks or strong lateral branches. In this study, we improved the traditional local-maximum (LM) algorithm using a dual Gaussian filter, variable window size, and local normalized correlation coefficient (NCC). Specifically, we adapted a crown model of maximum/minimum tree-crown radii and an angle strategy to detect treetops. We then removed and merged the pending tree vertices. Our results showed that our improved LM algorithm had an average user accuracy (UA) of 87.3% (SD± 4.6), an average producer accuracy (PA) of 82.8% (SD± 4.1), and an overall accuracy of 93.3% (SD± 3.9) for sample plots with canopy closures less than 0.5. As for the sample plots with canopy closures from 0.5 to 1, the accuracies were 78.6% (SD± 31.5), 73.8% (SD± 10.3), and 68.1% (SD± 12.7), respectively. The tree-height estimation accuracy reached more than 0.96, with an average RMSE of 0.61 m. Our results show that the UAV-image-derived CHM can be used to accurately detect individual trees in mixed forests in subtropical cities like Shanghai, China, to provide vital tree-structure parameters for precise and sustainable forest management.
UR - http://www.scopus.com/inward/record.url?scp=85167802957&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85167802957&partnerID=8YFLogxK
U2 - 10.3390/rs15153779
DO - 10.3390/rs15153779
M3 - Article
AN - SCOPUS:85167802957
SN - 2072-4292
VL - 15
JO - Remote Sensing
JF - Remote Sensing
IS - 15
M1 - 3779
ER -