Tree Species Classifications of Urban Forests Using UAV-LiDAR Intensity Frequency Data
The accurate classification of tree species is essential for the sustainable management of forest resources and the effective monitoring of biodiversity. However, a literature review shows that most of the previous unmanned aerial vehicle (UAV) light detection and ranging (LiDAR)-based studies on fi...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/1/110 |
| _version_ | 1827624007450492928 |
|---|---|
| author | Yulin Gong Xuejian Li Huaqiang Du Guomo Zhou Fangjie Mao Lv Zhou Bo Zhang Jie Xuan Dien Zhu |
| author_facet | Yulin Gong Xuejian Li Huaqiang Du Guomo Zhou Fangjie Mao Lv Zhou Bo Zhang Jie Xuan Dien Zhu |
| author_sort | Yulin Gong |
| collection | DOAJ |
| description | The accurate classification of tree species is essential for the sustainable management of forest resources and the effective monitoring of biodiversity. However, a literature review shows that most of the previous unmanned aerial vehicle (UAV) light detection and ranging (LiDAR)-based studies on fine tree species classification have used only limited intensity features, accurately identifying relatively few tree species. To address this gap, this study proposes developing a new intensity feature—intensity frequency—for the LiDAR-based fine classification of eight tree species. Intensity frequency is defined as the number of times a certain intensity value appears in the individual tree crown (ITC) point cloud. In this study, we use UAV laser scanning to obtain LiDAR data from urban forests. Intensity frequency features are constructed based on the extracted intensity information, and a random forest (RF) model is used to classify eight subtropical forest tree species in southeast China. Based on four-point cloud density sampling schemes of 100%, 80%, 50% and 30%, densities of 230 points/m<sup>2</sup>, 184 points/m<sup>2</sup>, 115 points/m<sup>2</sup> and 69 points/m<sup>2</sup> are obtained. These are used to analyze the effect of intensity frequency on tree species classification accuracy under four different point cloud densities. The results are shown as follows. (1) Intensity frequencies of trees are not significantly different for intraspecies (<i>p</i> > 0.05) values and are significantly different for interspecies (<i>p</i> < 0.01) values. (2) The intensity frequency features of LiDAR can be used to classify different tree species with an overall accuracy (OA) of 86.7%. <i>Acer Buergerianum</i> achieves a user accuracy (UA) of over 95% and a producer accuracy (PA) of over 90% for four density conditions. (3) The OA varies slightly under different point cloud densities, but the sum of correct classification trees (SCI) and PA decreases rapidly as the point cloud density decreases, while UA is less affected by density with some stability. (4) The priori feature selected by mean rank (MR) covers the top 10 posterior features selected by RF. These results show that the new intensity frequency feature proposed in this study can be used as a comprehensive and effective intensity feature for the fine classification of tree species. |
| first_indexed | 2024-03-09T11:59:44Z |
| format | Article |
| id | doaj.art-9272f10f19814866aaa057d5960a2d6f |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T11:59:44Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-9272f10f19814866aaa057d5960a2d6f2023-11-30T23:05:38ZengMDPI AGRemote Sensing2072-42922022-12-0115111010.3390/rs15010110Tree Species Classifications of Urban Forests Using UAV-LiDAR Intensity Frequency DataYulin Gong0Xuejian Li1Huaqiang Du2Guomo Zhou3Fangjie Mao4Lv Zhou5Bo Zhang6Jie Xuan7Dien Zhu8State Key Laboratory of Subtropical Silviculture, Zhejiang A & F University, Hangzhou 311300, ChinaState Key Laboratory of Subtropical Silviculture, Zhejiang A & F University, Hangzhou 311300, ChinaState Key Laboratory of Subtropical Silviculture, Zhejiang A & F University, Hangzhou 311300, ChinaState Key Laboratory of Subtropical Silviculture, Zhejiang A & F University, Hangzhou 311300, ChinaState Key Laboratory of Subtropical Silviculture, Zhejiang A & F University, Hangzhou 311300, ChinaState Key Laboratory of Subtropical Silviculture, Zhejiang A & F University, Hangzhou 311300, ChinaState Key Laboratory of Subtropical Silviculture, Zhejiang A & F University, Hangzhou 311300, ChinaState Key Laboratory of Subtropical Silviculture, Zhejiang A & F University, Hangzhou 311300, ChinaState Key Laboratory of Subtropical Silviculture, Zhejiang A & F University, Hangzhou 311300, ChinaThe accurate classification of tree species is essential for the sustainable management of forest resources and the effective monitoring of biodiversity. However, a literature review shows that most of the previous unmanned aerial vehicle (UAV) light detection and ranging (LiDAR)-based studies on fine tree species classification have used only limited intensity features, accurately identifying relatively few tree species. To address this gap, this study proposes developing a new intensity feature—intensity frequency—for the LiDAR-based fine classification of eight tree species. Intensity frequency is defined as the number of times a certain intensity value appears in the individual tree crown (ITC) point cloud. In this study, we use UAV laser scanning to obtain LiDAR data from urban forests. Intensity frequency features are constructed based on the extracted intensity information, and a random forest (RF) model is used to classify eight subtropical forest tree species in southeast China. Based on four-point cloud density sampling schemes of 100%, 80%, 50% and 30%, densities of 230 points/m<sup>2</sup>, 184 points/m<sup>2</sup>, 115 points/m<sup>2</sup> and 69 points/m<sup>2</sup> are obtained. These are used to analyze the effect of intensity frequency on tree species classification accuracy under four different point cloud densities. The results are shown as follows. (1) Intensity frequencies of trees are not significantly different for intraspecies (<i>p</i> > 0.05) values and are significantly different for interspecies (<i>p</i> < 0.01) values. (2) The intensity frequency features of LiDAR can be used to classify different tree species with an overall accuracy (OA) of 86.7%. <i>Acer Buergerianum</i> achieves a user accuracy (UA) of over 95% and a producer accuracy (PA) of over 90% for four density conditions. (3) The OA varies slightly under different point cloud densities, but the sum of correct classification trees (SCI) and PA decreases rapidly as the point cloud density decreases, while UA is less affected by density with some stability. (4) The priori feature selected by mean rank (MR) covers the top 10 posterior features selected by RF. These results show that the new intensity frequency feature proposed in this study can be used as a comprehensive and effective intensity feature for the fine classification of tree species.https://www.mdpi.com/2072-4292/15/1/110tree species classificationsunmanned aerial vehicle (UAV)LiDARpoint cloudintensity frequency |
| spellingShingle | Yulin Gong Xuejian Li Huaqiang Du Guomo Zhou Fangjie Mao Lv Zhou Bo Zhang Jie Xuan Dien Zhu Tree Species Classifications of Urban Forests Using UAV-LiDAR Intensity Frequency Data Remote Sensing tree species classifications unmanned aerial vehicle (UAV) LiDAR point cloud intensity frequency |
| title | Tree Species Classifications of Urban Forests Using UAV-LiDAR Intensity Frequency Data |
| title_full | Tree Species Classifications of Urban Forests Using UAV-LiDAR Intensity Frequency Data |
| title_fullStr | Tree Species Classifications of Urban Forests Using UAV-LiDAR Intensity Frequency Data |
| title_full_unstemmed | Tree Species Classifications of Urban Forests Using UAV-LiDAR Intensity Frequency Data |
| title_short | Tree Species Classifications of Urban Forests Using UAV-LiDAR Intensity Frequency Data |
| title_sort | tree species classifications of urban forests using uav lidar intensity frequency data |
| topic | tree species classifications unmanned aerial vehicle (UAV) LiDAR point cloud intensity frequency |
| url | https://www.mdpi.com/2072-4292/15/1/110 |
| work_keys_str_mv | AT yulingong treespeciesclassificationsofurbanforestsusinguavlidarintensityfrequencydata AT xuejianli treespeciesclassificationsofurbanforestsusinguavlidarintensityfrequencydata AT huaqiangdu treespeciesclassificationsofurbanforestsusinguavlidarintensityfrequencydata AT guomozhou treespeciesclassificationsofurbanforestsusinguavlidarintensityfrequencydata AT fangjiemao treespeciesclassificationsofurbanforestsusinguavlidarintensityfrequencydata AT lvzhou treespeciesclassificationsofurbanforestsusinguavlidarintensityfrequencydata AT bozhang treespeciesclassificationsofurbanforestsusinguavlidarintensityfrequencydata AT jiexuan treespeciesclassificationsofurbanforestsusinguavlidarintensityfrequencydata AT dienzhu treespeciesclassificationsofurbanforestsusinguavlidarintensityfrequencydata |