Study on Individual Tree Segmentation of Different Tree Species Using Different Segmentation Algorithms Based on 3D UAV Data
Individual structural parameters of trees, such as forest stand tree height and biomass, serve as the foundation for monitoring of dynamic changes in forest resources. Individual tree structural parameters are closely related to individual tree crown segmentation. Although three-dimensional (3D) dat...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-06-01
|
| Series: | Forests |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4907/14/7/1327 |
| _version_ | 1797589275153268736 |
|---|---|
| author | Yao Liu Haotian You Xu Tang Qixu You Yuanwei Huang Jianjun Chen |
| author_facet | Yao Liu Haotian You Xu Tang Qixu You Yuanwei Huang Jianjun Chen |
| author_sort | Yao Liu |
| collection | DOAJ |
| description | Individual structural parameters of trees, such as forest stand tree height and biomass, serve as the foundation for monitoring of dynamic changes in forest resources. Individual tree structural parameters are closely related to individual tree crown segmentation. Although three-dimensional (3D) data have been successfully used to determine individual tree crown segmentation, this phenomenon is influenced by various factors, such as the (i) source of 3D data, (ii) the segmentation algorithm, and (iii) the tree species. To further quantify the effect of various factors on individual tree crown segmentation, light detection and ranging (LiDAR) data and image-derived points were obtained by unmanned aerial vehicles (UAVs). Three different segmentation algorithms (PointNet++, Li2012, and layer-stacking segmentation (LSS)) were used to segment individual tree crowns for four different tree species. The results show that for two 3D data, the crown segmentation accuracy of LiDAR data was generally better than that obtained using image-derived 3D data, with a maximum difference of 0.13 in F values. For the three segmentation algorithms, the individual tree crown segmentation accuracy of the PointNet++ algorithm was the best, with an F value of 0.91, whereas the result of the LSS algorithm yields the worst result, with an F value of 0.86. Among the four tested tree species, the individual tree crown segmentation of <i>Liriodendron chinense</i> was the best, followed by <i>Magnolia grandiflora</i> and <i>Osmanthus fragrans</i>, whereas the individual tree crown segmentation of <i>Ficus microcarpa</i> was the worst. Similar crown segmentation of individual <i>Liriodendron chinense</i> and <i>Magnolia grandiflora</i> trees was observed based on LiDAR data and image-derived 3D data. The crown segmentation of individual <i>Osmanthus fragrans</i> and <i>Ficus microcarpa</i> trees was superior according to LiDAR data to that determined according to image-derived 3D data. These results demonstrate that the source of 3D data, the segmentation algorithm, and the tree species all have an impact on the crown segmentation of individual trees. The effect of the tree species is the greatest, followed by the segmentation algorithm, and the effect of the 3D data source. Consequently, in future research on individual tree crown segmentation, 3D data acquisition methods should be selected based on the tree species, and deep learning segmentation algorithms should be adopted to improve the crown segmentation of individual trees. |
| first_indexed | 2024-03-11T01:05:13Z |
| format | Article |
| id | doaj.art-f5f0dae60a834395adaf4f69eb589e83 |
| institution | Directory Open Access Journal |
| issn | 1999-4907 |
| language | English |
| last_indexed | 2024-03-11T01:05:13Z |
| publishDate | 2023-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Forests |
| spelling | doaj.art-f5f0dae60a834395adaf4f69eb589e832023-11-18T19:22:40ZengMDPI AGForests1999-49072023-06-01147132710.3390/f14071327Study on Individual Tree Segmentation of Different Tree Species Using Different Segmentation Algorithms Based on 3D UAV DataYao Liu0Haotian You1Xu Tang2Qixu You3Yuanwei Huang4Jianjun Chen5College of Geomatics and Geoinformation, Guilin University of Technology, No. 12 Jian’gan Road, Guilin 541006, ChinaCollege of Geomatics and Geoinformation, Guilin University of Technology, No. 12 Jian’gan Road, Guilin 541006, ChinaCollege of Geomatics and Geoinformation, Guilin University of Technology, No. 12 Jian’gan Road, Guilin 541006, ChinaCollege of Geomatics and Geoinformation, Guilin University of Technology, No. 12 Jian’gan Road, Guilin 541006, ChinaCollege of Geomatics and Geoinformation, Guilin University of Technology, No. 12 Jian’gan Road, Guilin 541006, ChinaCollege of Geomatics and Geoinformation, Guilin University of Technology, No. 12 Jian’gan Road, Guilin 541006, ChinaIndividual structural parameters of trees, such as forest stand tree height and biomass, serve as the foundation for monitoring of dynamic changes in forest resources. Individual tree structural parameters are closely related to individual tree crown segmentation. Although three-dimensional (3D) data have been successfully used to determine individual tree crown segmentation, this phenomenon is influenced by various factors, such as the (i) source of 3D data, (ii) the segmentation algorithm, and (iii) the tree species. To further quantify the effect of various factors on individual tree crown segmentation, light detection and ranging (LiDAR) data and image-derived points were obtained by unmanned aerial vehicles (UAVs). Three different segmentation algorithms (PointNet++, Li2012, and layer-stacking segmentation (LSS)) were used to segment individual tree crowns for four different tree species. The results show that for two 3D data, the crown segmentation accuracy of LiDAR data was generally better than that obtained using image-derived 3D data, with a maximum difference of 0.13 in F values. For the three segmentation algorithms, the individual tree crown segmentation accuracy of the PointNet++ algorithm was the best, with an F value of 0.91, whereas the result of the LSS algorithm yields the worst result, with an F value of 0.86. Among the four tested tree species, the individual tree crown segmentation of <i>Liriodendron chinense</i> was the best, followed by <i>Magnolia grandiflora</i> and <i>Osmanthus fragrans</i>, whereas the individual tree crown segmentation of <i>Ficus microcarpa</i> was the worst. Similar crown segmentation of individual <i>Liriodendron chinense</i> and <i>Magnolia grandiflora</i> trees was observed based on LiDAR data and image-derived 3D data. The crown segmentation of individual <i>Osmanthus fragrans</i> and <i>Ficus microcarpa</i> trees was superior according to LiDAR data to that determined according to image-derived 3D data. These results demonstrate that the source of 3D data, the segmentation algorithm, and the tree species all have an impact on the crown segmentation of individual trees. The effect of the tree species is the greatest, followed by the segmentation algorithm, and the effect of the 3D data source. Consequently, in future research on individual tree crown segmentation, 3D data acquisition methods should be selected based on the tree species, and deep learning segmentation algorithms should be adopted to improve the crown segmentation of individual trees.https://www.mdpi.com/1999-4907/14/7/1327image-derived pointsLiDAR datasegmentation algorithmsindividual treetree species |
| spellingShingle | Yao Liu Haotian You Xu Tang Qixu You Yuanwei Huang Jianjun Chen Study on Individual Tree Segmentation of Different Tree Species Using Different Segmentation Algorithms Based on 3D UAV Data Forests image-derived points LiDAR data segmentation algorithms individual tree tree species |
| title | Study on Individual Tree Segmentation of Different Tree Species Using Different Segmentation Algorithms Based on 3D UAV Data |
| title_full | Study on Individual Tree Segmentation of Different Tree Species Using Different Segmentation Algorithms Based on 3D UAV Data |
| title_fullStr | Study on Individual Tree Segmentation of Different Tree Species Using Different Segmentation Algorithms Based on 3D UAV Data |
| title_full_unstemmed | Study on Individual Tree Segmentation of Different Tree Species Using Different Segmentation Algorithms Based on 3D UAV Data |
| title_short | Study on Individual Tree Segmentation of Different Tree Species Using Different Segmentation Algorithms Based on 3D UAV Data |
| title_sort | study on individual tree segmentation of different tree species using different segmentation algorithms based on 3d uav data |
| topic | image-derived points LiDAR data segmentation algorithms individual tree tree species |
| url | https://www.mdpi.com/1999-4907/14/7/1327 |
| work_keys_str_mv | AT yaoliu studyonindividualtreesegmentationofdifferenttreespeciesusingdifferentsegmentationalgorithmsbasedon3duavdata AT haotianyou studyonindividualtreesegmentationofdifferenttreespeciesusingdifferentsegmentationalgorithmsbasedon3duavdata AT xutang studyonindividualtreesegmentationofdifferenttreespeciesusingdifferentsegmentationalgorithmsbasedon3duavdata AT qixuyou studyonindividualtreesegmentationofdifferenttreespeciesusingdifferentsegmentationalgorithmsbasedon3duavdata AT yuanweihuang studyonindividualtreesegmentationofdifferenttreespeciesusingdifferentsegmentationalgorithmsbasedon3duavdata AT jianjunchen studyonindividualtreesegmentationofdifferenttreespeciesusingdifferentsegmentationalgorithmsbasedon3duavdata |