Study on Single-Tree Extraction Method for Complex RGB Point Cloud Scenes
With the development of sensor technology and point cloud generation techniques, there has been an increasing amount of high-quality forest RGB point cloud data. However, popular clustering-based point cloud segmentation methods are usually only suitable for pure forest scenes and not ideal for scen...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/10/2644 |
| _version_ | 1797598482548129792 |
|---|---|
| author | Kai Xia Cheng Li Yinhui Yang Susu Deng Hailin Feng |
| author_facet | Kai Xia Cheng Li Yinhui Yang Susu Deng Hailin Feng |
| author_sort | Kai Xia |
| collection | DOAJ |
| description | With the development of sensor technology and point cloud generation techniques, there has been an increasing amount of high-quality forest RGB point cloud data. However, popular clustering-based point cloud segmentation methods are usually only suitable for pure forest scenes and not ideal for scenes with multiple ground features or complex terrain. Therefore, this study proposes a single-tree point cloud extraction method that combines deep semantic segmentation and clustering. This method first uses a deep semantic segmentation network, Improved-RandLA-Net, which is developed based on RandLA-Net, to extract point clouds of specified tree species by adding an attention chain to improve the model’s ability to extract channel and spatial features. Subsequently, clustering is employed to extract single-tree point clouds from the segmented point clouds. The feasibility of the proposed method was verified in the Gingko site, the Lin’an Pecan site, and a Fraxinus excelsior site in a conference center. Finally, semantic segmentation was performed on three sample areas using pre- and postimproved RandLA-Net. The experiments demonstrate that Improved-RandLA-Net had significant improvements in Accuracy, Precision, Recall, and F1 score. At the same time, based on the semantic segmentation results of Improved-RandLA-Net, single-tree point clouds of three sample areas were extracted, and the final single-tree recognition rates for each sample area were 89.80%, 75.00%, and 95.39%, respectively. The results demonstrate that our proposed method can effectively extract single-tree point clouds in complex scenes. |
| first_indexed | 2024-03-11T03:21:44Z |
| format | Article |
| id | doaj.art-b98f7456be244b8197593361cf454f2b |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T03:21:44Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-b98f7456be244b8197593361cf454f2b2023-11-18T03:08:08ZengMDPI AGRemote Sensing2072-42922023-05-011510264410.3390/rs15102644Study on Single-Tree Extraction Method for Complex RGB Point Cloud ScenesKai Xia0Cheng Li1Yinhui Yang2Susu Deng3Hailin Feng4College of Mathematics and Computer Science, Zhejiang A & F University, Hangzhou 311300, ChinaCollege of Mathematics and Computer Science, Zhejiang A & F University, Hangzhou 311300, ChinaCollege of Mathematics and Computer Science, Zhejiang A & F University, Hangzhou 311300, ChinaCollege of Environmental and Resource Science, Zhejiang A & F University, Hangzhou 311300, ChinaCollege of Mathematics and Computer Science, Zhejiang A & F University, Hangzhou 311300, ChinaWith the development of sensor technology and point cloud generation techniques, there has been an increasing amount of high-quality forest RGB point cloud data. However, popular clustering-based point cloud segmentation methods are usually only suitable for pure forest scenes and not ideal for scenes with multiple ground features or complex terrain. Therefore, this study proposes a single-tree point cloud extraction method that combines deep semantic segmentation and clustering. This method first uses a deep semantic segmentation network, Improved-RandLA-Net, which is developed based on RandLA-Net, to extract point clouds of specified tree species by adding an attention chain to improve the model’s ability to extract channel and spatial features. Subsequently, clustering is employed to extract single-tree point clouds from the segmented point clouds. The feasibility of the proposed method was verified in the Gingko site, the Lin’an Pecan site, and a Fraxinus excelsior site in a conference center. Finally, semantic segmentation was performed on three sample areas using pre- and postimproved RandLA-Net. The experiments demonstrate that Improved-RandLA-Net had significant improvements in Accuracy, Precision, Recall, and F1 score. At the same time, based on the semantic segmentation results of Improved-RandLA-Net, single-tree point clouds of three sample areas were extracted, and the final single-tree recognition rates for each sample area were 89.80%, 75.00%, and 95.39%, respectively. The results demonstrate that our proposed method can effectively extract single-tree point clouds in complex scenes.https://www.mdpi.com/2072-4292/15/10/2644point cloud extraction of single-treeSfM methodRandLA-Netattention mechanismmeanshift |
| spellingShingle | Kai Xia Cheng Li Yinhui Yang Susu Deng Hailin Feng Study on Single-Tree Extraction Method for Complex RGB Point Cloud Scenes Remote Sensing point cloud extraction of single-tree SfM method RandLA-Net attention mechanism meanshift |
| title | Study on Single-Tree Extraction Method for Complex RGB Point Cloud Scenes |
| title_full | Study on Single-Tree Extraction Method for Complex RGB Point Cloud Scenes |
| title_fullStr | Study on Single-Tree Extraction Method for Complex RGB Point Cloud Scenes |
| title_full_unstemmed | Study on Single-Tree Extraction Method for Complex RGB Point Cloud Scenes |
| title_short | Study on Single-Tree Extraction Method for Complex RGB Point Cloud Scenes |
| title_sort | study on single tree extraction method for complex rgb point cloud scenes |
| topic | point cloud extraction of single-tree SfM method RandLA-Net attention mechanism meanshift |
| url | https://www.mdpi.com/2072-4292/15/10/2644 |
| work_keys_str_mv | AT kaixia studyonsingletreeextractionmethodforcomplexrgbpointcloudscenes AT chengli studyonsingletreeextractionmethodforcomplexrgbpointcloudscenes AT yinhuiyang studyonsingletreeextractionmethodforcomplexrgbpointcloudscenes AT susudeng studyonsingletreeextractionmethodforcomplexrgbpointcloudscenes AT hailinfeng studyonsingletreeextractionmethodforcomplexrgbpointcloudscenes |