一种基于UAV-LiDAR点云的多尺度单木分割
A Multi-Scale Method for 3D Individual Tree Extraction Using UAV-LiDAR
DOI: 10.12677/GST.2021.91003, PDF,  被引量   
作者: 李森磊, 李健平, 蒋腾平, 丛阳滋：武汉大学，测绘遥感信息工程国家重点实验室，湖北 武汉
关键词: 单木分割；LiDAR；UAV；多尺度；Individual Tree Extraction； LiDAR； UAV； Multi-Scale
摘要: 小型UAV-LiDAR (Unmanned Aerial Vehicle-Light Detecting and Ranging)可以快速获取林区三维数据，已经被广泛运用于林业调查。并且通过单木分割可以在激光点云中快速获取单株植被，进而获取单木几何参数。本文利用UAV-LiDAR进行数据采集，针对现有单木分割算法邻域尺度不易确定、复杂场景下单一尺度无法满足等问题设计由粗到精多尺度的单木分割策略，避免对邻域大小等参数的依赖。此外以往区域合并方法主要基于分割点云的水平投影的曲率、大小等，模糊了高程方向信息，由此本文基于点云三维分布特征设计合并准则。实验表明，本文方法在更有效的分割树冠的同时极大的抑制过分割的产生，测区内F得分达到了89%，较原方法提高7%左右。
Abstract: The UAV-LiDAR (Unmanned Aerial Vehicle-Light Detecting and Ranging) can quickly produce 3D point clouds in forest industry, and has been widely used for forestry characterization to facilitate forest ecological and management studies. The geometric properties of individual tree can be easily got from the point clouds, which is handled by the method of individual tree extraction. In this paper, the original point cloud is acquired by low-cost UAV-LiDAR. Because of the problems of the existing method, such as the difficulty in determining the scale of neighborhood and the situation of complex scenes, which is hardly processed by the method with fixed scale, we design a coarse-to-fine multi-scale method. In addition, the methods of previous regional merging are based on the curvature and size of the horizontal projection of segmented point clouds, which blur the information in elevation direction. Therefore, we design a new one, based on the 3D distribution characteristics of point clouds. The experiments show that the framework identifies individual trees more precisely, and greatly inhibits the generation of over-segmentation. The result F-score reaches 89%, which is about 7% more than the original method.
文章引用：李森磊, 李健平, 蒋腾平, 丛阳滋. 一种基于UAV-LiDAR点云的多尺度单木分割[J]. 测绘科学技术, 2021, 9(1): 14-25. https://doi.org/10.12677/GST.2021.91003

参考文献

[1] Hyyppa, J., Kelle, O., Lehikoinen, M., et al. (2001) A Segmentation-Based Method to Retrieve Stem Volume Estimates from 3-D Tree Height Models Produced by Laser Scanners. IEEE Transactions on Geoscience and Remote Sensing, 39, 969-975. [Google Scholar] [CrossRef] 
[2] Popescu, S.C., Wynne, R.H. and Nelson, R.F. (2003) Estimating Plot-Level Tree Heights with LiDAR: Local Filtering with a Canopy-Height Based Variable Window Size. Computers and Electronics in Agriculture, 37, 71-95. [Google Scholar] [CrossRef] 
[3] Chen, Q., Baldocchi, D., Gong, P., et al. (2006) Isolating Individual Trees in a Savanna Woodland Using Small Footprint LIDAR Data. Photogrammetric Engineering & Remote Sensing, 72, 923-932. [Google Scholar] [CrossRef] 
[4] Mongus, D. and Zalik, B. (2015) An Efficient Approach to 3D Sin-gle Tree-Crown Delineation in LiDAR Data. ISPRS Journal of Photogrammetry and Remote Sensing, 108, 219-233. [Google Scholar] [CrossRef] 
[5] Morsdorf, F., Meier, E., Ktz, B., et al. (2004) LIDAR-Based Geometric Reconstruction of Boreal Type Forest Stands at Single Tree Level for Forest and Wildland Fire Management. Remote Sensing of Environment, 92, 353-362. [Google Scholar] [CrossRef] 
[6] 王濮, 邢艳秋, 王成, 等. 一种基于图割的机载LiDAR单木识别方法[J]. 中国科学院大学学报, 2019, 36(3): 385-391.
[7] Li, W., Guo, Q., Jakubowski, M.K., et al. (2012) A New Method for Segmenting Individual Trees from the Lidar Point Cloud. Photogrammetric Engineering and Remote Sensing, 78, 75-84. [Google Scholar] [CrossRef] 
[8] Burt, A., Disney, M. and Calders, K. (2019) Ex-tracting Individual Trees from Lidar Point Clouds Using Treeseg. Methods in Ecology and Evolution, 10, 438-445. [Google Scholar] [CrossRef] 
[9] Shendryk, I., Broich, M., Tulbure, M.G., et al. (2016) Bottom-Up Delineation of Individual Trees from Full-Waveform Airborne Laser Scans in a Structurally Complex Eucalypt Forest. Remote Sensing of Environment, 173, 69-83. [Google Scholar] [CrossRef] 
[10] Ferraz, A., Bretar, F., Jacquemoud, S., et al. (2012) 3-D Mapping of a Multi-Layered Mediterranean Forest Using ALS Data. Remote Sensing of Environment, 121, 210-223. [Google Scholar] [CrossRef] 
[11] Ferraz, A., Bretar, F., Jacquemoud, S., et al. (2010) 3D Segmenta-tion of Forest Structure Using a Mean-Shift Based Algorithm. IEEE International Conference on Image Processing, Hong Kong, 26-29 September 2010, 1413-1416. [Google Scholar] [CrossRef] 
[12] Ferraz, A., Saatchi, S., Mallet, C., et al. (2016) Lidar Detection of Individual Tree Size in Tropical Forests. Remote Sensing of Environment, 183, 318-333. [Google Scholar] [CrossRef] 
[13] Yan, W., Guan, H., Cao, L., et al. (2020) A Self-Adaptive Mean Shift Tree-Segmentation Method Using UAV LiDAR Data. Remote Sensing, 12, 515. [Google Scholar] [CrossRef] 
[14] Xiao, W., Xu, S., Elberink, S.O., et al. (2016) Individual Tree Crown Modeling and Change Detection from Airborne Lidar Data. IEEE Journal of Selected Topics in Applied Earth Obser-vations and Remote Sensing, 9, 3467-3477. [Google Scholar] [CrossRef] 
[15] Dai, W., Yang, B., Dong, Z., et al. (2018) A New Method for 3D Individual Tree Extraction Using Multispectral Airborne LiDAR Point Clouds. ISPRS Journal of Photogrammetry and Remote Sensing, 144, 400-411. [Google Scholar] [CrossRef] 
[16] Xiao, W., Zaforemska, A., Smigaj, M., et al. (2019) Mean Shift Segmentation Assessment for Individual Forest Tree Delineation from Airborne Lidar Data. Remote Sensing, 11, 1263. [Google Scholar] [CrossRef] 
[17] Wang, Y., Hyyppä, J., Liang, X., et al. (2016) International Benchmarking of the Individual Tree Detection Methods for Modeling 3-D Canopy Structure for Silviculture and Forest Ecology Using Airborne Laser Scanning. IEEE Transactions on Geoscience and Remote Sensing, 54, 5011-5027. [Google Scholar] [CrossRef] 
[18] Zhang, W.M., et al. (2016) An Easy-to-Use Airborne LiDAR Data Filtering Method Based on Cloth Simulation. Remote Sensing, 8, 501. [Google Scholar] [CrossRef] 
[19] 杨必胜, 李健平. 轻小型低成本无人机激光扫描系统研制与实践[J]. 武汉大学学报(信息科学版), 2018, 43(12): 219-225.
[20] Goutte, C. and Gaussier, E. (2005) A Probabilistic Interpretation of Precision, Recall and F-Score, with Implication for Evaluation. International Journal of Radiation Biology & Related Studies in Physics Chemistry & Medicine, 51, 952-952.
[21] Sokolova, M., Japkowicz, N. and Szpakowicz, S. (2006) Beyond Accuracy, F-Score and ROC: A Family of Discriminant Measures for Performance Evaluation. In: Australian Joint Conference on Artificial Intelligence: Advances in Artificial Intelligence, Springer, Berlin, 1015-1021. [Google Scholar] [CrossRef] 

为你推荐