An Automated Hierarchical Approach for Three-Dimensional Segmentation of Single Trees Using UAV LiDAR Data

被引:35
作者
Yan, Wanqian [1 ]
Guan, Haiyan [2 ]
Cao, Lin [3 ]
Yu, Yongtao [4 ]
Gao, Sha [3 ]
Lu, JianYong [5 ]
机构
[1] Nanjing Univ Informat Sci & Technol, Sch Geog Sci, Nanjing 210044, Jiangsu, Peoples R China
[2] Nanjing Univ Informat Sci & Technol, Sch Remote Sensing & Geomat Engn, Nanjing 210044, Jiangsu, Peoples R China
[3] Nanjing Forestry Univ, Coinnovat Ctr Sustainable Forestry Southern China, 159 Longpan Rd, Nanjing 210037, Jiangsu, Peoples R China
[4] Huaiyin Inst Technol, Fac Comp & Software Engn, Huaian 223003, Peoples R China
[5] Nanjing Univ Informat Sci & Technol, Sch Math & Stat, Inst Space Weather, Nanjing 210044, Jiangsu, Peoples R China
基金
中国国家自然科学基金;
关键词
UAV LiDAR; single tree; segmentation; mean shift; improved normalized cut; INDIVIDUAL TREES; POINT CLOUDS; STEM VOLUME; FOREST; EXTRACTION; ACCURACY; BIOMASS; IMAGERY; MODELS; LEVEL;
D O I
10.3390/rs10121999
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Forests play a key role in terrestrial ecosystems, and the variables extracted from single trees can be used in various fields and applications for evaluating forest production and assessing forest ecosystem services. In this study, we developed an automated hierarchical single-tree segmentation approach based on the high density three-dimensional (3D) Unmanned Aerial Vehicle (UAV) point clouds. First, this approach obtains normalized non-ground UAV points in data preprocessing; then, a voxel-based mean shift algorithm is used to roughly classify the non-ground UAV points into well-detected and under-segmentation clusters. Moreover, potential tree apices for each under-segmentation cluster are obtained with regard to profile shape curves and finally input to the normalized cut segmentation (NCut) algorithm to segment iteratively the under-segmentation cluster into single trees. We evaluated the proposed method using datasets acquired by a Velodyne 16E LiDAR system mounted on a multi-rotor UAV. The results showed that the proposed method achieves the average correctness, completeness, and overall accuracy of 0.90, 0.88, and 0.89, respectively, in delineating single trees. Comparative analysis demonstrated that our method provided a promising solution to reliable and robust segmentation of single trees from UAV LiDAR data with high point cloud density.
引用
收藏
页数:16
相关论文
共 40 条
[1]   Stem Volume and Above-Ground Biomass Estimation of Individual Pine Trees From LiDAR Data: Contribution of Full-Waveform Signals [J].
Allouis, Tristan ;
Durrieu, Sylvie ;
Vega, Cedric ;
Couteron, Pierre .
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2013, 6 (02) :924-934
[2]  
Balenovic I, 2018, CROAT J FOR ENG, V39, P117
[3]   Individual Tree Crown Delineation from Airborne Laser Scanning for Diseased Larch Forest Stands [J].
Barnes, Chloe ;
Balzter, Heiko ;
Barrett, Kirsten ;
Eddy, James ;
Milner, Sam ;
Suarez, Juan C. .
REMOTE SENSING, 2017, 9 (03)
[4]   A new method for 3D individual tree extraction using multispectral airborne LiDAR point clouds [J].
Dai, Wenxia ;
Yang, Bisheng ;
Dong, Zhen ;
Shaker, Ahmed .
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2018, 144 :400-411
[5]   3-D mapping of a multi-layered Mediterranean forest using ALS data [J].
Ferraz, Antonio ;
Bretar, Frederic ;
Jacquemoud, Stephane ;
Goncalves, Gil ;
Pereira, Luisa ;
Tome, Margarida ;
Soares, Paula .
REMOTE SENSING OF ENVIRONMENT, 2012, 121 :210-223
[6]   Comparative Analysis of Clustering-Based Approaches for 3-D Single Tree Detection Using Airborne Fullwave Lidar Data [J].
Gupta, Sandeep ;
Weinacker, Holger ;
Koch, Barbara .
REMOTE SENSING, 2010, 2 (04) :968-989
[7]   Assessing the Accuracy of Georeferenced Point Clouds Produced via Multi-View Stereopsis from Unmanned Aerial Vehicle (UAV) Imagery [J].
Harwin, Steve ;
Lucieer, Arko .
REMOTE SENSING, 2012, 4 (06) :1573-1599
[8]   Advances in Forest Inventory Using Airborne Laser Scanning [J].
Hyyppa, Juha ;
Yu, Xiaowei ;
Hyyppa, Hannu ;
Vastaranta, Mikko ;
Holopainen, Markus ;
Kukko, Antero ;
Kaartinen, Harri ;
Jaakkola, Anttoni ;
Vaaja, Matti ;
Koskinen, Jarkko ;
Alho, Petteri .
REMOTE SENSING, 2012, 4 (05) :1190-1207
[9]   Delineating Individual Trees from Lidar Data: A Comparison of Vector- and Raster-based Segmentation Approaches [J].
Jakubowski, Marek K. ;
Li, Wenkai ;
Guo, Qinghua ;
Kelly, Maggi .
REMOTE SENSING, 2013, 5 (09) :4163-4186
[10]   An International Comparison of Individual Tree Detection and Extraction Using Airborne Laser Scanning [J].
Kaartinen, Harri ;
Hyyppa, Juha ;
Yu, Xiaowei ;
Vastaranta, Mikko ;
Hyyppa, Hannu ;
Kukko, Antero ;
Holopainen, Markus ;
Heipke, Christian ;
Hirschmugl, Manuela ;
Morsdorf, Felix ;
Naesset, Erik ;
Pitkanen, Juho ;
Popescu, Sorin ;
Solberg, Svein ;
Wolf, Bernd Michael ;
Wu, Jee-Cheng .
REMOTE SENSING, 2012, 4 (04) :950-974