基于分层叠加的机载LiDAR点云单木分割

doi:10.11707/j.1001-7488.LYKX20220303

Abstract

Abstract:

Objective: This paper proposed an individual tree segmentation algorithm utilizing hierarchical layer stacking approach to optimize the use of high-density LiDAR point cloud data, thereby improving the accuracy of individual tree segmentation in the understory of forest stands. Method: Diverging from traditional algorithms which utilize canopy vertices as cluster seeds, this hierarchical overlay-based segmentation algorithm selects local maxima of each layer after horizontal slicing of point clouds for tiered clustering. It diminishes the over-segmentation due to branches through layered overlay and iterative refinement, securing segmentation precision of canopy trees and boosting extraction of understory trees. Result: The tree segmentation algorithm based on layer stacking exhibits high precision in larch stands of various stem densities, with a maximum matching success rate of 94% between extracted and observed trees, and up to 92% in medium to high density stands. Compared to other algorithms, the matching rate for mid and lower-layer trees can be improved by 20% to 40%. In terms of individual tree height extraction precision, the correlation coefficient between extracted and observed tree heights is 0.8, with a relative root mean square error of 8.45%. The highest correlation coefficient between extracted and observed crown widths is 0.83, with a relative root mean square error of 16.5%. Conclusion: By stacking hierarchical clustering and optimizing seed point selection, the comprehensive use of point cloud data across forest layers enhances individual tree segmentation accuracy, providing valuable data support for forest management and operations.

Key words: airborne LiDAR, larch plantation, understory trees, layers stacking, seed point optimization

CLC Number:

S757

Dan Kong,Yong Pang,Xiaojun Liang,Liming Du,Yu Bai. Individual Tree Segmentation from ALS Point Clouds Based on Layers Stacking Algorithm[J]. Scientia Silvae Sinicae, 2024, 60(3): 87-99.

Figures/Tables 17

Fig.1

Table 1

Table 2

Fig.2

Fig.3

Table 3

Fig.4

Fig.5

Fig.6

Fig.7

Fig.8

Fig.9

Fig.10

Fig.11

Fig.12

Fig.13

Fig.14

References 0

	霍朗宁, 张晓丽. 基于机载LiDAR点云多层聚类的单木信息提取及其精度评价. 林业科学, 2021, 57 (1): 85- 94.
	Huo L N, Zhang X L. Individual tree information extraction and accuracy evaluation based on airborne LiDAR point cloud by multilayer clustering method. Scientia Silvae Sinicae, 2021, 57 (1): 85- 94.
	梁晓军, 庞　勇, 陈博伟. 基于地基激光雷达胸径提取的单木位置精确测量. 林业科学研究, 2020, 33 (4): 67- 74.
	Liang X J, Pang Y, Chen B W. Accurate measurement of individual tree position based on DBH extraction of terrestrial laser scanning. Forest Research, 2020, 33 (4): 67- 74.
	庞　勇, 梁晓军, 荚　文, 等. 塞罕坝林场机载综合遥感试验. 遥感学报, 2021, 25 (4): 904- 917. doi: 10.11834/jrs.20210222
	Pang Y, Liang X J, Jia W, et al. The comprehensive airborne remote sensing experiment in Saihanba forest farm. National Remote Sensing Bulletin, 2021, 25 (4): 904- 917. doi: 10.11834/jrs.20210222
	Ayrey E, Fraver S, Kershaw J A Jr, et al. Layer stacking: a novel algorithm for individual forest tree segmentation from LiDAR point clouds. Canadian Journal of Remote Sensing, 2017, 43 (1): 16- 27. doi: 10.1080/07038992.2017.1252907
	Dong T, Zhang X, Ding Z, et al. Multi-layered tree crown extraction from LiDAR data using graph-based segmentation. Computers and Electronics in Agriculture, 2020, 170, 105213. doi: 10.1016/j.compag.2020.105213
	Dubayah R, Blair J B, Goetz S, et al. The global ecosystem dynamics investigation: high-resolution laser ranging of the earth’s forests and topography. Science of Remote Sensing, 2020, 1, 100002. doi: 10.1016/j.srs.2020.100002
	Ferraz A, Bretar F, Jacquemoud S, et al. 3-D mapping of a multi-layered Mediterranean forest using ALS data. Remote Sensing of Environment, 2012, 121, 210. doi: 10.1016/j.rse.2012.01.020
	Gupta S, Weinacker H, Koch B. Comparative analysis of clustering-based approaches for 3-D single tree detection using airborne fullwave LiDAR data. Remote Sensing, 2010, 2 (4): 968- 989. doi: 10.3390/rs2040968
	Hamraz H, Contreras M A, Zhang J. Vertical stratification of forest canopy for segmentation of understory trees within small-footprint airborne LiDAR point clouds. ISPRS Journal of Photogrammetry and Remote Sensing, 2017, 130, 385- 392. doi: 10.1016/j.isprsjprs.2017.07.001
	Hu B, Li J, Jing L, et al. Improving the efficiency and accuracy of individual tree crown delineation from high-density LiDAR data. International Journal of Applied Earth Observation and Geoinformation, 2014, 26, 145- 155. doi: 10.1016/j.jag.2013.06.003
	Hyyppä J, Hyyppä H, Inkinen M, et al. Accuracy comparison of various remote sensing data sources in the retrieval of forest stand attributes. Forest Ecology and Management, 2000, 128 (1/2): 109- 120.
	Jin S C, Su Y J, Gao S, et al. Deep learning: individual maize segmentation from terrestrial LiDAR data using faster R-CNN and regional growth algorithms. Frontiers in Plant Science, 2018, 22 (9): 866.
	Kandare K, Ørka H O, Chan J C W, et al. Effects of forest structure and airborne laser scanning point cloud density on 3D delineation of individual tree crowns. European Journal of Remote Sensing, 2016, 49 (1): 337- 359. doi: 10.5721/EuJRS20164919
	Khosravipour A, Skidmore A K, Isenburg M. Generating spike-free digital surface models using LiDAR raw point clouds: a new approach for forestry applications. International Journal of Applied Earth Observation and Geoinformation, 2016, 52, 104- 114. doi: 10.1016/j.jag.2016.06.005
	Li W K, Guo Q H, Jakubowski M K, et al. A new method for segmenting individual trees from the LiDAR point cloud. Photogrammetric Engineering & Remote Sensing, 2012, 78 (1): 75- 84.
	Lindberg E, Holmgren J. Individual tree crown methods for 3D data from remote sensing. Current Forestry Reports, 2017, 3 (1): 19- 31. doi: 10.1007/s40725-017-0051-6
	Morsdorf F, Meier E, Kötz B, et al. LIDAR-based geometric reconstruction of boreal type forest stands at single tree level for forest and wildland fire management. Remote Sensing of Environment, 2004, 92 (3): 353- 362. doi: 10.1016/j.rse.2004.05.013
	Næsset E. Predicting forest stand characteristics with airborne scanning laser using a practical two-stage procedure and field data. Remote Sensing of Environment, 2002, 80 (1): 88- 99. doi: 10.1016/S0034-4257(01)00290-5
	Pang Y, Li Z, Ju H, et al. LiCHy: The CAF’s LiDAR, CCD and hyperspectral integrated airborne observation system. Remote Sensing, 2016, 8 (5): 398. doi: 10.3390/rs8050398
	Pang Y, Wang W W, Du L M, et al. Nyström-based spectral clustering using airborne LiDAR point cloud data for individual tree segmentation. International Journal of Digital Earth, 2021, 14 (10): 1452- 1476. doi: 10.1080/17538947.2021.1943018
	Pitkänen J, Maltamo M, Hyyppä J, et al. 2004. Adaptive methods for individual tree detection on airborne laser based canopy height model. International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, XXXVI-8/W2
	Pu S, Rutzinger M, Vosselman G, et al. Recognizing basic structures from mobile laser scanning data for road inventory studies. ISPRS Journal of Photogrammetry and Remote Sensing, 2011, 66 (6): S28- S39. doi: 10.1016/j.isprsjprs.2011.08.006
	Reitberger J, Schnörr C, Krzystek P, et al. 3D segmentation of single trees exploiting full waveform LiDAR data. ISPRS Journal of Photogrammetry and Remote Sensing, 2009, 64 (6): 561- 574. doi: 10.1016/j.isprsjprs.2009.04.002
	Soille P. 2004. Morphological image analysis: principles and applications. New York: Springer, 201-204.
	Tang F F, Zhang X H, Liu J N. 2007. Segmentation of tree crown model with complex structure from airborne LiDAR data. Geoinformatics 2007: Remotely Sensed Data and Information. Nanjing, China, SPIE, 6752(1): 67520A- 67520A- 9.
	Wang J, Chen X, Cao L, et al. Individual rubber tree segmentation based on ground-based LiDAR data and faster R-CNN of deep learning. Forests, 2019, 10 (9): 793. doi: 10.3390/f10090793
	Zhao D, Pang Y, Li Z Y, et al. Isolating individual trees in a closed coniferous forest using small footprint LiDAR data. International Journal of Remote Sensing, 2014, 35 (20): 7199- 7218. doi: 10.1080/01431161.2014.967886
	Zimble D A, Evans D L, Carlson G C, et al. Characterizing vertical forest structure using small-footprint airborne LiDAR. Remote Sensing of Environment, 2003, 87 (2/3): 171- 182.

样地 Plot	点云密度 Point density/ (pts·m^?2)	株数 Number of trees	样地尺寸 Plot size /hm²	平均树高 Average height/m	平均冠幅半径 Average crown radius /m	密度 Stem density/ (trees·hm^?2)	密度等级 Stem density
1	9	114	0.06	13.55	1.23	1 900	高High
2	31	113	0.09	20.28	1.45	1 256	中Middle
3	11	73	0.06	22.24	1.26	1 217	中Middle
4	10	113	0.09	19.25	1.44	1 256	中Middle
5	7	6	0.06	17.41	1.50	1 117	中Middle
6	9	71	0.06	20.62	1.40	1 183	中Middle
7	9	65	0.06	21.31	1.42	1 083	中Middle
8	9	109	0.09	19.36	1.56	1 211	中Middle
9	9	111	0.15	22.19	1.89	740	低Low
10	11	82	0.15	22.82	2.45	547	低Low
11	10	73	0.15	24.23	2.53	487	低Low
12	31	1 435	5.20	18.92	3.05	276	低Low
12^*	31	119		27.10	1.91		低Low

研究区 Study area	飞行时间 Fight time	相对飞行高度 Relative fight height/m	平均点云密度 Mean point density/m^?2	航带融合偏差 Airband fusion difference/m	飞行平台 Flying platform
孟家岗Mengjiagang	2017年6—7月 June—July 2017	800	≥ 12	≤ 0.25	运五固定翼飞机 Y-5 fixed-wing aircraft
塞罕坝Saihanba	2018年8—9月 August—September 2018	900	≥ 30	≤ 0.2	小松鼠直升机 Squirrel helicopter

编号No.	树高范围 Tree height/m	高度阈值 Height criterion/m	距离阈值 Distance criterion/m
1	H ≤ 10	ΔH < 3	ΔD < 1+CrMean
2	10 <H ≤ 15	ΔH < 3	ΔD <1+ CrMean
3	15 < H ≤ 25	ΔH < 4	ΔD < 1+CrMean
4	H > 25	ΔH < 5	ΔD < 1+CrMean

[1]	Zhou Xiangbei, Li Chungan, Dai Huabing, Yu Zhu, Li Zhen, Su Kai. Effects of Point Cloud Density on the Estimation Accuracy of Large-Area Subtropical Forest Inventory Attributes Using Airborne LiDAR Data [J]. Scientia Silvae Sinicae, 2023, 59(9): 23-33.
[2]	Yalin Xie,Xiangdong Lei,Weisheng Zeng. Compilation of Growth and Yield Table for Larch Plantations Based on 3-PG_mix Model [J]. Scientia Silvae Sinicae, 2023, 59(12): 87-104.
[3]	Ting Ma,Chonggui Li,Fuquan Tang,Jie Lü. Extraction of Larch Plantation Based on Multi-Classifier Ensemble [J]. Scientia Silvae Sinicae, 2021, 57(11): 105-118.
[4]	Chungan Li,Zhen Li. Generalizing Predictive Models of Sub-Tropical Forest Inventory Attributes Using an Area-Based Approach with Airborne LiDAR Data [J]. Scientia Silvae Sinicae, 2021, 57(10): 23-35.
[5]	Xiao He,Xiangdong Lei. Spatial Autoregressive Biomass Conversion and Expansion Factor Models for Larch Plantations in Northeast China [J]. Scientia Silvae Sinicae, 2021, 57(10): 49-58.
[6]	Langning Huo,Xiaoli Zhang. Individual Tree Information Extraction and Accuracy Evaluation Based on Airborne LiDAR Point Cloud by Multilayer Clustering Method [J]. Scientia Silvae Sinicae, 2021, 57(1): 85-94.
[7]	Chen Dongsheng, Li Fengri, Sun Xiaomei, Zhang Shougong. Reconstruction Dynamic Models of Height to Crown Base of Larch(Larix olgensis)Plantation Applying Knot Analysis Technique [J]. Scientia Silvae Sinicae, 2019, 55(9): 103-110.
[8]	You Haotian, Xing Yanqiu, Peng Tao, Ding Jianhua. Research on the Effect of Side-Overlap between Airborne LiDAR Adjacent Swaths on the Coniferous Forest Structural Parameters Estimation [J]. Scientia Silvae Sinicae, 2018, 54(6): 109-118.
[9]	Gu Wei, Ma Ling, Sun Hu, Wang Lidong, Zhang Zilong. Variation in Structure and Dynamics of Insect Community in Larch Plantations under Different Soil Conditions [J]. Scientia Silvae Sinicae, 2017, 53(5): 97-106.
[10]	Gao Min, Ma Xiangli, Yang Jinyu, Huang Xuanrui, Wu Yanan. Influence of the Mixed Modes of Larch and Birch on Soil Faunal Community in Mountain Area of Northern Hebei, China [J]. Scientia Silvae Sinicae, 2017, 53(1): 70-81.
[11]	Cao Lin, Dai Jinsong, Pang Yong, Zhao Bing, Xu Jianxin, Li Zengyuan. Estimation of Urban Building Rooftop-Received Solar Energy by LiDAR and Irradiation Model in the Urban Vegetation Shading Environment [J]. Scientia Silvae Sinicae, 2014, 50(2): 99-110.
[12]	Yin Yanbao;Tang Shouzheng;Lang Pumei;Gao Ruixin. Determination of DEM Based on Multiple-Echo Data of Airborne LiDAR in Mountainous Wooded Area Using Discriminant Analysis [J]. Scientia Silvae Sinicae, 2011, 47(12): 106-113.
[13]	Chen Dongsheng;Li Fengri;Sun Xiaomei;Jia Weiwei. Models to Predict Knot Size for Larch Plantation Using Linear Mixed Model [J]. Scientia Silvae Sinicae, 2011, 47(11): 121-128.
[14]	Dong Xibin;Wang Lihai. Optimal Selection of Harvesting Modes in Larch Plantation [J]. Scientia Silvae Sinicae, 2007, 43(9): 48-52.
[15]	Chen Lixin;Yang Chengdong. Component of Soil Humic Substances in Larch Plantations and Its Effects on Soil Acidity [J]. Scientia Silvae Sinicae, 2007, 43(2): 8-14.

Individual Tree Segmentation from ALS Point Clouds Based on Layers Stacking Algorithm

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 17

References 0

Related Articles 15

Recommended Articles

Metrics

Comments