基于L1中值骨架提取的植物茎干补全研究

doi:10.12302/j.issn.1000-2006.202110040

国家林草科技领军期刊
中国精品科技期刊
中国高校百佳科技期刊
江苏省新闻出版政府奖期刊奖
RCCSE林学权威期刊（A+）
CSCD核心期刊
Scopus数据库收录期刊
中文核心期刊
SCD核心期刊

作者加群：102861116

微信公众号：南京林业大学学报

高级检索

南京林业大学学报（自然科学版） ›› 2022, Vol. 46 ›› Issue (1): 40-50.doi: 10.12302/j.issn.1000-2006.202110040

所属专题：第二届中国林草计算机大会论文精选

• 专题报道Ⅱ：第二届中国林草计算机大会论文精选（执行主编李凤日） • 上一篇下一篇

基于L1中值骨架提取的植物茎干补全研究

姜金岑¹(), 李联队², 王美丽¹^,³^,⁴^,^*()

1.西北农林科技大学信息工程学院,陕西杨凌 712100
2.陕西省林业科学院,陕西西安 710082
3.农业农村部农业物联网重点实验室,陕西杨凌 712100
4.陕西省农业信息与智能服务重点实验室,陕西杨凌 712100

收稿日期:2021-10-20 接受日期:2021-11-18 出版日期:2022-01-30 发布日期:2022-02-09
通讯作者: 王美丽
基金资助:
陕西省林业科学院2021年科技创新计划专项(SXLK2021-0214)

Research on plant stem complement based on L1-medial skeleton extraction

JIANG Jincen¹(), LI Liandui², WANG Meili¹^,³^,⁴^,^*()

1. College of Information Engineering Northwest A&F University, Yangling 712100, China
2. Shaanxi Academy of Forestry, Xi’an 710082, China
3. Key Laboratory of Agricultural Internet of Things,Ministry of Agriculture and Rural Affairs, Yangling 712100, China
4. Shaanxi Key Laboratory of Agricultural Information Perception and Intelligent Service, Yangling 712100, China

Received:2021-10-20 Accepted:2021-11-18 Online:2022-01-30 Published:2022-02-09
Contact: WANG Meili

摘要/Abstract

摘要：

【目的】植物的可视化技术是数字林业研究的重要组成部分。针对植物进行三维点云重建时茎干部分容易缺失的问题,基于拓扑连接的缺失部分位置判断及L1中值骨架提取提出一种茎干补全方法,为实现植物可视化提供技术支撑。【方法】依据概率图模型及最小生成树确定点云簇之间的拓扑连接情况,判断缺失部位所在位置。提出了一种基于搜索的待拟合点点集确定方法,使用基于 L1 中值的局部迭代方法提取茎干点云骨架,并对骨架点集进行排序,确定缺失部分待拟合点。最终使用Bezier曲线拟合缺失部分茎干轴线并使用三维参数圆补全缺失部分点云。【结果】对于叶片与茎干缺失分离的植物点云,茎干补全方法可以真实且有效地对其进行补全,拟合结果整体平滑且具有一定的实际物理意义。【结论】通过三维扫描得到的不完整点云在补全后,能在一定程度上弥补扫描的缺陷,构建出完整且逼真的植物三维点云模型,使其能够更加有效地应用于植物的三维可视化建模。

关键词: 三维点云, 细节补全, 骨架优化, 点云排序, 空间拟合, 植物可视化技术

Abstract:

【Objective】 Plant visualization technology is an important part of digital forestry research. This study used the stem missing points to propose a plant stem complement based on L1-medial skeleton extraction to provide technical support for plant visualization. 【Method】 First, a method to determine the position of the missing part based on topological connection was utilized. Based on the density of the point cloud, the point cloud was classed by using the union-find sets. The weight of the edge of the cluster between nodes was calculated based on the probability graph model, and the minimum spanning tree was used to determine the topological connection between clusters; this enabled the determination of the position of missing parts. Following this, a search-based method was used to determine the set of points to be fitted. The L1-medial local iterative method was used to extract the stem point cloud skeleton. A search algorithm based on nearest neighbor distance was proposed to sort the skeleton point set for the disorder of the point cloud, to determine points to be fitted for missing parts. To address issues with inaccurate skeleton extraction, an iterative optimization method of stem skeleton based on Gauss kernel weight was proposed. This approach used Gauss smoothing stem direction vector, and the Gauss weighted average to calculate stem radius and the updated stem skeleton point set. Finally, a method of point cloud completion of missing parts based on fitting was utilized. The stem radius of missing parts was fitted based on the least squares method, and the stem line of missing parts was fitted based on the Bezier curve. A method based on point cloud density to adjust the generation of the fitting point cloud was proposed to better fit the actual point cloud. 【Result】 The experimental results show that the method proposed in this paper can effectively complete the plant point cloud with leaf and stem missing separation; the fitting result was smooth and has certain practical, physical significance. 【Conclusion】 To some extent, the research results in this paper make up for the defects of scanning, building a complete and realistic three-dimensional point cloud model of plants; this may be more effectively applied to the three-dimensional visual modeling of plants.

Key words: 3D point cloud, detail completion, skeleton optimization, point cloud sorting, spatial fitting, plant visualization technology

中图分类号:

S237
TP391

姜金岑,李联队,王美丽. 基于L1中值骨架提取的植物茎干补全研究[J]. 南京林业大学学报（自然科学版）, 2022, 46(1): 40-50.

JIANG Jincen, LI Liandui, WANG Meili. Research on plant stem complement based on L1-medial skeleton extraction[J].Journal of Nanjing Forestry University (Natural Science Edition), 2022, 46(1): 40-50.DOI: 10.12302/j.issn.1000-2006.202110040.

图/表 17

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

图11

图12

图13

图14

图15

表1

图16

参考文献 26

[1]	赵春江, 陆声链, 郭新宇, 等. 数字植物研究进展:植物形态结构三维数字化[J]. 中国农业科学, 2015, 48(17):3415-3428.
	ZHAO C J, LU S L, GUO X Y, et al. Advances in research of digital plant:3D digitization of plant morphological structure[J]. Sci Agric Sin, 2015, 48(17):3415-3428.DOI: 10.3864/j.issn.0578-1752.2015.17.009. doi: 10.3864/j.issn.0578-1752.2015.17.009
[2]	史川石, 郑倩, 黄惠. 基于叶片识别的侵入式室内植物建模[J]. 计算机辅助设计与图形学学报, 2021, 33(2):161-168.
	SHI C S, ZHENG Q, HUANG H. Intrusive indoor plant modeling guided by leaf recognition[J]. J Comput Aided Des Comput Graph, 2021, 33(2):161-168.
[3]	胡春华, 李萍萍. 树木三维可视化建模技术研究述评[J]. 南京林业大学学报(自然科学版), 2015, 39(6):148-154.
	HU C H, LI P P. A survey of 3D visualization modeling technologies for trees[J]. J Nanjing For Univ (Nat Sci Ed), 2015, 39(6):148-154.
[4]	ZENG L L. 3D plants reconstruction based on point cloud[J]. Int J Perform Eng, 2018, 14(1):121.DOI: 10.23940/ijpe.18.01.p13.121133. doi: 10.23940/ijpe.18.01.p13.121133
[5]	辛卫涛. 基于参数智能提取的植物建模方法研究[D]. 杭州:浙江工业大学, 2020.
	XIN W T. Research on plant modeling method based on intelligent parameter extraction[D]. Hangzhou:Zhejiang University of Technology, 2020.
[6]	MURCIA H F, SANABRIA D A, DEHYRO-MÉNDEZ, et al. Development of a simulation tool for 3D plant modeling based on 2D LiDAR sensor[C]// 2020 Virtual Symposium in Plant Omics Sciences (OMICAS).November 23-27,2020.Bogotá,Colombia: IEEE, 2020:1-6.DOI: 10.1109/OMICAS52284.2020.9535651. doi: 10.1109/OMICAS52284.2020.9535651
[7]	PATURKAR A, GUPTA G S, BAILEY D. Effect on quality of 3D model of plant with change in number and resolution of images used:an investigation[M]// Lecture Notes in Electrical Engineering.Singapore:Springer Singapore, 2021:377-388.DOI: 10.1007/978-981-15-8391-9_28. doi: 10.1007/978-981-15-8391-9_28
[8]	朱超, 苗腾, 许童羽, 等. 基于骨架和最优传输距离的玉米点云茎叶分割和表型提取[J]. 农业工程学报, 2021, 37(4):188-198.
	ZHU C, MIAO T, XU T Y, et al. Segmentation and phenotypic trait extraction of maize point cloud stem-leaf based on skeleton and optimal transportation distances[J]. Trans Chin Soc Agric Eng, 2021, 37(4):188-198.
[9]	LARI Z, HABIB A, A novel hybrid approach for the extraction of linear/cylindrical features from laser scanning data[J]. ISPRS Ann Photogramm Remote Sens Spatial Inf Sci, 2013, II-5/W2:151-156.DOI: 10.5194/isprsannals-ii-5-w2-151-2013. doi: 10.5194/isprsannals-ii-5-w2-151-2013
[10]	ZHAN Q, LIANG Y, XIAO Y. Color-based segmentation of point clouds[J]. Laser Scanning, 2009, 38(3):155-161.
[11]	PAULUS S, DUPUIS J, MAHLEIN A K, et al. Surface feature based classification of plant organs from 3D laserscanned point clouds for plant phenotyping[J]. BMC Bioinformatics, 2013, 14:238.DOI: 10.1186/1471-2105-14-238. doi: 10.1186/1471-2105-14-238
[12]	GELARD W, DEVY M, HERBULOT A, et al. Model-based segmentation of 3D point clouds for phenotyping sunflower plants[C]// Proceedings of the 12th International Joint Conference on Computer Vision,Imaging and Computer Graphics Theory and Applications.February 27-March 1,2017.Porto,Portugal: SCITEPRESS-Science and Technology Publications, 2017:459-467.DOI: 10.5220/0006126404590467. doi: 10.5220/0006126404590467
[13]	李杨先, 张慧春, 杨旸. 一种基于图像处理技术的植物形态表型参数获取方法[J]. 林业工程学报, 2020, 5(6):128-136.
	LI Y X, ZHANG H C, YANG Y. A method for obtaining plant morphological phenotypic parameters using image processing technology[J]. J For Eng, 2020, 5(6):128-136.doi: 10.13360/j.issn.2096-1359.201911003. doi: 10.13360/j.issn.2096-1359.201911003
[14]	TAGLIASACCHI A, ZHANG H, COHEN-OR D. Curve skeleton extraction from incomplete point cloud[C]//ACM SIGGRAPH 2009 papers on-SIGGRAPH’09.August 3-7,2009.New Orleans,Louisiana. New York: ACM Press, 2009:1-9. DOI: 10.1145/1576246.1531377. doi: 10.1145/1576246.1531377
[15]	HUANG H, WU S H, COHEN-OR D, et al. L1 -medial skeleton of point cloud[J]. ACM Trans Graph, 2013, 32(4):1-8.DOI: 10.1145/2461912.2461913. doi: 10.1145/2461912.2461913
[16]	WU S H, HUANG H, GONG M L, et al. Deep points consolidation[J]. ACM Trans Graph, 2015, 34(6):1-13.DOI: 10.1145/2816795.2818073. doi: 10.1145/2816795.2818073
[17]	ZHANG Q S, SONG X, SHAO X W, et al. Unsupervised skeleton extraction and motion capture from 3D deformable matching[J]. Neurocomputing, 2013, 100:170-182.DOI: 10.1016/j.neucom.2011.11.032. doi: 10.1016/j.neucom.2011.11.032
[18]	LU X, CHEN H, YEUNG S K, et al. Unsupervised articulated skeleton extraction from point set sequences captured by a single depth camera[C]// Thirty-Second AAAI Conference on Artificial Intelligence. 2018:7226-7234
[19]	LU X Q, DENG Z G, LUO J, et al. 3D articulated skeleton extraction using a single consumer-grade depth camera[J]. Comput Vis Image Underst, 2019, 188:102792.DOI: 10.1016/j.cviu.2019.102792. doi: 10.1016/j.cviu.2019.102792
[20]	CHARLES R Q, HAO S, MO K C, et al. PointNet:deep learning on point sets for 3D classification and segmentation[C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).July 21-26,2017. Honolulu: IEEE, 2017:77-85.DOI: 10.1109/CVPR.2017.16. doi: 10.1109/CVPR.2017.16
[21]	YU L Q, LI X Z, FU C W, et al. PU-net:point cloud upsampling network[C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.June 18-23,2018. Salt Lake City, IEEE, 2018:2790-2799.DOI: 10.1109/CVPR.2018.00295. doi: 10.1109/CVPR.2018.00295
[22]	YU L Q, LI X Z, FU C W, et al. EC-net:an edge-aware point set consolidation network[M]//Computer Vision: ECCV 2018. Cham: Springer International Publishing, 2018:398-414. DOI: 10.1007/978-3-030-01234-2_24. doi: 10.1007/978-3-030-01234-2_24
[23]	YIFAN W, WU S H, HUANG H, et al. Patch-based progressive 3D point set upsampling[C]// 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).June 15-20,2019. Long Beach: IEEE, 2019:5951-5960.DOI: 10.1109/CVPR.2019.00611. doi: 10.1109/CVPR.2019.00611
[24]	罗开乾, 朱江平, 周佩, 等. 基于多分支结构的点云补全网络[J]. 激光与光电子学进展, 2020, 57(24):209-216.
	LUO K Q, ZHU J P, ZHOU P, et al. Point cloud completion network based on multibranch structure[J]. Laser Optoelectron Prog, 2020, 57(24):209-216.
[25]	WEN X, HAN Z Z, CAO Y P, et al. Cycle4Completion:unpaired point cloud completion using cycle transformation with missing region coding[C]// 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).June 20-25,2021. Nashville: IEEE, 2021:13075-13084.DOI: 10.1109/CVPR46437.2021.01288. doi: 10.1109/CVPR46437.2021.01288
[26]	ZHANG X C, FENG Y T, LI S Q, et al. View-guided point cloud completion[C]// 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).June 20-25,2021,Nashville: IEEE, 2021:15885-15894.DOI: 10.1109/CVPR46437.2021.01563. doi: 10.1109/CVPR46437.2021.01563

模型 model	倒角距离 chamfer distance	均方误差 mean square error
玫瑰花(图15上)	0.44×10^-5	1.22×10^-3
向日葵(图15中)	1.21×10^-5	1.91×10^-3
罂粟(图15下)	1.03×10^-5	1.84×10^-3

基于L1中值骨架提取的植物茎干补全研究

Research on plant stem complement based on L1-medial skeleton extraction

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 17

参考文献 26

相关文章 0

编辑推荐

Metrics

本文评价

作者

读者

审稿