Please wait a minute...
浙江大学学报(理学版)  2021, Vol. 48 Issue (5): 531-539    DOI: 10.3785/j.issn.1008-9497.2021.05.002
图像分析与三维重建     
面向表型精确鉴定的豆株快速三维重建
傅汝佳1, 冼楚华1, 李桂清1, 万隽杰2, 曹铖2, 杨存义2, 高月芳2
1.华南理工大学 计算机科学与工程学院,广东 广州 510006
2.华南农业大学 农学院,广东 广州 510640
Rapid 3D reconstruction of bean plant for accurate phenotype identification
FU Rujia1, XIAN Chuhua1, LI Guiqing1, WAN Juanjie2, CAO Cheng2, YANG Cunyi2, GAO Yuefang2
1.School of Computer Science and Engineering, South China University of Technology, Guangzhou 510006, China
2.College of Agriculture, South China Agricultural University, Guangzhou 510640, China
 全文: PDF(2239 KB)   HTML  
摘要: 利用计算机视觉与图像技术对植物进行数字化重建是植物表型组学的重要手段。以国内常见的粮食作物豆类植株为研究对象,利用RGB-D深度相机采集的深度图像对豆株进行快速三维数字化重建,首先,基于点云分层聚类提取点云骨架点;然后,根据各骨架点到根节点的最短距离连接第一阶段的主干骨架点,并根据形态特征筛选子图和主干图的连接点、选择子图生长路径;最后,由连接骨架进行植物数字化建模。实验表明,基于真实大豆植株点云的单帧和配准数据,本文方法能对不同形态特征的大豆植株进行快速三维重建,并能对分辨率不高、噪音干扰较大、配准误差较大等情形做处理。
关键词: 植物建模植物表型组学骨架提取植物三维重建    
Abstract: Using computer vision and image technology to digitally reconstruct plants is an important means for plant phenotyping. In this paper, we take the common grain crop legume plants in China as the research object, study the rapid three-dimensional digital reconstruction of the bean plants based on the depth images collected by the RGB-D depth camera for accurate phenotype identification. Firstly, the skeleton points are extracted from the point cloud of bean plant by employing a hierarchical clustering algorithm. Secondly, the backbone skeleton points of the first stage are connected according to the shortest distance of each skeleton point to the root node. According to the morphological characteristics, the connection points of the subgraph and the backbone graph are filtered out and the path growth of the subgraph is performed. Finally, the 3D plant model is reconstructed based on the connected skeleton. Experiments show that, under a single frame and registration data of multiple real soybean plants point cloud, the method of this article can carry out rapid three-dimensional reconstruction of the soybean plants with different morphological characteristics, and it is robust for situations such as low resolution, large noise interference, and large registration error.
Key words: plant modeling    plant 3D reconstruction    plant phenotyping    skeleton extraction
收稿日期: 2020-12-08 出版日期: 2021-09-15
CLC:  TP 391.41  
基金资助: 广东省自然科学基金资助项目(2021A1515011849,2019A1515011793);中央高校基本科研业务费项目(2020ZYGXZR042);国家自然科学基金项目(51978271).
作者简介: 傅汝佳(1996—),ORCID:https://orcid.org/0000-0003-4088-2805,男,硕士研究生,主要从事计算机视觉、计算机图形学研究,E-mail:964219224@qq.co;
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
傅汝佳
冼楚华
李桂清
万隽杰
曹铖
杨存义
高月芳

引用本文:

傅汝佳, 冼楚华, 李桂清, 万隽杰, 曹铖, 杨存义, 高月芳. 面向表型精确鉴定的豆株快速三维重建[J]. 浙江大学学报(理学版), 2021, 48(5): 531-539.

FU Rujia, XIAN Chuhua, LI Guiqing, WAN Juanjie, CAO Cheng, YANG Cunyi, GAO Yuefang. Rapid 3D reconstruction of bean plant for accurate phenotype identification. Journal of Zhejiang University (Science Edition), 2021, 48(5): 531-539.

链接本文:

https://www.zjujournals.com/sci/CN/10.3785/j.issn.1008-9497.2021.05.002        https://www.zjujournals.com/sci/CN/Y2021/V48/I5/531

1 BLUM H. Biological shape and visual science (Part I)[J]. Journal of Theoretical Biology, 1973, 38(2): 205-287. DOI: 10.1016/0022-5193(73)90175-6
2 CAO J, TAGLIASACCHI A, OLSON M, et al. Point cloud skeletons via laplacian based contraction[C]//2010 Shape Modeling International Conference. Piscataway: IEEE, 2010: 187-197. DOI: 10.1109/SMI.2010.25.
3 DEY T K, ZHAO W L. Approximating the medial axis from the Voronoi diagram with a convergence guarantee[J]. Algorithmica, 2004, 38(1): 179-200. DOI: 10.1007/s00453-003-1049-y
4 SHINAGAWA Y, KUNII T L. Constructing a Reeb graph automatically from cross sections[J]. IEEE Computer Graphics and Applications, 1991 (6): 44-51. DOI: 10.1109/38.103393.
5 HUANG H, WU S H, COHEN-OR D, et al. L1-medial skeleton of point cloud[J]. ACM Transactions on Graphic,2013, 32(4):65. DOI: 10.1145/2461912. 2461913.
6 SHARF A, LEWINER T, SHAMIR A, et al. On the fly curve skeleton computation for 3D shapes[J]. Computer Graphics Forum, 2007, 26(3): 323-328. DOI: 10.1111/j.1467-8659.2007.01054.x
7 NIBLACK C W, GIBBONS P B, CAPSON D W. Generating skeletons and centerlines from the distance transform[J]. CVGIP: Graphical Models and Image Processing, 1992, 54(5): 420-437. DOI: 10.1016/1049-9652(92)90026-T
8 WU F C, MA W C, LIOU P C, et al. Skeleton extraction of 3D objects with visible repulsive force[C]//KOBBELT L,SCHEDER P,HOPDE H.Eurographics Symposium on Geometry Processing. New York: ACM Press, 2003.
9 LIVNY Y, YAN F, OLSON M, et al. Automatic reconstruction of tree skeletal structures from point clouds[J]. ACM Transaction of Graphics, 2010, 29(6):151. DOI: 10.1145/1866158.1866177
10 DU S L, LINDENBERGH R, LEDOUX H, et al. AdTree: Accurate, detailed, and automatic modelling of laser-scanned trees[J]. Remote Sensing, 2019, 11(18): 2074. DOI: 10.3390/rs11182074
11 BREMER M, RUTZINGER M, WICHMANN V. Derivation of tree skeletons and error assessment using LiDAR point cloud data of varying quality[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2013, 80: 39-50. DOI: 10.1016/j.isprsjprs. 2013.03.003
12 张天安, 云挺, 薛联凤, 等. 基于骨架提取的树木主枝干三维重建算法[J]. 南京师范大学学报 (工程技术版), 2014, 14(4): 51-57. DOI: 10.3969/j.issn. 1672-1292.2014.04.009 ZHANG T A, YUN T, XUE L F, et al. Three-Dimensional reconstruction algorithm of tree limbs based on skeleton extraction[J]. Journal of Nanjing Normal University (Engineering and Technology Edition), 2014, 14(4): 51-57. DOI: 10.3969/j.issn. 1672-1292.2014.04.009
13 PFEIFER N, WINTERHALDER D. Modelling of tree cross sections from terrestrial laser scanning data with free-form curves[C]//International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences. Nice: ISPRS, 2004: 76-81. doi:doi:10.1109/TEST.2004.1387399
14 RUTZINGER M, PRATIHAST A K, OUDE ELBERINK S, et al. Detection and modelling of 3D trees from mobile laser scanning data[C]//International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences. Nice: ISPRS, 2010: 520-525. doi:10.1111/j.1477-9730.2011.00635.x
15 TEOBALDELLI M, PUIG A D, ZENONE T, et al. Building a topological and geometrical model of poplar tree using portable on-ground scanning LIDAR[J]. Functional Plant Biology, 2008, 35(10): 1080-1090. DOI: 10.1071/FP08053.
16 XU H, GOSSETT N, CHEN B Q. Knowledge and heuristic-based modeling of laser-scanned trees[J]. ACM Transactions on Graphics, 2007, 26(4): 19-es. DOI: 10.1145/1289603.1289610
17 BUCKSCH A, LINDENBERGH R. CAMPINO: A skeletonization method for point cloud processing[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2008, 63(1): 115-127. DOI: 10. 1016/j.isprsjprs.2007.10.004
18 钟南, 罗锡文, 秦琴. 基于生长函数的大豆根系生长的三维可视化模拟[J]. 农业工程学报, 2008, 24(7): 151-154. DOI: 10.3321/j.issn:1002-6819. 2008.07.031 ZHONG N, LUO X W, QIN Q. Modeling and visualization of three-dimensional soybean root system growth based on growth functions[J]. Transactions of the Chinese Society of Agricultural Engineering, 2008, 24(7): 151-154. DOI: 10.3321/j.issn:1002-6819.2008.07.031
19 刘阁, 周国民, 胡林. 基于 L 系统的开心形苹果树枝干模型[J]. 安徽农业科学, 2009, 37(16): 7795-7796, 7804. DOI: 10.3969/j.issn.0517-6611.2009. 16.191 LIU G, ZHOU G M, HU L. Trunk and branch model of open-center apple tree based on the L system[J]. Journal of Anhui Agricultural Sciences, 2009, 37(16): 7795-7796, 7804. DOI: 10.3969/j.issn.0517-6611.2009.16.191
20 陈动, 张振鑫, 王臻, 等. 骨架优化下的地面激光树木点云重建方法[J]. 地球信息科学学报, 2019, 21(2): 236-248. DOI:10.12082/dqxxkx.2019.180223 CHEN D, ZHANG Z X, WANG Z, et al. Individual tree modeling from terrestrial laser scanning point clouds via skeleton-based optimization[J]. Journal of Geo-Information Science, 2019, 21(2): 236-248. DOI:10.12082/dqxxkx.2019.180223
[1] 方于华,叶枫. MFDC-Net:一种融合多尺度特征和注意力机制的乳腺癌病理图像分类算法[J]. 浙江大学学报(理学版), 2023, 50(4): 455-464.
[2] 虞瑞麒,刘玉华,沈禧龙,翟如钰,张翔,周志光. 表征学习驱动的多重网络图采样[J]. 浙江大学学报(理学版), 2022, 49(3): 271-279.
[3] 祝锦泰,叶继华,郭凤,江蕗,江爱文. FSAGN: 一种自主选择关键帧的表情识别方法[J]. 浙江大学学报(理学版), 2022, 49(2): 141-150.
[4] 钟颖,王松,吴浩,程泽鹏,李学俊. 基于SEMMA的网络安全事件可视探索[J]. 浙江大学学报(理学版), 2022, 49(2): 131-140.
[5] 朱强,王超毅,张吉庆,尹宝才,魏小鹏,杨鑫. 基于事件相机的无人机目标跟踪算法[J]. 浙江大学学报(理学版), 2022, 49(1): 10-18.
[6] 杨猛,丁曙,马云涛,谢佳翊,段瑞枫. 基于纹理特征的小麦锈病动态模拟方法[J]. 浙江大学学报(理学版), 2022, 49(1): 1-9.
[7] 余鹏, 刘兰, 蔡韵, 何煜, 张松海. 基于单目摄像头的自主健身监测系统[J]. 浙江大学学报(理学版), 2021, 48(5): 521-530.
[8] 桂志强, 姚裕友, 张高峰, 徐本柱, 郑利平. 3D-power图的快速生成方法[J]. 浙江大学学报(理学版), 2021, 48(4): 410-417.
[9] 徐敏, 王科, 戴浩然, 罗晓博, 余炜伦, 陶煜波, 林海. 基于电子病历的乳腺癌群组与治疗方案可视分析[J]. 浙江大学学报(理学版), 2021, 48(4): 391-401.
[10] 邹北骥, 杨文君, 刘姝, 姜灵子. 面向自然场景图像的三阶段文字识别框架[J]. 浙江大学学报(理学版), 2021, 48(1): 1-8.
[11] 陈园琼, 邹北骥, 张美华, 廖望旻, 黄嘉儿, 朱承璋. 医学影像处理的深度学习可解释性研究进展[J]. 浙江大学学报(理学版), 2021, 48(1): 18-29.
[12] 邓惠俊. 排序支持的交互数据分类算法及其应用[J]. 浙江大学学报(理学版), 2021, 48(1): 9-17.
[13] 李华飙, 侯小刚, 王婷婷, 赵海英. 基于规则学习的传统纹样统一生成模式研究[J]. 浙江大学学报(理学版), 2020, 47(6): 669-676.
[14] 檀结庆, 曹宁宁. 一种四边形网格上的Midedge细分格式[J]. 浙江大学学报(理学版), 2019, 46(2): 154-163.