期刊文献+

面向表型精确鉴定的豆株快速三维重建 被引量:2

Rapid 3D reconstruction of bean plant for accurate phenotype identification
下载PDF
导出
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。 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.
作者 傅汝佳 冼楚华 李桂清 万隽杰 曹铖 杨存义 高月芳 FU Rujia;XIAN Chuhua;LI Guiqing;WAN Juanjie;CAO Cheng;YANG Cunyi;GAO Yuefang(School of Computer Science and Engineering,South China University of Technology,Guangzhou 510006,China;College of Agriculture,South China Agricultural University,Guangzhou 510640,China)
出处 《浙江大学学报(理学版)》 CAS CSCD 北大核心 2021年第5期531-539,共9页 Journal of Zhejiang University(Science Edition)
基金 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).
关键词 植物表型组学 植物三维重建 骨架提取 植物建模 plant phenotyping plant 3D reconstruction skeleton extraction plant modeling
  • 相关文献

参考文献4

二级参考文献40

共引文献54

同被引文献6

引证文献2

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部