|Table of Contents|

Three-Dimensional Phenotypic Reconstruction ofCrop Fruit Based on Multi-View Image(PDF)

《南京师大学报（自然科学版）》[ISSN:1001-4616/CN:32-1239/N]

Issue:
2021年02期
Page:
92-103
Research Field:
·计算机科学与技术·
Publishing date:

Info

Title:
Three-Dimensional Phenotypic Reconstruction ofCrop Fruit Based on Multi-View Image
Author(s):
Yang Huijun1; 4; Wang Ruiping1; Wang Zengying3; Wang Xin2
(1.College of Information Engineering,Northwest A&F University,Yangling 712100,China)(2.Department of Foreign Languages,Northwest A&F University,Yangling 712100,China)(3.Three Squirrels Nanjing R&D Innovation Center,Nanjing 210019,China)(4.Key Laboratory of Agricultural Internet of Things,Ministry of Agriculture and Rural Affairs,Yangling 712100,China)
Keywords:
three-dimensional fruit phenotype; sparse point cloud algorithm; dense point cloud algorithm; denoising
PACS:
O4-39,TP37
DOI:
10.3969/j.issn.1001-4616.2021.02.014
Abstract:
Obtaining point cloud based on laser scanning equipment has many problems such as complicated operation,high cost,and difficulty in popularization. Therefore,this paper studies the three-dimensional phenotypic reconstruction of crop fruit in complex background based on common images. We have built a 3D reconstruction architecture integrating the advantages of SFM algorithm,PMVS algorithm and semi-automatic denoising method. Taking a set of multi-view two-dimensional images of target crop fruits as input sources,we first extracted the feature information of multiple two-dimensional images based on scale of the SIFT operator and rotation invariance parameters. After that,we combined the FLANN algorithm to achieve data matching from different angles. Furthermore,we proposed a fast method of generating sparse point clouds based on the information of key points of 2D pictures and camera parameters. Then,the dense patches are obtained by seed patch extraction and diffusion based on the initial feature matching of PMVS algorithm. We further used visibility constraints to filter out the wrong patches caused by incorrect matching,and realized the generation of complex point cloud model. Finally,we proposed a semi-automatic method to remove outliers from fruit phenotypic point cloud by combining interactive selection and filter,which solved the problem of accurate reconstruction of crop fruit model. The results show that this method in this paper can effectively solve the problem of low-cost,accurate,convenient and fast acquisition of fruit phenotype data in complex experimental environment.

References:

[1] 王孟博. 基于点云的作物植株三维重建技术研究[J]. 鄂州大学学报,2018,25(1):104-106,109.
[2]史维,张吴平,郝雅洁,等. 基于视觉三维重建的作物表型分析[J]. 湖北农业科学,2019(16):125-128.
[3]周静静,郭新宇,吴升,等. 基于多视角图像的植物三维重建研究进展[J]. 中国农业科技导报,2019,21(2):9-18.
[4]黄雄. 三维重建中点云数据配准算法的研究[D]. 秦皇岛:燕山大学,2016.
[5]贾鹤鸣,孟羽佳,邢致恺,等. 基于点云拼接的植物三维模型重建[J]. 应用科技,2019,46(1):23-28.
[6]杨会君. 基于点元的果实三维重建技术研究[D]. 杨凌:西北农林科技大学,2014.
[7]娄吕. 三维激光扫描点云数据精简算法研究[D]. 昆明:昆明理工大学,2017.
[8]皮志荣. 地面三维激光扫描技术在工程测量中的实践[J]. 江西建材,2017(24):225,230.
[9]HENRY P,KRAININ M,HERBST E,et al. RGB-D mapping:using depth cameras for dense 3D modeling of indoor environments[C]. Berlin,Heidelberg:Springer,2010.
[10]马银中. 基于Kinect的三维场景实时重建及相关技术研究[D]. 合肥:安徽大学,2018.
[11]任谦. 基于Kinect传感器的三维稠密地图构建系统设计[J]. 电工技术,2019(6):144-146,149.
[12]杨红庄. 全自动深度相机三维扫描系统[D]. 合肥:中国科学技术大学,2016.
[13]余秀丽,王丹丹,牛磊磊,等. Kinect 在现代农业信息领域中的应用与研究进展[J]. 农机化研究,2015(11):216-221.
[14]董鹏辉,柯良军. 基于图像的三维重建技术综述[J]. 无线电通信技术,2019,45(2):4-8.
[15]XU B,YANG L F,LEI B,et al. A study of the accuracy improvement strategy for multi-view 3D reconstruction instrument based on automatic calibration technology[J]. Acta geoscientica sinica,2017,38(2):243-248.
[16]RUPNIK E,PIERROT D M,DELORME A. 3D reconstruction from multi-view VHR-satellite images in MicMac[J]. ISPRS journal of photogrammetry and remote sensing,2018,139:201-211.
[17]周静静,郭新宇,吴升,等. 基于多视角图像的植物三维重建研究进展[J]. 中国农业科技导报,2019,21(2):9-18.
[18]GANG C,BIN C,YUXIN L,et al. 3D virtual plant photosynthesis simulation model based on L-system[J]. Transactions of the chinese society for agricultural machinery,2018,49(10):275-283.
[19]全思博,李伟光,郑少华. 基于RGB-D传感器的车间三维场景建模[J]. 华南理工大学学报(自然科学版),2015,43(6):42-47.

Memo

Memo:
-
Last Update: 2021-06-30