Three-Dimensional Modeling of Weed Plants Using Low-Cost Photogrammetry

被引:45
作者
Andujar, Dionisio [1 ]
Calle, Mikel [2 ]
Fernandez-Quintanilla, Cesar [1 ]
Ribeiro, Angela [3 ]
Dorado, Jose [1 ]
机构
[1] CSIC, Inst Agr Sci, E-28006 Madrid, Spain
[2] CSIC, Natl Museum Nat Sci, E-28006 Madrid, Spain
[3] UPM, CSIC, Ctr Automat & Robot, Madrid 28500, Spain
关键词
plant phenotyping; RGB imagery; structure from motion; multi-view stereo; digital surface models; IMAGE-ANALYSIS; SYSTEM; RECONSTRUCTION; VEGETATION; SENSOR; LEVEL; CROPS;
D O I
10.3390/s18041077
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
Sensing advances in plant phenotyping are of vital importance in basic and applied plant research. Plant phenotyping enables the modeling of complex shapes, which is useful, for example, in decision-making for agronomic management. In this sense, 3D processing algorithms for plant modeling is expanding rapidly with the emergence of new sensors and techniques designed to morphologically characterize. However, there are still some technical aspects to be improved, such as an accurate reconstruction of end-details. This study adapted low-cost techniques, Structure from Motion (SfM) and MultiView Stereo (MVS), to create 3D models for reconstructing plants of three weed species with contrasting shape and plant structures. Plant reconstruction was developed by applying SfM algorithms to an input set of digital images acquired sequentially following a track that was concentric and equidistant with respect to the plant axis and using three different angles, from a perpendicular to top view, which guaranteed the necessary overlap between images to obtain high precision 3D models. With this information, a dense point cloud was created using MVS, from which a 3D polygon mesh representing every plants' shape and geometry was generated. These 3D models were validated with ground truth values (e.g., plant height, leaf area (LA) and plant dry biomass) using regression methods. The results showed, in general, a good consistency in the correlation equations between the estimated values in the models and the actual values measured in the weed plants. Indeed, 3D modeling using SfM algorithms proved to be a valuable methodology for weed phenotyping, since it accurately estimated the actual values of plant height and LA. Additionally, image processing using the SfM method was relatively fast. Consequently, our results indicate the potential of this budget system for plant reconstruction at high detail, which may be usable in several scenarios, including outdoor conditions. Future research should address other issues, such as the time-cost relationship and the need for detail in the different approaches.
引用
收藏
页数:11
相关论文
共 33 条
[1]   Weed discrimination using ultrasonic sensors [J].
Andujar, D. ;
Escola, A. ;
Dorado, J. ;
Fernandez-Quintanilla, C. .
WEED RESEARCH, 2011, 51 (06) :543-547
[2]   Influence of Wind Speed on RGB-D Images in Tree Plantations [J].
Andujar, Dionisio ;
Dorado, Jose ;
Maria Bengochea-Guevara, Jose ;
Conesa-Munoz, Jesus ;
Fernandez-Quintanilla, Cesar ;
Ribeiro, Angela .
SENSORS, 2017, 17 (04)
[3]   An Approach to the Use of Depth Cameras for Weed Volume Estimation [J].
Andujar, Dionisio ;
Dorado, Jose ;
Fernandez-Quintanilla, Cesar ;
Ribeiro, Angela .
SENSORS, 2016, 16 (07)
[4]   Discriminating Crop, Weeds and Soil Surface with a Terrestrial LIDAR Sensor [J].
Andujar, Dionisio ;
Rueda-Ayala, Victor ;
Moreno, Hugo ;
Rosell-Polo, Joan Ramon ;
Escola, Alexandre ;
Valero, Constantino ;
Gerhards, Roland ;
Fernandez-Quintanilla, Cesar ;
Dorado, Jose ;
Griepentrog, Hans-Werner .
SENSORS, 2013, 13 (11) :14662-14675
[5]   Potential of a terrestrial LiDAR-based system to characterise weed vegetation in maize crops [J].
Andujar, Dionisio ;
Escola, Alexandre ;
Rosell-Polo, Joan R. ;
Fernandez-Quintanilla, Cesar ;
Dorado, Jose .
COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2013, 92 :11-15
[6]   A growth phenotyping pipeline for Arabidopsis thaliana integrating image analysis and rosette area modeling for robust quantification of genotype effects [J].
Arvidsson, Samuel ;
Perez-Rodriguez, Paulino ;
Mueller-Roeber, Bernd .
NEW PHYTOLOGIST, 2011, 191 (03) :895-907
[7]   Rapid Characterization of Vegetation Structure with a Microsoft Kinect Sensor [J].
Azzari, George ;
Goulden, Michael L. ;
Rusu, Radu B. .
SENSORS, 2013, 13 (02) :2384-2398
[8]   A stereo imaging system for measuring structural parameters of plant canopies [J].
Biskup, Bernhard ;
Scharr, Hanno ;
Schurr, Ulrich ;
Rascher, Uwe .
PLANT CELL AND ENVIRONMENT, 2007, 30 (10) :1299-1308
[9]   Analysis of natural images processing for the extraction of agricultural elements [J].
Burgos-Artizzu, Xavier P. ;
Ribeiro, Angela ;
Tellaeche, Alberto ;
Pajares, Gonzalo ;
Fernandez-Quintanilla, Cesar .
IMAGE AND VISION COMPUTING, 2010, 28 (01) :138-149
[10]  
Guo Q., 2017, SCI CHINA LIFE SCI