In-field crop row phenotyping from 3D modeling performed using Structure from Motion

We propose a phenotyping method to characterize the crop row structure.A crop row 3D model is built using a single camera and Structure from Motion.Structural parameters such as height and leaf area are estimated from this 3D model.Our method was tested with various plant structures and outdoor conditions.Strong agreements were obtained between estimated and actual heights and leaf areas. This article presents a method for crop row structure characterization that is adapted to phenotyping-related issues. In the proposed method, a crop row 3D model is built and serves as a basis for retrieving plant structural parameters. This model is computed using Structure from Motion with RGB images acquired by translating a single camera along the row. Then, to estimate plant height and leaf area, plant and background are discriminated by a robust method that uses both color and height information in order to handle low-contrasted regions. The 3D model is scaled and the plant surface is finally approximated using a triangular mesh.The efficacy of our method was assessed with two data sets collected under outdoor conditions. We also evaluated its robustness against various plant structures, sensors, acquisition techniques and lighting conditions. The crop row 3D models were accurate and led to satisfactory height estimation results, since both the average error and reference measurement error were similar. Strong correlations and low errors were also obtained for leaf area estimation. Thanks to its ease of use, estimation accuracy and robustness under outdoor conditions, our method provides an operational tool for phenotyping applications.

[1]  Sagi Filin,et al.  Estimating plant growth parameters using an energy minimization-based stereovision model , 2013 .

[2]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[3]  Hans Jørgen Andersen,et al.  Geometric plant properties by relaxed stereo vision using simulated annealing , 2005 .

[4]  G. Meyer,et al.  Color indices for weed identification under various soil, residue, and lighting conditions , 1994 .

[5]  John F. Reid,et al.  Stereo vision three-dimensional terrain maps for precision agriculture , 2008 .

[6]  Peter Biber,et al.  Plant detection and mapping for agricultural robots using a 3D LIDAR sensor , 2011, Robotics Auton. Syst..

[7]  S. P. Lloyd,et al.  Least squares quantization in PCM , 1982, IEEE Trans. Inf. Theory.

[8]  A. Escolà,et al.  Obtaining the three-dimensional structure of tree orchards from remote 2D terrestrial LIDAR scanning , 2009 .

[9]  Philippe Lucidarme,et al.  On the use of depth camera for 3D phenotyping of entire plants , 2012 .

[10]  F. Truchetet,et al.  Crop/weed discrimination in perspective agronomic images , 2008 .

[11]  Mei Fangquan,et al.  Growth prediction of a transplant population using artificial neural networks combined with image analysis. , 2002 .

[12]  Andrew Zisserman,et al.  Multiple View Geometry in Computer Vision (2nd ed) , 2003 .

[13]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[14]  B. Andrieu,et al.  Computer stereo plotting for 3-D reconstruction of a maize canopy , 1995 .

[15]  Gabriel Taubin,et al.  The ball-pivoting algorithm for surface reconstruction , 1999, IEEE Transactions on Visualization and Computer Graphics.

[16]  P. C. Robert,et al.  Determination of early stage corn plant height using stereo-vision. , 2003 .

[17]  Thiago T. Santos,et al.  Image-based 3 D digitizing for plant architecture analysis and phenotyping , 2012 .

[18]  C. Willmott,et al.  Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance , 2005 .

[19]  Benjamin Dumont,et al.  Assessment of plant leaf area measurement by using stereo-vision , 2013, 2013 International Conference on 3D Imaging.

[20]  G. Meyer,et al.  Verification of color vegetation indices for automated crop imaging applications , 2008 .

[21]  Qin Zhang,et al.  Development of a stereovision sensing system for 3D crop row structure mapping and tractor guidance , 2008 .

[22]  N. Vigneau.  Potentiel de l'imagerie hyperspectrale de proximité comme outil de phénotypage : application à la concentration en azote du blé , 2010 .

[23]  K. Kraus.  Photogrammetry: Geometry from Images and Laser Scans , 2007 .