Point cloud based iterative segmentation technique for 3D plant phenotyping

The segmentation of 3D point clouds is an important prerequisite step for many plant phenotype and data analysis. One of the main challenges is high resolution 3D plant model segmentation. In this paper, we present an iteration based approach for 3D segmentation directly from the dense point clouds that are reconstructed from multi-view images. We extend the existing euclidean distance and spectral clustering (SC) algorithms and using iteration approach to segment the 3D point clouds into elementary shape units that could represent the plant organs (stems, branches, leaves, etc.). Such approach only requires the 3D coordinate data information. Experimental results show our approach can effectively segmented the obtained point cloud for various plant species.

[1]  Reinhard Klein,et al.  Efficient RANSAC for Point‐Cloud Shape Detection , 2007, Comput. Graph. Forum.

[2]  W. Diepenbrock,et al.  A method to extract morphological traits of plant organs from 3D point clouds as a database for an architectural plant model , 2007 .

[3]  K. Omasa,et al.  3D lidar imaging for detecting and understanding plant responses and canopy structure. , 2006, Journal of experimental botany.

[4]  Hans Pretzsch,et al.  Structural crown properties of Norway spruce (Picea abies [L.] Karst.) and European beech (Fagus sylvatica [L.]) in mixed versus pure stands revealed by terrestrial laser scanning , 2013, Trees.

[5]  Alan H. Strahler,et al.  Finding Leaves in the Forest: The Dual-Wavelength Echidna Lidar , 2015, IEEE Geoscience and Remote Sensing Letters.

[6]  Radu Bogdan Rusu,et al.  Semantic 3D Object Maps for Everyday Manipulation in Human Living Environments , 2010, KI - Künstliche Intelligenz.

[7]  Lutz Plümer,et al.  Low-Cost 3D Systems: Suitable Tools for Plant Phenotyping , 2014, Sensors.

[8]  U. Schurr,et al.  Leaf development in Ricinus communis during drought stress: dynamics of growth processes, of cellular structure and of sink-source transition. , 2000, Journal of experimental botany.

[9]  Nico Blodow,et al.  Towards 3D Point cloud based object maps for household environments , 2008, Robotics Auton. Syst..

[10]  Minglun Gong,et al.  Full 3D Plant Reconstruction via Intrusive Acquisition , 2016, Comput. Graph. Forum.

[11]  Jean Ponce,et al.  Accurate, Dense, and Robust Multiview Stereopsis , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  I. Xenarios,et al.  Measuring the diurnal pattern of leaf hyponasty and growth in Arabidopsis - a novel phenotyping approach using laser scanning. , 2012, Functional plant biology : FPB.

[13]  Ulrike von Luxburg,et al.  A tutorial on spectral clustering , 2007, Stat. Comput..

[14]  Olivier Salvado,et al.  Automated 3D Segmentation and Analysis of Cotton Plants , 2011, 2011 International Conference on Digital Image Computing: Techniques and Applications.

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

[16]  F. Tardieu,et al.  Multi-scale phenotyping of leaf expansion in response to environmental changes: the whole is more than the sum of parts. , 2009, Plant, cell & environment.

[17]  Radu Bogdan Rusu,et al.  3D is here: Point Cloud Library (PCL) , 2011, 2011 IEEE International Conference on Robotics and Automation.

[18]  Tony P. Pridmore,et al.  A patch-based approach to 3D plant shoot phenotyping , 2016, Machine Vision and Applications.

[19]  B. Andrieu,et al.  Towards a generic architectural model of tillering in Gramineae, as exemplified by spring wheat (Triticum aestivum). , 2005, The New phytologist.

[20]  M. Tester,et al.  Phenomics--technologies to relieve the phenotyping bottleneck. , 2011, Trends in plant science.

[21]  H. Scharr,et al.  A stereo imaging system for measuring structural parameters of plant canopies. , 2007, Plant, cell & environment.

[22]  Jayme G. A. Barbedo,et al.  3D Plant Modeling: Localization, Mapping and Segmentation for Plant Phenotyping Using a Single Hand-held Camera , 2014, ECCV Workshops.

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

[24]  Jean-Louis Drouet,et al.  MODICA and MODANCA: modelling the three-dimensional shoot structure of graminaceous crops from two methods of plant description , 2003 .

[25]  Yonghuai Liu,et al.  Estimation of Branch Angle from 3D Point Cloud of Plants , 2015, 2015 International Conference on 3D Vision.

[26]  Anh Nguyen,et al.  3D point cloud segmentation: A survey , 2013, 2013 6th IEEE Conference on Robotics, Automation and Mechatronics (RAM).

[27]  Kristian Kersting,et al.  Automated interpretation of 3D laserscanned point clouds for plant organ segmentation , 2015, BMC Bioinformatics.

[28]  Q. Guo,et al.  A geometric method for wood-leaf separation using terrestrial and simulated Lidar data , 2015 .

[29]  K. Omasa,et al.  Estimating vertical plant area density profile and growth parameters of a wheat canopy at different growth stages using three-dimensional portable lidar imaging , 2009 .

[30]  N. Pfeifer,et al.  SEGMENTATION BASED ROBUST INTERPOLATION - A NEW APPROACH TO LASER DATA FILTERING , 2005 .

[31]  B. Andrieu,et al.  Functional-structural plant modelling: a new versatile tool in crop science. , 2010, Journal of experimental botany.

[32]  Teng Ma,et al.  Point cloud segmentation through spectral clustering , 2010, The 2nd International Conference on Information Science and Engineering.

[33]  Michael I. Jordan,et al.  On Spectral Clustering: Analysis and an algorithm , 2001, NIPS.

[34]  A. Walter,et al.  Plant phenotyping: from bean weighing to image analysis , 2015, Plant Methods.

[35]  Jean Dauzat,et al.  Using virtual plants to analyse the light-foraging efficiency of a low-density cotton crop. , 2007, Annals of botany.

[36]  Yonghuai Liu,et al.  A Cost-Effective Automatic 3D Reconstruction Pipeline for Plants Using Multi-view Images , 2014, TAROS.