Greenotyper: Image-Based Plant Phenotyping Using Distributed Computing and Deep Learning

Image-based phenotype data with high temporal resolution offers advantages over end-point measurements in plant quantitative genetics experiments, because growth dynamics can be assessed and analysed for genotype-phenotype association. Recently, network-based camera systems have been deployed as customizable, low-cost phenotyping solutions. Here, we implemented a large, automated image-capture system based on distributed computing using 180 networked Raspberry Pi units that could simultaneously monitor 1,800 white clover (Trifolium repens) plants. The camera system proved stable with an average uptime of 96% across all 180 cameras. For analysis of the captured images, we developed the Greenotyper image analysis pipeline. It detected the location of the plants with a bounding box accuracy of 97.98%, and the U-net-based plant segmentation had an intersection over union accuracy of 0.84 and a pixel accuracy of 0.95. We used Greenotyper to analyze a total of 355,027 images, which required 24–36 h. Automated phenotyping using a large number of static cameras and plants thus proved a cost-effective alternative to systems relying on conveyor belts or mobile cameras.

[1]  W. Philips,et al.  Rosette Tracker: An Open Source Image Analysis Tool for Automatic Quantification of Genotype Effects1[C][W] , 2012, Plant Physiology.

[2]  C. Wang,et al.  Growth and Yield Performance of Some Cotton Cultivars in Xinjiang, China, An Arid Area with Short Growing Period , 2004 .

[3]  Sotirios A. Tsaftaris,et al.  Image-based plant phenotyping with incremental learning and active contours , 2014, Ecol. Informatics.

[4]  N. Dudai,et al.  Dynamics of yield components and stevioside production in Stevia rebaudiana grown under different planting times, plant stands and harvest regime , 2013 .

[5]  Sang Cheol Kim,et al.  A Robust Deep-Learning-Based Detector for Real-Time Tomato Plant Diseases and Pests Recognition , 2017, Sensors.

[6]  Ping Zhang,et al.  Unsupervised Segmentation of Greenhouse Plant Images Based on Statistical Method , 2018, Scientific Reports.

[7]  Satoshi Yoshida,et al.  Growth and yield components of wheat genotypes exposed to high temperature stress under control environment , 2009 .

[8]  Seishi Ninomiya,et al.  EasyPCC: Benchmark Datasets and Tools for High-Throughput Measurement of the Plant Canopy Coverage Ratio under Field Conditions , 2017, Sensors.

[9]  Symbiosis genes show a unique pattern of introgression and selection within a Rhizobium leguminosarum species complex , 2020, Microbial genomics.

[10]  Luc Van Gool,et al.  The Pascal Visual Object Classes (VOC) Challenge , 2010, International Journal of Computer Vision.

[11]  Comparative genomics confirms a rare melioidosis human-to-human transmission event and reveals incorrect phylogenomic reconstruction due to polyclonality , 2020, Microbial genomics.

[12]  O. Loudet,et al.  Phenoscope: an automated large-scale phenotyping platform offering high spatial homogeneity. , 2013, The Plant journal : for cell and molecular biology.

[13]  S. Tsaftaris,et al.  Phenotiki: an open software and hardware platform for affordable and easy image‐based phenotyping of rosette‐shaped plants , 2017, The Plant journal : for cell and molecular biology.

[15]  R. A. Fischer,et al.  Breeding and Cereal Yield Progress , 2010 .

[16]  D. Bates,et al.  Fitting Linear Mixed-Effects Models Using lme4 , 2014, 1406.5823.

[17]  C. Sloger.  Symbiotic effectiveness and n(2) fixation in nodulated soybean. , 1969, Plant physiology.

[18]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[19]  Andy Lin,et al.  PlantCV v2: Image analysis software for high-throughput plant phenotyping , 2017, PeerJ.

[20]  Noah Fahlgren,et al.  Raspberry Pi–powered imaging for plant phenotyping , 2018, Applications in plant sciences.

[21]  V. Guen,et al.  Breeding Hevea brasiliensis for yield, growth and SALB resistance for high disease environments , 2013 .

[22]  Mohammad Najafi,et al.  Deep phenotyping: deep learning for temporal phenotype/genotype classification , 2017, Plant Methods.

[23]  Matthijs Tollenaar,et al.  Physiological Basis of Successful Breeding Strategies for Maize Grain Yield , 2007 .

[24]  Paul D. Blischak,et al.  Affordable remote monitoring of plant growth in facilities using Raspberry Pi computers , 2019, Applications in plant sciences.

[25]  F. T. Turner,et al.  Assessing the nitrogen requirements of rice crops with a chlorophyll meter , 1994 .

[26]  G. Carter,et al.  Leaf optical properties in higher plants: linking spectral characteristics to stress and chlorophyll concentration. , 2001, American journal of botany.

[27]  K. Shinozaki,et al.  RIPPS: A Plant Phenotyping System for Quantitative Evaluation of Growth Under Controlled Environmental Stress Conditions , 2018, Plant & cell physiology.

[28]  Ullrich Köthe,et al.  Ilastik: Interactive learning and segmentation toolkit , 2011, 2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[29]  Virendra Tewari,et al.  Estimation of plant nitrogen content using digital image processing , 2013 .

[30]  Marian Wiwart,et al.  Early diagnostics of macronutrient deficiencies in three legume species by color image analysis , 2009 .

[31]  Dong Hwan Kim,et al.  An automated, high-throughput plant phenotyping system using machine learning-based plant segmentation and image analysis , 2018, PloS one.

[32]  Rachael L. Ashby,et al.  Breaking Free: The Genomics of Allopolyploidy-Facilitated Niche Expansion in White Clover[OPEN] , 2019, Plant Cell.

[33]  Noor M. Al-Shakarji,et al.  Unsupervised Learning Method for Plant and Leaf Segmentation , 2017, 2017 IEEE Applied Imagery Pattern Recognition Workshop (AIPR).

[34]  Shang Gao,et al.  Deep Learning: Individual Maize Segmentation From Terrestrial Lidar Data Using Faster R-CNN and Regional Growth Algorithms , 2018, Front. Plant Sci..

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

[36]  David Reiser,et al.  Robust index-based semantic plant/background segmentation for RGB- images , 2020, Comput. Electron. Agric..