Automatic wheat ear counting using machine learning based on RGB UAV imagery.

In wheat and other cereals, the number of ears per unit area is one of the main yield determining components. An automatic evaluation of this parameter may contribute to the advance of wheat phenotyping and monitoring. There is no standard protocol for wheat ear counting in the field, and moreover it is time-consuming. An automatic ear counting system is proposed using machine learning techniques based on RGB images acquired from an unmanned aerial vehicle (UAV). Evaluation was performed on a set of 12 winter wheat cultivars with 3 nitrogen treatments during the 2017-2018 crop season. The automatic system uses a frequency filter, segmentation, and feature extraction with different classification techniques to discriminate wheat ears in micro-plot images. The relationship between the image-based manual counting and the algorithm counting exhibited high accuracy and efficiency. In addition, manual ear counting was conducted in the field for secondary validation. The correlations between the automatic and the manual in-situ ear counting with grain yield were also compared. Correlations between both ear counting systems were strong, particularly for the lower N treatment. Methodological requirements and limitations are discussed.

[1]  F. Baret,et al.  High-Throughput Measurements of Stem Characteristics to Estimate Ear Density and Above-Ground Biomass , 2019, Plant phenomics.

[2]  Jose Armando Fernandez-Gallego,et al.  UAV and Ground Image-Based Phenotyping: A Proof of Concept with Durum Wheat , 2019, Remote. Sens..

[3]  J. Araus,et al.  Low-cost assessment of grain yield in durum wheat using RGB images , 2019, European Journal of Agronomy.

[4]  Jose Armando Fernandez-Gallego,et al.  Automatic Wheat Ear Counting Using Thermal Imagery , 2019, Remote. Sens..

[5]  Ma. Luisa Buchaillot,et al.  Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images. , 2019, Journal of visualized experiments : JoVE.

[6]  Frédéric Baret,et al.  Ear density estimation from high resolution RGB imagery using deep learning technique , 2019, Agricultural and Forest Meteorology.

[7]  Christophe Delacourt,et al.  Suggestions to Limit Geometric Distortions in the Reconstruction of Linear Coastal Landforms by SfM Photogrammetry with PhotoScan® and MicMac® for UAV Surveys with Restricted GCPs Pattern , 2018, Drones.

[8]  Shawn C. Kefauver,et al.  Automatic wheat ear counting in-field conditions: simulation and implication of lower resolution images , 2018, Remote Sensing.

[9]  J. Araus,et al.  Breeding to adapt agriculture to climate change: affordable phenotyping solutions. , 2018, Current opinion in plant biology.

[10]  Dewa Made Sri Arsa,et al.  Multicodebook Neural Network Using Intelligent K-Means Clustering Based on Histogram Information for Multimodal Data Classification , 2018, 2018 International Workshop on Big Data and Information Security (IWBIS).

[11]  Dong Liang,et al.  Wheat Ears Counting in Field Conditions Based on Multi-Feature Optimization and TWSVM , 2018, Front. Plant Sci..

[12]  Eija Honkavaara,et al.  Quantitative Remote Sensing at Ultra-High Resolution with UAV Spectroscopy: A Review of Sensor Technology, Measurement Procedures, and Data Correction Workflows , 2018, Remote. Sens..

[13]  Jordi Bort,et al.  Challenges and Bottlenecks in VAV Phenotyping , 2018, IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium.

[14]  M. Zaman-Allah,et al.  Translating High-Throughput Phenotyping into Genetic Gain , 2018, Trends in plant science.

[15]  Hong Sun,et al.  Sensors for measuring plant phenotyping: A review , 2018 .

[16]  J. Araus,et al.  Wheat ear counting in-field conditions: high throughput and low-cost approach using RGB images , 2018, Plant Methods.

[17]  Dong Liang,et al.  Recognition of Wheat Spike from Field Based Phenotype Platform Using Multi-Sensor Fusion and Improved Maximum Entropy Segmentation Algorithms , 2018, Remote. Sens..

[18]  David Hernández-López,et al.  Automatic Hotspot and Sun Glint Detection in UAV Multispectral Images , 2017, Sensors.

[19]  Frédéric Baret,et al.  Wheat ear detection in plots by segmenting mobile laser scanning data , 2017 .

[20]  Ujjwal Maulik,et al.  Remote Sensing Image Classification: A survey of support-vector-machine-based advanced techniques , 2017, IEEE Geoscience and Remote Sensing Magazine.

[21]  Pouria Sadeghi-Tehran,et al.  Automated Method to Determine Two Critical Growth Stages of Wheat: Heading and Flowering , 2017, Front. Plant Sci..

[22]  Shawn M. Kaeppler,et al.  A robust, high‐throughput method for computing maize ear, cob, and kernel attributes automatically from images , 2017, The Plant journal : for cell and molecular biology.

[23]  Mariana Belgiu,et al.  Random forest in remote sensing: A review of applications and future directions , 2016 .

[24]  Zhiguo Cao,et al.  In-field automatic observation of wheat heading stage using computer vision , 2016 .

[25]  D. Inzé,et al.  The Future of Field Trials in Europe: Establishing a Network Beyond Boundaries. , 2016, Trends in plant science.

[26]  Ashutosh Kumar Singh,et al.  Machine Learning for High-Throughput Stress Phenotyping in Plants. , 2016, Trends in plant science.

[27]  Sandra Lowe,et al.  Classification Methods For Remotely Sensed Data , 2016 .

[28]  Toni Kazic,et al.  An opinion on imaging challenges in phenotyping field crops , 2015, Machine Vision and Applications.

[29]  Jiangye Yuan,et al.  Image feature based GPS trace filtering for road network generation and road segmentation , 2015, Machine Vision and Applications.

[30]  Hanno Scharr,et al.  Image Analysis: The New Bottleneck in Plant Phenotyping [Applications Corner] , 2015, IEEE Signal Processing Magazine.

[31]  Martino Pesaresi,et al.  Image Enhancement and Feature Extraction Based on Low-Resolution Satellite Data , 2015, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[32]  S. Tripathy,et al.  A Survey of different methods of clustering for anomaly detection , 2015 .

[33]  Jose A. Jiménez-Berni,et al.  Proximal Remote Sensing Buggies and Potential Applications for Field-Based Phenotyping , 2014 .

[34]  Gustavo A. Slafer,et al.  Coarse and fine regulation of wheat yield components in response to genotype and environment , 2014 .

[35]  J. Araus,et al.  Field high-throughput phenotyping: the new crop breeding frontier. , 2014, Trends in plant science.

[36]  Kevin W Eliceiri,et al.  NIH Image to ImageJ: 25 years of image analysis , 2012, Nature Methods.

[37]  Wenzhong Shi,et al.  A fuzzy topology-based maximum likelihood classification , 2011 .

[38]  F. Cointault,et al.  In‐field Triticum aestivum ear counting using colour‐texture image analysis , 2008 .

[39]  P. Gong,et al.  Isolating individual trees in a savanna woodland using small footprint lidar data , 2006 .

[40]  J. Greenberg,et al.  Shadow allometry: Estimating tree structural parameters using hyperspatial image analysis , 2005 .

[41]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[42]  P. Struik,et al.  Ontogenetic analysis of yield components and yield stability of durum wheat in water-limited environments , 2004, Euphytica.

[43]  Dolors Villegas,et al.  Evaluation of Grain Yield and Its Components in Durum Wheat under Mediterranean Conditions , 2003 .

[44]  Eric R. Ziegel,et al.  An Introduction to Generalized Linear Models , 2002, Technometrics.

[45]  Douglas J. King,et al.  Automated tree crown detection and delineation in high-resolution digital camera imagery of coniferous forest regeneration , 2002 .

[46]  Nello Cristianini,et al.  Support Vector Machines and Kernel Methods: The New Generation of Learning Machines , 2002, AI Mag..

[47]  K. O. Niemann,et al.  Local Maximum Filtering for the Extraction of Tree Locations and Basal Area from High Spatial Resolution Imagery , 2000 .

[48]  Ron Kohavi,et al.  Wrappers for Feature Subset Selection , 1997, Artif. Intell..

[49]  J. Power,et al.  Tiller development and yield of standard and semidwarf spring wheat varieties as affected by nitrogen fertilizer , 1978, The Journal of Agricultural Science.

[50]  J. Zadoks.  A decimal code for the growth stages of cereals , 1974 .

[51]  H. M. Ishag,et al.  Production and survival of tillers of wheat and their contribution to yield , 1974, Journal of Agricultural Sciences.

[52]  G. Box,et al.  A general distribution theory for a class of likelihood criteria. , 1949, Biometrika.