A Low-Cost and Unsupervised Image Recognition Methodology for Yield Estimation in a Vineyard

Yield prediction is a key factor to optimize vineyard management and achieve the desired grape quality. Classical yield estimation methods, which consist of manual sampling within the field on a limited number of plants before harvest, are time-consuming and frequently insufficient to obtain representative yield data. Non-invasive machine vision methods are therefore being investigated to assess and implement a rapid grape yield estimate tool. This study aimed at an automated estimation of yield in terms of cluster number and size from high resolution RGB images (20 MP) taken with a low-cost UAV platform in representative zones of the vigor variability within an experimental vineyard. The flight campaigns were conducted in different light conditions and canopy cover levels for 2017 and 2018 crop seasons. An unsupervised recognition algorithm was applied to derive cluster number and size, which was used for estimating yield per vine. The results related to the number of clusters detected in different conditions, and the weight estimation for each vigor zone are presented. The segmentation results in cluster detection showed a performance of over 85% in partially leaf removal and full ripe condition, and allowed grapevine yield to be estimated with more than 84% of accuracy several weeks before harvest. The application of innovative technologies in field-phenotyping such as UAV, high-resolution cameras and visual computing algorithms enabled a new methodology to assess yield, which can save time and provide an accurate estimate compared to the manual method.

[1]  W. Cynkar,et al.  Comparison of extraction protocols to determine differences in wine-extractable tannin and anthocyanin in Vitis vinifera L. cv. Shiraz and Cabernet Sauvignon grapes. , 2014, Journal of agricultural and food chemistry.

[2]  Andrea Berton,et al.  Assessment of a canopy height model (CHM) in a vineyard using UAV-based multispectral imaging , 2017 .

[3]  L. S. Pereira,et al.  Estimation of Actual Crop Coefficients Using Remotely Sensed Vegetation Indices and Soil Water Balance Modelled Data , 2015, Remote. Sens..

[4]  Cristina Portalés,et al.  An image-based system to preliminary assess the quality of grape harvest batches on arrival at the winery , 2015, Comput. Ind..

[5]  María-Paz Diago,et al.  Automated early yield prediction in vineyards from on-the-go image acquisition , 2018, Comput. Electron. Agric..

[6]  José Blasco,et al.  Assessment of flower number per inflorescence in grapevine by image analysis under field conditions. , 2014, Journal of the science of food and agriculture.

[7]  P. Pieri,et al.  EFFECTS OF DEFOLIATION ON TEMPERATURE AND WETNESS OF GRAPEVINE BERRIES , 2005 .

[8]  J. Gómez-Sanchís,et al.  Advances in Machine Vision Applications for Automatic Inspection and Quality Evaluation of Fruits and Vegetables , 2011 .

[9]  J. Kennedy,et al.  Direct method for determining seed and skin proanthocyanidin extraction into red wine. , 2003, Journal of agricultural and food chemistry.

[10]  José M. Martínez-Zapater,et al.  A genetic analysis of seed and berry weight in grapevine , 2006 .

[11]  Stephen Nuske,et al.  Automated Assessment and Mapping of Grape Quality through Image-based Color Analysis , 2016 .

[12]  Alessandro Matese,et al.  Airborne high‐resolution images for grape classification: changes in correlation between technological and late maturity in a Sangiovese vineyard in Central Italy , 2012 .

[13]  Mahmoud Omid,et al.  Egg volume prediction using machine vision technique based on pappus theorem and artificial neural network , 2015, Journal of Food Science and Technology.

[14]  Javier Tardáguila,et al.  A new methodology for estimating the grapevine-berry number per cluster using image analysis , 2017 .

[15]  Da-Wen Sun,et al.  Shape Analysis of Agricultural Products: A Review of Recent Research Advances and Potential Application to Computer Vision , 2011 .

[16]  J. A. Schell,et al.  Monitoring vegetation systems in the great plains with ERTS , 1973 .

[17]  Xihan Mu,et al.  A novel method for extracting green fractional vegetation cover from digital images , 2012 .

[18]  Sile Wang,et al.  Greenness identification based on HSV decision tree , 2015 .

[19]  Andrea Cavallaro,et al.  Sensor Capability and Atmospheric Correction in Ocean Colour Remote Sensing , 2015, Remote. Sens..

[20]  J. Schellberg,et al.  Identification of broad-leaved dock (Rumex obtusifolius L.) on grassland by means of digital image processing , 2006, Precision Agriculture.

[21]  Ribana Roscher,et al.  Image based evaluation for the detection of cluster parameters in grapevine , 2015 .

[22]  Hong Sun,et al.  Potato feature prediction based on machine vision and 3D model rebuilding , 2017, Comput. Electron. Agric..

[23]  J. Flexas,et al.  UAVs challenge to assess water stress for sustainable agriculture , 2015 .

[24]  Nuria Aleixos,et al.  Erratum to: Advances in Machine Vision Applications for Automatic Inspection and Quality Evaluation of Fruits and Vegetables , 2011 .

[25]  Javier Ibáñez,et al.  Evaluation of indexes for the quantitative and objective estimation of grapevine bunch compactness , 2013 .

[26]  G. Dunn,et al.  Yield prediction from digital image analysis: A technique with potential for vineyard assessments prior to harvest , 2008 .

[27]  M. Cervera,et al.  A genetic analysis of seed and berry weight in grapevine. , 2009, Genome.

[28]  Maria Stella Grando,et al.  Berry and phenology-related traits in grapevine (Vitis vinifera L.): From Quantitative Trait Loci to underlying genes , 2008, BMC Plant Biology.

[29]  Daoliang Li,et al.  The Measurement of Fish Size by Machine Vision - A Review , 2015, CCTA.

[30]  Martin Fowler,et al.  The new methodology , 2001, Wuhan University Journal of Natural Sciences.

[31]  C. Steel,et al.  The Basis of Defoliation Effects on Reproductive Parameters in Vitis vinifera L. cv. Chardonnay Lies in the Latent Bud , 2016, American Journal of Enology and Viticulture.

[32]  V. Freitas,et al.  Influence of the heterogeneity of grape phenolic maturity on wine composition and quality , 2011 .

[33]  Nuria Aleixos,et al.  Assessment of cluster yield components by image analysis. , 2015, Journal of the science of food and agriculture.

[34]  L. G. Santesteban,et al.  High-resolution UAV-based thermal imaging to estimate the instantaneous and seasonal variability of plant water status within a vineyard , 2017 .

[35]  Hossein Pourghassem,et al.  Computer vision-based apple grading for golden delicious apples based on surface features , 2017 .

[36]  Alex. B. McBratney,et al.  A Parametric Transfer Function for Grain-Flow Within a Conventional Combine Harvester , 2002, Precision Agriculture.

[37]  Piero Toscano,et al.  Intercomparison of UAV, Aircraft and Satellite Remote Sensing Platforms for Precision Viticulture , 2015, Remote. Sens..

[38]  A. Reynolds,et al.  Influence of cluster exposure on fruit composition and wine quality of seyval blanc grapes , 2015 .

[39]  Y. Cohen,et al.  Use of aerial thermal imaging to estimate water status of palm trees , 2011, Precision Agriculture.

[40]  Brian L. Steward,et al.  Video Processing for Early Stage Maize Plant Detection , 2004 .

[41]  Borja Millán,et al.  Grapevine flower estimation by applying artificial vision techniques on images with uncontrolled scene and multi-model analysis , 2015, Comput. Electron. Agric..

[42]  G. Fanizza,et al.  QTL analysis for fruit yield components in table grapes (Vitis vinifera) , 2005, Theoretical and Applied Genetics.

[43]  Christian Germain,et al.  Transformation of high resolution aerial images in vine vigour maps at intra-block scale by semi automatic image processing , 2007 .

[44]  W. Batchelor,et al.  Shape identification and particles size distribution from basic shape parameters using ImageJ , 2008 .

[45]  L. Genesio,et al.  Vine vigour modulates bunch microclimate and affects the composition of grape and wine flavonoids: an unmanned aerial vehicle approach in a Sangiovese vineyard in Tuscany , 2017 .

[46]  G. S. Howell,et al.  Effects of Early Defoliation on Yield, Fruit Composition, and Harvest Season Cluster Rot Complex of , 2010 .

[47]  Ribana Roscher,et al.  BAT (Berry Analysis Tool): A high-throughput image interpretation tool to acquire the number, diameter, and volume of grapevine berries , 2013 .

[48]  Pablo J. Zarco-Tejada,et al.  Airborne Thermal Imagery to Detect the Seasonal Evolution of Crop Water Status in Peach, Nectarine and Saturn Peach Orchards , 2016, Remote. Sens..

[49]  María-Paz Diago,et al.  Grapevine Yield and Leaf Area Estimation Using Supervised Classification Methodology on RGB Images Taken under Field Conditions , 2012, Sensors.

[50]  Stefano Poni,et al.  Mechanical yield regulation in winegrapes: comparison of early defoliation and crop thinning , 2012 .

[51]  José Blasco,et al.  Application of 2D and 3D image technologies to characterise morphological attributes of grapevine clusters. , 2016, Journal of the science of food and agriculture.

[52]  N. Dokoozlian,et al.  Sunlight Exposure and Temperature Effects on Berry Growth and Composition of Cabernet Sauvignon and Grenache in the Central San Joaquin Valley of California , 2001, American Journal of Enology and Viticulture.

[53]  Matthew Bardeen,et al.  Detection and Segmentation of Vine Canopy in Ultra-High Spatial Resolution RGB Imagery Obtained from Unmanned Aerial Vehicle (UAV): A Case Study in a Commercial Vineyard , 2017, Remote. Sens..

[54]  Eugenio Ivorra,et al.  Assessment of grape cluster yield components based on 3D descriptors using stereo vision , 2015 .

[55]  Ribana Roscher,et al.  Automated Image Analysis Framework for the High-Throughput Determination of Grapevine Berry Sizes Using Conditional Random Fields , 2017, ArXiv.

[56]  Sanjiv Singh,et al.  Yield estimation in vineyards by visual grape detection , 2011, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[57]  P. P. Ling,et al.  Machine vision techniques for measuring the canopy of tomato seedling , 1996 .

[58]  S. F. D. Gennaro,et al.  Unmanned Aerial Vehicle (UAV)-based remote sensing to monitor grapevine leaf stripe disease within a vineyard affected by esca complex , 2016 .

[59]  John R. Clark,et al.  Fruit Shape Analysis of Vitis Using Digital Photography , 2008 .

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

[61]  YangQuan Chen,et al.  Melon yield prediction using small unmanned aerial vehicles , 2017, Commercial + Scientific Sensing and Imaging.

[62]  José Blasco,et al.  A new method for pedicel/peduncle detection and size assessment of grapevine berries and other fruits by image analysis , 2014 .

[63]  J. Valls,et al.  Influence of ethanol concentration on the extraction of color and phenolic compounds from the skin and seeds of Tempranillo grapes at different stages of ripening. , 2005, Journal of agricultural and food chemistry.

[64]  Ribana Roscher,et al.  Initial steps for high-throughput phenotyping in vineyards , 2014 .

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

[66]  Mark Krstic,et al.  Cultural Practice and Environmental Impacts on the Flavonoid Composition of Grapes and Wine: A Review of Recent Research , 2006, American Journal of Enology and Viticulture.

[67]  Dah-Jye Lee,et al.  Automatic shrimp shape grading using evolution constructed features , 2014 .

[68]  Sanjiv Singh,et al.  Automated Visual Yield Estimation in Vineyards , 2014, J. Field Robotics.

[69]  Qian Du,et al.  Graph-Regularized Fast and Robust Principal Component Analysis for Hyperspectral Band Selection , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[70]  Supreeth Achar,et al.  A Camera and Laser System for Automatic Vine Balance Assessment , 2011 .

[71]  Guangjian Yan,et al.  Extracting the Green Fractional Vegetation Cover from Digital Images Using a Shadow-Resistant Algorithm (SHAR-LABFVC) , 2015, Remote. Sens..

[72]  Alessandro Matese,et al.  Practical Applications of a Multisensor UAV Platform Based on Multispectral, Thermal and RGB High Resolution Images in Precision Viticulture , 2018, Agriculture.