A Non-Invasive Method Based on Computer Vision for Grapevine Cluster Compactness Assessment Using a Mobile Sensing Platform under Field Conditions

Grapevine cluster compactness affects grape composition, fungal disease incidence, and wine quality. Thus far, cluster compactness assessment has been based on visual inspection performed by trained evaluators with very scarce application in the wine industry. The goal of this work was to develop a new, non-invasive method based on the combination of computer vision and machine learning technology for cluster compactness assessment under field conditions from on-the-go red, green, blue (RGB) image acquisition. A mobile sensing platform was used to automatically capture RGB images of grapevine canopies and fruiting zones at night using artificial illumination. Likewise, a set of 195 clusters of four red grapevine varieties of three commercial vineyards were photographed during several years one week prior to harvest. After image acquisition, cluster compactness was evaluated by a group of 15 experts in the laboratory following the International Organization of Vine and Wine (OIV) 204 standard as a reference method. The developed algorithm comprises several steps, including an initial, semi-supervised image segmentation, followed by automated cluster detection and automated compactness estimation using a Gaussian process regression model. Calibration (95 clusters were used as a training set and 100 clusters as the test set) and leave-one-out cross-validation models (LOOCV; performed on the whole 195 clusters set) were elaborated. For these, determination coefficient (R2) of 0.68 and a root mean squared error (RMSE) of 0.96 were obtained on the test set between the image-based compactness estimated values and the average of the evaluators’ ratings (in the range from 1–9). Additionally, the leave-one-out cross-validation yielded a R2 of 0.70 and an RMSE of 1.11. The results show that the newly developed computer vision based method could be commercially applied by the wine industry for efficient cluster compactness estimation from RGB on-the-go image acquisition platforms in commercial vineyards.

[1]  Javier Ibáñez,et al.  Multicultivar and multivariate study of the natural variation for grapevine bunch compactness , 2015 .

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

[3]  José Blasco,et al.  A new method for assessment of bunch compactness using automated image analysis , 2015 .

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

[5]  M. J. Bukovac,et al.  Effect of CPPU on Fruit Development of Selected Seedless and Seeded Grape Cultivars , 2006 .

[6]  Daniel Cremers,et al.  Automatic image‐based determination of pruning mass as a determinant for yield potential in grapevine management and breeding , 2017 .

[7]  L. Hoffmann,et al.  Efficiency of different strategies for the control of grey mold on grapes including gibberellic acid (Gibb3), leaf removal and/or botrycide treatments , 2010 .

[8]  Christopher Hunt,et al.  Notes on the OpenSURF Library , 2009 .

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

[10]  A. Dobson.  An introduction to generalized linear models , 1990 .

[11]  Xiangjun Zou,et al.  Vision-based extraction of spatial information in grape clusters for harvesting robots , 2016 .

[12]  Xiong Chen,et al.  A vision methodology for harvesting robot to detect cutting points on peduncles of double overlapping grape clusters in a vineyard , 2018, Comput. Ind..

[13]  Xiaojing Chen,et al.  New approach of simultaneous, multi‐perspective imaging for quantitative assessment of the compactness of grape bunches , 2018 .

[14]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[15]  Gabriela Csurka,et al.  Visual categorization with bags of keypoints , 2002, eccv 2004.

[16]  L. Hoffmann,et al.  Research note: benefits and drawbacks of pre-bloom applications of gibberellic acid (GA3) for stem elongation in Sauvignon blanc. , 2016 .

[17]  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..

[18]  A. Aquino,et al.  On‐the‐go assessment of vineyard canopy porosity, bunch and leaf exposure by image analysis , 2019, Australian Journal of Grape and Wine Research.

[19]  Santiago Velasco-Forero,et al.  On-the-Go Grapevine Yield Estimation Using Image Analysis and Boolean Model , 2018, J. Sensors.

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

[21]  J. Marois,et al.  Grape cluster architecture and the susceptibility of berries to Botrytis cinerea , 1991 .

[22]  Paul R. Petrie,et al.  A robust automated flower estimation system for grape vines , 2018, Biosystems Engineering.

[23]  Javier Tardáguila,et al.  Assessment of Vineyard Canopy Porosity Using Machine Vision , 2016, American Journal of Enology and Viticulture.

[24]  W. Wilcox,et al.  Effects of sunlight exposure on grapevine powdery mildew development. , 2012, Phytopathology.

[25]  Javier Tardáguila,et al.  Vineyard pruning weight assessment by machine vision: towards an on-the-go measurement system , 2019, OENO One.

[26]  Andrew P. Bradley,et al.  The use of the area under the ROC curve in the evaluation of machine learning algorithms , 1997, Pattern Recognit..

[27]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

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

[29]  S. Poni,et al.  Early Leaf Removal to Improve Vineyard Efficiency: Gas Exchange, Source-to-Sink Balance, and Reserve Storage Responses , 2011, American Journal of Enology and Viticulture.

[30]  Bryan Hed,et al.  Relationship Between Cluster Compactness and Bunch Rot in Vignoles Grapes. , 2009, Plant disease.

[31]  Donald R. Jones,et al.  A Taxonomy of Global Optimization Methods Based on Response Surfaces , 2001, J. Glob. Optim..