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

Abstract

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.

Combination of an Automated 3D Field Phenotyping Workflow and Predictive Modelling for High-Throughput and Non-Invasive Phenotyping of Grape Bunches

“…Liu and Whitty [67] and Pérez-Zavala et al [68] were able to detect grape bunches by 2D image analysis [70,71]. In a recent study, Di Gennaro et al [72] used images from a UAV to detect bunches from RGB-images. Based on their detection method, they could predict yield on the vines with R2 = 0.82 [72].…”

“…In a recent study, Di Gennaro et al [72] used images from a UAV to detect bunches from RGB-images. Based on their detection method, they could predict yield on the vines with R2 = 0.82 [72]. Another possibility for 3D based phenotyping would be the use of another sensor system that would allow a wider range and a faster data acquisition.…”

Sentinel-2 Validation for Spatial Variability Assessment in Overhead Trellis System Viticulture Versus UAV and Agronomic Data

“…It is undeniable that the factor that has exponentially encouraged the spread of UAV application in agriculture is the continuous advance in sensor technologies, providing higher resolution, lower weight and dimensions, and cost reduction [23,[25][26][27][28]. Several authors describe a wide range of UAV applications for PV purposes: vigor and biomass [29][30][31][32][33][34], yield and quality monitoring [35,36], water stress [37][38][39][40][41], canopy management [42], diseases [43][44][45][46], weeds [47][48][49], and missing plants [50][51][52][53].…”

GBCNet: In-Field Grape Berries Counting for Yield Estimation by Dilated CNNs

“…An example is the use of small sophisticated tools [5][6][7] or even portable generic cameras [8,9], mounted on tractors or robots for in-field image acquisition, or the use of remote sensing imagery [10]. An even better and more appealing opportunity for farmers is to employ the smartphone [11][12][13][14] they already have and use in their daily activities. This simplified approach can overcome the current procedure based on destructive sampling (cutting off and weighting a collection of grape bunches) to obtain a yield estimate, as proposed in a rich line of research initiated by Nuske and colleagues in [15,16], that can help in increasing their productivity, even if sometimes specific setups are required [17].…”