A Ground-based Platform for Reliable Estimates of Fruit Number, Size, and Color in Stone Fruit Orchards

Abstract

Automatic in-field fruit recognition techniques can be used to estimate fruit number, fruit size, fruit skin color, and yield in fruit crops. Fruit color and size represent two of the most important fruit quality parameters in stone fruit (Prunus sp.). This study aimed to evaluate the reliability of a commercial mobile platform, sensors, and artificial intelligence software system for fast estimates of fruit number, fruit size, and fruit skin color in peach (Prunus persica), nectarine (P. persica var. nucipersica), plum (Prunus salicina), and apricot (Prunus armeniaca), and to assess their spatial and temporal variability. An initial calibration was needed to obtain estimates of absolute fruit number per tree and a forecasted yield. However, the technology can also be used to produce fast relative density maps in stone fruit orchards. Fruit number prediction accuracy was ≥90% in all the crops and training systems under study. Overall, predictions of fruit number in two-dimensional training systems were slightly more accurate. Estimates of fruit diameter (FD) and color did not need an initial calibration. The FD predictions had percent standard errors <10% and root mean square error <5 mm under different training systems, row spacing, crops, and fruit position within the canopy. Hue angle, a color attribute previously associated with fruit maturity in peach and nectarine, was the color attribute that was best predicted by the mobile platform. A new color parameter—color development index (CDI), ranging from 0 to 1—was derived from hue angle. The adoption of CDI, which represents the color progression or distance from green, improved the interpretation of color measurements by end-users as opposed to hue angle and generated more robust color estimations in fruit that turn purple when ripe, such as dark plum. Spatial maps of fruit number, FD, and CDI obtained with the mobile platform can be used to inform orchard decisions such as thinning, pruning, spraying, and harvest timing. The importance and application of crop yield and fruit quality real-time assessments and forecasts are discussed.

A Fruit Colour Development Index (CDI) to Support Harvest Time Decisions in Peach and Nectarine Orchards

“…Images are segmented and fruit detected with a proprietary Green Atlas machine learning algorithm that produces estimations of fruit number per image, and detection boxes are automatically generated around detected fruit in each image. Fruit detections had overall low prediction errors, although a slightly better performance was obtained in peach (% standard errors = 4.5%) compared to nectarine (% standard error = 7.4%), in line with Islam et al [13], as the former was trained on 2D trellises and fruit was more visible.…”

“…Green Atlas attempts to limit the external light effect by simultaneously flashing the canopies with strobe lights while collecting images so that image brightness is relatively standardised. Although Cartographer has been validated and used for measurements of fruit number, fruit colour and size in peach and nectarine cultivars [13], the consistency of fruit colour measurements in different light environments or time of the day, and the relationship between fruit colour and ripeness or harvest time need to be investigated to determine if scanning the orchards can provide a valuable tool to plan harvest time based on objective fruit colour thresholds. This work aimed to (i) derive a fruit skin colour development index (CDI, ranging from 0 to 1) that can be easily calculated from hue angle data-a CIELab colour attribute that was successfully related to harvest time and maturity in stone fruit [3][4][5][6][7][8] using a fast-scanning mobile platform; (ii) determine the temporal variability of CDI readings when measurements are collected at different times of the day thereby providing changing light environments on different sides of the canopy; and (iii) test the relationship between the CDI and a conventional fruit maturity index used in peach and nectarine.…”

A Data Ecosystem for Orchard Research and Early Fruit Traceability

“…Although all the peripheral ecosystem elements and use cases described in the methodology have been designed, some of the specialised systems and workflows remain in various stages of completion. An example is the full systematisation of workflows for the Green Atlas Cartographer [23]. While these are developed, they have yet to be chained together in an application to completely automate data submission through the API services.…”

Management Information Systems for Tree Fruit–2: Design of a Mango Harvest Forecast Engine

“…The US hazelnut industry provides a (dry) tree-fruit example, with a national crop forecast made by the United States Department of Agriculture (USDA) based on manual counts of two randomly selected trees in each of 180 randomly selected orchards [6]. New tools are also emerging for tree-fruit load estimation, ranging from inorchard machine vision to relationships based on canopy size or vegetation indices obtained from satellite imagery [7,8]. The growing requirement for point of origin traceability also creates a need for electronic databases for harvest data accessed through an information system [9].…”