Agronomy

Editorial

Jump to: Research, Review, Other

3 pages, 430 KiB

Open AccessEditorial

In-Field Estimation of Fruit Quality and Quantity

by Kerry B. Walsh

Agronomy 2022, 12(5), 1074; https://doi.org/10.3390/agronomy12051074 - 29 Apr 2022

Cited by 2 | Viewed by 1558

Abstract

Every new tool gives humankind a new capability or capabilities, as a new tool finds a range of applications [...] Full article

(This article belongs to the Special Issue In-Field Estimation of Fruit Quality and Quantity)

► Show Figures

Figure 1

Research

Jump to: Editorial, Review, Other

20 pages, 17048 KiB

Open AccessEditor’s ChoiceArticle

Estimation of Fruit Load in Australian Mango Orchards Using Machine Vision

by Nicholas Todd Anderson, Kerry Brian Walsh, Anand Koirala, Zhenglin Wang, Marcelo Henrique Amaral, Geoff Robert Dickinson, Priyakant Sinha and Andrew James Robson

Agronomy 2021, 11(9), 1711; https://doi.org/10.3390/agronomy11091711 - 27 Aug 2021

Cited by 23 | Viewed by 4549

Abstract

The performance of a multi-view machine vision method was documented at an orchard level, relative to packhouse count. High repeatability was achieved in night-time imaging, with an absolute percentage error of 2% or less. Canopy architecture impacted performance, with reasonable estimates achieved on [...] Read more.

The performance of a multi-view machine vision method was documented at an orchard level, relative to packhouse count. High repeatability was achieved in night-time imaging, with an absolute percentage error of 2% or less. Canopy architecture impacted performance, with reasonable estimates achieved on hedge, single leader and conventional systems (3.4, 5.0, and 8.2 average percentage error, respectively) while fruit load of trellised orchards was over-estimated (at 25.2 average percentage error). Yield estimations were made for multiple orchards via: (i) human count of fruit load on ~5% of trees (FARM), (ii) human count of 18 trees randomly selected within three NDVI stratifications (CAL), (iii) multi-view counts (MV-Raw) and (iv) multi-view corrected for occluded fruit using manual counts of CAL trees (MV-CAL). Across the nine orchards for which results for all methods were available, the FARM, CAL, MV-Raw and MV-CAL methods achieved an average percentage error on packhouse counts of 26, 13, 11 and 17%, with SD of 11, 8, 11 and 9%, respectively, in the 2019–2020 season. The absolute percentage error of the MV-Raw estimates was 10% or less in 15 of the 20 orchards assessed. Greater error in load estimation occurred in the 2020–2021 season due to the time-spread of flowering. Use cases for the tree level data on fruit load was explored in context of fruit load density maps to inform early harvesting and to interpret crop damage, and tree frequency distributions based on fruit load per tree. Full article

(This article belongs to the Special Issue In-Field Estimation of Fruit Quality and Quantity)

► Show Figures

Figure 1

20 pages, 10787 KiB

Open AccessEditor’s ChoiceArticle

Attempting to Estimate the Unseen—Correction for Occluded Fruit in Tree Fruit Load Estimation by Machine Vision with Deep Learning

by Anand Koirala, Kerry B. Walsh and Zhenglin Wang

Agronomy 2021, 11(2), 347; https://doi.org/10.3390/agronomy11020347 - 15 Feb 2021

Cited by 26 | Viewed by 4106

Abstract

Machine vision from ground vehicles is being used for estimation of fruit load on trees, but a correction is required for occlusion by foliage or other fruits. This requires a manually estimated factor (the reference method). It was hypothesised that canopy images could [...] Read more.

Machine vision from ground vehicles is being used for estimation of fruit load on trees, but a correction is required for occlusion by foliage or other fruits. This requires a manually estimated factor (the reference method). It was hypothesised that canopy images could hold information related to the number of occluded fruits. Several image features, such as the proportion of fruit that were partly occluded, were used in training Random forest and multi-layered perceptron (MLP) models for estimation of a correction factor per tree. In another approach, deep learning convolutional neural networks (CNNs) were directly trained against harvest count of fruit per tree. A R2 of 0.98 (n = 98 trees) was achieved for the correlation of fruit count predicted by a Random forest model and the ground truth fruit count, compared to a R² of 0.68 for the reference method. Error on prediction of whole orchard (880 trees) fruit load compared to packhouse count was 1.6% for the MLP model and 13.6% for the reference method. However, the performance of these models on data of another season was at best equivalent and generally poorer than the reference method. This result indicates that training on one season of data was insufficient for the development of a robust model. Full article

(This article belongs to the Special Issue In-Field Estimation of Fruit Quality and Quantity)

► Show Figures

Figure 1

23 pages, 2848 KiB

Open AccessArticle

Manipulation of Fruit Dry Matter via Seasonal Pruning and Its Relationship to d’Anjou Pear Yield and Fruit Quality

by Alex Goke, Sara Serra and Stefano Musacchi

Agronomy 2020, 10(6), 897; https://doi.org/10.3390/agronomy10060897 - 24 Jun 2020

Cited by 9 | Viewed by 3975

Abstract

Orchard-side optimization of fruit quality is experiencing renewed research focus in the fresh fruit industry as new technologies and quality metrics have emerged to enhance consumer acceptance and satisfaction. Fruit dry matter, one such quality index gaining traction among numerous fresh fruit commodities, [...] Read more.

Orchard-side optimization of fruit quality is experiencing renewed research focus in the fresh fruit industry as new technologies and quality metrics have emerged to enhance consumer acceptance and satisfaction. Fruit dry matter, one such quality index gaining traction among numerous fresh fruit commodities, was targeted for improvement in d’Anjou pear with the application of seasonal pruning cycles (fall, fall and summer, winter, and winter and summer) across two growing seasons in 2016 and 2017 in a mid-aged, traditionally managed commercial orchard in the Columbia basin, Washington, USA. Dry matter was assessed non-destructively on pears using near-infrared spectroscopy at harvest and fruit categorized in to low (<13%), moderate (13–16%), and high (>16%) dry matter quality categories, revealing that fall pruning positively impacted average predicted fruit dry matter in comparison to winter pruning (15.1 vs. 14.2% in 2016 and 13.7 vs. 13.1% predicted dry matter in 2017 for winter vs. fall pruning, respectively), as well in the abundance of high dry matter fruits. The addition of summer pruning to either fall or winter pruning increased fruit size by up to 13% of proportion of fruits 80 mm or greater in diameter. Further, a tendency for summer pruning to decrease yield (up to nearly 30 kg/tree lower yields), average fruit dry matter (up to 0.5% lower average predicted dry matter), and abundance of high dry matter fruits (up to 11% fewer high predicted dry matter fruits) was observed. Fruit quality classes assembled on predicted dry matter verified the utility of this emerging parameter as a fruit quality metric for pears as demonstrated by more desirable post-harvest eating characteristics such as higher soluble solids content corresponding to greater at-harvest predicted dry matter categories. Targeted seasonal pruning in association with precise at-harvest dry matter fruit sorting may preserve the profitability of pear cultivation through their impact on fruit quality and associated consumer experiences. Full article

(This article belongs to the Special Issue In-Field Estimation of Fruit Quality and Quantity)

► Show Figures

Figure 1

21 pages, 40290 KiB

Open AccessEditor’s ChoiceArticle

Deep Learning for Mango (Mangifera indica) Panicle Stage Classification

by Anand Koirala, Kerry B. Walsh, Zhenglin Wang and Nicholas Anderson

Agronomy 2020, 10(1), 143; https://doi.org/10.3390/agronomy10010143 - 18 Jan 2020

Cited by 33 | Viewed by 9096

Abstract

Automated assessment of the number of panicles by developmental stage can provide information on the time spread of flowering and thus inform farm management. A pixel-based segmentation method for the estimation of flowering level from tree images was confounded by the developmental stage. [...] Read more.

Automated assessment of the number of panicles by developmental stage can provide information on the time spread of flowering and thus inform farm management. A pixel-based segmentation method for the estimation of flowering level from tree images was confounded by the developmental stage. Therefore, the use of a single and a two-stage deep learning framework (YOLO and R²CNN) was considered, using either upright or rotated bounding boxes. For a validation image set and for a total panicle count, the models MangoYOLO(-upright), MangoYOLO-rotated, YOLOv3-rotated, R²CNN(-rotated) and R²CNN-upright achieved weighted F1 scores of 76.5, 76.1, 74.9, 74.0 and 82.0, respectively. For a test set of the images of another cultivar and using a different camera, the R² for machine vision to human count of panicles per tree was 0.86, 0.80, 0.83, 0.81 and 0.76 for the same models, respectively. Thus, there was no consistent benefit from the use of rotated over the use of upright bounding boxes. The YOLOv3-rotated model was superior in terms of total panicle count, and the R²CNN-upright model was more accurate for panicle stage classification. To demonstrate practical application, panicle counts were made weekly for an orchard of 994 trees, with a peak detection routine applied to document multiple flowering events. Full article

(This article belongs to the Special Issue In-Field Estimation of Fruit Quality and Quantity)

► Show Figures

Figure 1

18 pages, 6507 KiB

Open AccessArticle

In-Field Estimation of Orange Number and Size by 3D Laser Scanning

by Valeriano Méndez, Antonio Pérez-Romero, Rubén Sola-Guirado, Antonio Miranda-Fuentes, Francisco Manzano-Agugliaro, Antonio Zapata-Sierra and Antonio Rodríguez-Lizana

Agronomy 2019, 9(12), 885; https://doi.org/10.3390/agronomy9120885 - 13 Dec 2019

Cited by 27 | Viewed by 4278

Abstract

The estimation of fruit load of an orchard prior to harvest is useful for planning harvest logistics and trading decisions. The manual fruit counting and the determination of the harvesting capacity of the field results are expensive and time-consuming. The automatic counting of [...] Read more.

The estimation of fruit load of an orchard prior to harvest is useful for planning harvest logistics and trading decisions. The manual fruit counting and the determination of the harvesting capacity of the field results are expensive and time-consuming. The automatic counting of fruits and their geometry characterization with 3D LiDAR models can be an interesting alternative. Field research has been conducted in the province of Cordoba (Southern Spain) on 24 ‘Salustiana’ variety orange trees—Citrus sinensis (L.) Osbeck—(12 were pruned and 12 unpruned). Harvest size and the number of each fruit were registered. Likewise, the unitary weight of the fruits and their diameter were determined (N = 160). The orange trees were also modelled with 3D LiDAR with colour capture for their subsequent segmentation and fruit detection by using a K-means algorithm. In the case of pruned trees, a significant regression was obtained between the real and modelled fruit number (R² = 0.63, p = 0.01). The opposite case occurred in the unpruned ones (p = 0.18) due to a leaf occlusion problem. The mean diameters proportioned by the algorithm (72.15 ± 22.62 mm) did not present significant differences (p = 0.35) with the ones measured on fruits (72.68 ± 5.728 mm). Even though the use of 3D LiDAR scans is time-consuming, the harvest size estimation obtained in this research is very accurate. Full article

(This article belongs to the Special Issue In-Field Estimation of Fruit Quality and Quantity)

► Show Figures

Figure 1

Review

Jump to: Editorial, Research, Other

37 pages, 10122 KiB

Open AccessEditor’s ChoiceReview

Technologies for Forecasting Tree Fruit Load and Harvest Timing—From Ground, Sky and Time

by Nicholas Todd Anderson, Kerry Brian Walsh and Dvoralai Wulfsohn

Agronomy 2021, 11(7), 1409; https://doi.org/10.3390/agronomy11071409 - 14 Jul 2021

Cited by 53 | Viewed by 7729

Abstract

The management and marketing of fruit requires data on expected numbers, size, quality and timing. Current practice estimates orchard fruit load based on the qualitative assessment of fruit number per tree and historical orchard yield, or manually counting a subsample of trees. This [...] Read more.

The management and marketing of fruit requires data on expected numbers, size, quality and timing. Current practice estimates orchard fruit load based on the qualitative assessment of fruit number per tree and historical orchard yield, or manually counting a subsample of trees. This review considers technological aids assisting these estimates, in terms of: (i) improving sampling strategies by the number of units to be counted and their selection; (ii) machine vision for the direct measurement of fruit number and size on the canopy; (iii) aerial or satellite imagery for the acquisition of information on tree structural parameters and spectral indices, with the indirect assessment of fruit load; (iv) models extrapolating historical yield data with knowledge of tree management and climate parameters, and (v) technologies relevant to the estimation of harvest timing such as heat units and the proximal sensing of fruit maturity attributes. Machine vision is currently dominating research outputs on fruit load estimation, while the improvement of sampling strategies has potential for a widespread impact. Techniques based on tree parameters and modeling offer scalability, but tree crops are complicated (perennialism). The use of machine vision for flowering estimates, fruit sizing, external quality evaluation is also considered. The potential synergies between technologies are highlighted. Full article

(This article belongs to the Special Issue In-Field Estimation of Fruit Quality and Quantity)

► Show Figures

Figure 1

Other

Jump to: Editorial, Research, Review

14 pages, 1887 KiB

Open AccessEditor’s ChoiceTechnical Note

Evaluation of Depth Cameras for Use in Fruit Localization and Sizing: Finding a Successor to Kinect v2

by Chiranjivi Neupane, Anand Koirala, Zhenglin Wang and Kerry Brian Walsh

Agronomy 2021, 11(9), 1780; https://doi.org/10.3390/agronomy11091780 - 5 Sep 2021

Cited by 50 | Viewed by 6894

Abstract

Eight depth cameras varying in operational principle (stereoscopy: ZED, ZED2, OAK-D; IR active stereoscopy: Real Sense D435; time of flight (ToF): Real Sense L515, Kinect v2, Blaze 101, Azure Kinect) were compared in context of use for in-orchard fruit localization and sizing. For [...] Read more.

Eight depth cameras varying in operational principle (stereoscopy: ZED, ZED2, OAK-D; IR active stereoscopy: Real Sense D435; time of flight (ToF): Real Sense L515, Kinect v2, Blaze 101, Azure Kinect) were compared in context of use for in-orchard fruit localization and sizing. For this application, a specification on bias-corrected root mean square error of 20 mm for a camera-to-fruit distance of 2 m and operation under sunlit field conditions was set. The ToF cameras achieved the measurement specification, with a recommendation for use of Blaze 101 or Azure Kinect made in terms of operation in sunlight and in orchard conditions. For a camera-to-fruit distance of 1.5 m in sunlight, the Azure Kinect measurement achieved an RMSE of 6 mm, a bias of 17 mm, an SD of 2 mm and a fill rate of 100% for depth values of a central 50 × 50 pixels group. To enable inter-study comparisons, it is recommended that future assessments of depth cameras for this application should include estimation of a bias-corrected RMSE and estimation of bias on estimated camera-to-fruit distances at 50 cm intervals to 3 m, under both artificial light and sunlight, with characterization of image distortion and estimation of fill rate. Full article

(This article belongs to the Special Issue In-Field Estimation of Fruit Quality and Quantity)

► Show Figures

Figure 1

11 pages, 6288 KiB

Open AccessBrief Report

Detection and Characterization of Cherries: A Deep Learning Usability Case Study in Chile

by Juan Fernando Villacrés and Fernando Auat Cheein

Agronomy 2020, 10(6), 835; https://doi.org/10.3390/agronomy10060835 - 12 Jun 2020

Cited by 43 | Viewed by 4663

Abstract

Chile is one of the main exporters of sweet cherries in the world and one of the few in the southern hemisphere, being their harvesting between October and January. Hence, Chilean cherries have gained market in the last few years and positioned Chile [...] Read more.

Chile is one of the main exporters of sweet cherries in the world and one of the few in the southern hemisphere, being their harvesting between October and January. Hence, Chilean cherries have gained market in the last few years and positioned Chile in a strategic situation which motivates to undergo through a deep innovation process in the field. Currently, cherry crop estimates have an error of approximately 45%, which propagates to all stages of the production process. In order to mitigate such error, we develop, test and evaluate a deep neural-based approach, using a portable artificial vision system to enhance the cherries harvesting estimates. Our system was tested in a cherry grove, under real field conditions. It was able to detect cherries with up to 85% of accuracy and to estimate production with up to 25% of error. In addition, it was able to classify cherries into four sizes, for a better characterization of the production for exportation. Full article

(This article belongs to the Special Issue In-Field Estimation of Fruit Quality and Quantity)

► Show Figures

Figure 1

Journal Menu

Journal Browser

In-Field Estimation of Fruit Quality and Quantity

Share This Special Issue

Special Issue Editor

Special Issue Information

Benefits of Publishing in a Special Issue

Published Papers (9 papers)

Editorial

Research

Review

Other

Further Information

Guidelines

MDPI Initiatives

Follow MDPI