Estimation of fruit load in mango orchards: tree sampling considerations and use of machine vision and satellite imagery

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.

Download Full-text

Estimation of Fruit Load in Australian Mango Orchards Using Machine Vision

Agronomy ◽

10.3390/agronomy11091711 ◽

2021 ◽

Vol 11 (9) ◽

pp. 1711

Author(s):

Nicholas Todd Anderson ◽

Kerry Brian Walsh ◽

Anand Koirala ◽

Zhenglin Wang ◽

Marcelo Henrique Amaral ◽

...

Keyword(s):

Machine Vision ◽

Crop Damage ◽

Tree Level ◽

Percentage Error ◽

Canopy Architecture ◽

Night Time ◽

Average Percentage ◽

Absolute Percentage Error ◽

Average Percentage Error ◽

Fruit Load

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.

Download Full-text

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

Agronomy ◽

10.3390/agronomy11020347 ◽

2021 ◽

Vol 11 (2) ◽

pp. 347

Author(s):

Anand Koirala ◽

Kerry B. Walsh ◽

Zhenglin Wang

Keyword(s):

Deep Learning ◽

Random Forest ◽

Machine Vision ◽

Reference Method ◽

Ground Truth ◽

Image Features ◽

Ground Vehicles ◽

Method Error ◽

Robust Model ◽

Fruit Load

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.

Download Full-text

Machine Vision

10.1017/cbo9781139168229 ◽

2009 ◽

Cited By ~ 15

Author(s):

Wesley E. Snyder ◽

Hairong Qi

Keyword(s):

Machine Vision

Download Full-text

MONITORING IRRIGATION AND DRAINAGE SYSTEMS FROM SATELLITE IMAGERY FROM PUBLIC SOURCES

PROCEEDINGS of Nizhnevolzhskiy agrouniversity complex science and higher vocational education ◽

10.32786/2071-9485-2018-04-51 ◽

2018 ◽

Keyword(s):

Satellite Imagery ◽

Drainage Systems

Download Full-text

Classroom Lighting Energy-Saving Control System Based on Machine Vision Technology

Light & Engineering ◽

10.33383/2018-135 ◽

2018 ◽

pp. 143-149 ◽

Cited By ~ 1

Author(s):

Ruijie CHENG

Keyword(s):

Control System ◽

Machine Vision ◽

Energy Saving ◽

Back Propagation ◽

Back Propagation Neural Network ◽

Lighting Control ◽

Lighting Energy ◽

Neural Network Algorithm ◽

Energy Saving Control ◽

Model Algorithm

In order to further improve the energy efficiency of classroom lighting, a classroom lighting energy saving control system based on machine vision technology is proposed. Firstly, according to the characteristics of machine vision design technology, a quantum image storage model algorithm is proposed, and the Back Propagation neural network algorithm is used to analyze the technology, and a multifeedback model for energysaving control of classroom lighting is constructed. Finally, the algorithm and lighting model are simulated. The test results show that the design of this paper can achieve the optimization of the classroom lighting control system, different number of signals can comprehensively control the light and dark degree of the classroom lights, reduce the waste of resources of classroom lighting, and achieve the purpose of energy saving and emission reduction. Technology is worth further popularizing in practice.

Download Full-text