File(s) stored somewhere else

Please note: Linked content is NOT stored on CQUniversity and we can't guarantee its availability, quality, security or accept any liability.

Estimation of fruit load in Australian mango orchards using machine vision

journal contribution
posted on 29.11.2021, 01:26 by Nicholas AndersonNicholas Anderson, Kerry WalshKerry Walsh, Anand KoiralaAnand Koirala, Zhenglin WangZhenglin Wang, Marcelo AmaralMarcelo Amaral, Geoff R Dickinson, Priyakant Sinha, Andrew J Robson
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.

Funding

Category 3 - Industry and Other Research Income

History

Volume

11

Issue

9

Start Page

1

End Page

20

Number of Pages

20

eISSN

2073-4395

Publisher

MDPI

Additional Rights

CC BY 4.0

Language

en

Peer Reviewed

Yes

Open Access

Yes

Acceptance Date

24/08/2021

External Author Affiliations

Queensland Government; University of New England

Author Research Institute

Institute for Future Farming Systems

Era Eligible

Yes

Journal

Agronomy

Article Number

1711