Optimizing Mask R-CNN for enhanced quinoa panicle detection and segmentation in precision agriculture

Quinoa is a resilient, nutrient-rich crop with strong potential for cultivation in marginal environments, yet it remains underutilized and under-researched, particularly in the context of automated yield estimation. In this study, we introduce a novel deep learning approach for quinoa panicle detect...

Full description

Saved in:
Bibliographic Details
Main Authors: Manal El Akrouchi, Manal Mhada, Dachena Romain Gracia, Malcolm J. Hawkesford, Bruno Gérard
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-06-01
Series:Frontiers in Plant Science
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fpls.2025.1472688/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849706144506839040
author Manal El Akrouchi
Manal El Akrouchi
Manal Mhada
Dachena Romain Gracia
Malcolm J. Hawkesford
Bruno Gérard
author_facet Manal El Akrouchi
Manal El Akrouchi
Manal Mhada
Dachena Romain Gracia
Malcolm J. Hawkesford
Bruno Gérard
author_sort Manal El Akrouchi
collection DOAJ
description Quinoa is a resilient, nutrient-rich crop with strong potential for cultivation in marginal environments, yet it remains underutilized and under-researched, particularly in the context of automated yield estimation. In this study, we introduce a novel deep learning approach for quinoa panicle detection and counting using instance segmentation via Mask R-CNN, enhanced with an EfficientNet-B7 backbone and Mish activation function. We conducted a comparative analysis of various backbone architectures, and our improved model demonstrated superior performance in accurately detecting and segmenting individual panicles. This instance-level detection enables more precise yield estimation and offers a significant advancement over traditional methods. To the best of our knowledge, this is the first application of instance segmentation for quinoa panicle analysis, highlighting the potential of advanced deep learning techniques in agricultural monitoring and contributing valuable benchmarks for future AI-driven research in quinoa cultivation.
format Article
id doaj-art-2d7149f9c2ce42f0b38991c08ddd2e7a
institution DOAJ
issn 1664-462X
language English
publishDate 2025-06-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Plant Science
spelling doaj-art-2d7149f9c2ce42f0b38991c08ddd2e7a2025-08-20T03:16:17ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2025-06-011610.3389/fpls.2025.14726881472688Optimizing Mask R-CNN for enhanced quinoa panicle detection and segmentation in precision agricultureManal El Akrouchi0Manal El Akrouchi1Manal Mhada2Dachena Romain Gracia3Malcolm J. Hawkesford4Bruno Gérard5College of Agriculture and Environmental Sciences, University Mohammed VI Polytechnic (UM6P), Ben Guerir, MoroccoSchool of Collective Intelligence, University Mohammed VI Polytechnic (UM6P), Rabat, MoroccoCollege of Agriculture and Environmental Sciences, University Mohammed VI Polytechnic (UM6P), Ben Guerir, MoroccoCollege of Agriculture and Environmental Sciences, University Mohammed VI Polytechnic (UM6P), Ben Guerir, MoroccoSustainable Soils and Crops Department, Rothamsted Research, Harpenden, Hertfordshire, United KingdomCollege of Agriculture and Environmental Sciences, University Mohammed VI Polytechnic (UM6P), Ben Guerir, MoroccoQuinoa is a resilient, nutrient-rich crop with strong potential for cultivation in marginal environments, yet it remains underutilized and under-researched, particularly in the context of automated yield estimation. In this study, we introduce a novel deep learning approach for quinoa panicle detection and counting using instance segmentation via Mask R-CNN, enhanced with an EfficientNet-B7 backbone and Mish activation function. We conducted a comparative analysis of various backbone architectures, and our improved model demonstrated superior performance in accurately detecting and segmenting individual panicles. This instance-level detection enables more precise yield estimation and offers a significant advancement over traditional methods. To the best of our knowledge, this is the first application of instance segmentation for quinoa panicle analysis, highlighting the potential of advanced deep learning techniques in agricultural monitoring and contributing valuable benchmarks for future AI-driven research in quinoa cultivation.https://www.frontiersin.org/articles/10.3389/fpls.2025.1472688/fullMask R-CNNinstance segmentationquinoaprecision agriculturedeep learning
spellingShingle Manal El Akrouchi
Manal El Akrouchi
Manal Mhada
Dachena Romain Gracia
Malcolm J. Hawkesford
Bruno Gérard
Optimizing Mask R-CNN for enhanced quinoa panicle detection and segmentation in precision agriculture
Frontiers in Plant Science
Mask R-CNN
instance segmentation
quinoa
precision agriculture
deep learning
title Optimizing Mask R-CNN for enhanced quinoa panicle detection and segmentation in precision agriculture
title_full Optimizing Mask R-CNN for enhanced quinoa panicle detection and segmentation in precision agriculture
title_fullStr Optimizing Mask R-CNN for enhanced quinoa panicle detection and segmentation in precision agriculture
title_full_unstemmed Optimizing Mask R-CNN for enhanced quinoa panicle detection and segmentation in precision agriculture
title_short Optimizing Mask R-CNN for enhanced quinoa panicle detection and segmentation in precision agriculture
title_sort optimizing mask r cnn for enhanced quinoa panicle detection and segmentation in precision agriculture
topic Mask R-CNN
instance segmentation
quinoa
precision agriculture
deep learning
url https://www.frontiersin.org/articles/10.3389/fpls.2025.1472688/full
work_keys_str_mv AT manalelakrouchi optimizingmaskrcnnforenhancedquinoapanicledetectionandsegmentationinprecisionagriculture
AT manalelakrouchi optimizingmaskrcnnforenhancedquinoapanicledetectionandsegmentationinprecisionagriculture
AT manalmhada optimizingmaskrcnnforenhancedquinoapanicledetectionandsegmentationinprecisionagriculture
AT dachenaromaingracia optimizingmaskrcnnforenhancedquinoapanicledetectionandsegmentationinprecisionagriculture
AT malcolmjhawkesford optimizingmaskrcnnforenhancedquinoapanicledetectionandsegmentationinprecisionagriculture
AT brunogerard optimizingmaskrcnnforenhancedquinoapanicledetectionandsegmentationinprecisionagriculture