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

A - Papers appearing in refereed journals

El Akrouchi, M., Mhada, M., Gracia, D. R., Hawkesford, M. J. and Gerard, B. 2025. Optimizing Mask R-CNN for enhanced quinoa panicle detection and segmentation in precision agriculture. Frontiers in Plant Science. 16, p. 1472688. https://doi.org/10.3389/fpls.2025.1472688

AuthorsEl Akrouchi, M., Mhada, M., Gracia, D. R., Hawkesford, M. J. and Gerard, B.
Abstract

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

KeywordsMask R-CNN; Instance segmentation; Quinoa; Precision agriculture; Deep learning
Year of Publication2025
JournalFrontiers in Plant Science
Journal citation16, p. 1472688
Digital Object Identifier (DOI)https://doi.org/10.3389/fpls.2025.1472688
Open accessPublished as ‘gold’ (paid) open access
FunderOffice Chérifien des Phosphate (OCP)
Funder project or codeOCP/UM6P Bioproducts for African Agriculture
Publisher's version
Output statusPublished
Publication dates
Online02 Jun 2025
Publication process dates
Accepted25 Apr 2025
PublisherFrontiers Media SA
ISSN1664-462X

Permalink - https://repository.rothamsted.ac.uk/item/993z6/optimizing-mask-r-cnn-for-enhanced-quinoa-panicle-detection-and-segmentation-in-precision-agriculture

39 total views
2 total downloads
6 views this month
0 downloads this month
Download files as zip