Semantic segmentation of plant roots from RGB (mini-) rhizotron images—generalisation potential and false positives of established methods and advanced deep-learning models

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningfagfællebedømt


  • Fulltext

    Forlagets udgivne version, 1,97 MB, PDF-dokument

  • Pavel Baykalov
  • Bart Bussmann
  • Richard Nair
  • Smith, Abraham George
  • Gernot Bodner
  • Ofer Hadar
  • Naftali Lazarovitch
  • Boris Rewald

Background: Manual analysis of (mini-)rhizotron (MR) images is tedious. Several methods have been proposed for semantic root segmentation based on homogeneous, single-source MR datasets. Recent advances in deep learning (DL) have enabled automated feature extraction, but comparisons of segmentation accuracy, false positives and transferability are virtually lacking. Here we compare six state-of-the-art methods and propose two improved DL models for semantic root segmentation using a large MR dataset with and without augmented data. We determine the performance of the methods on a homogeneous maize dataset, and a mixed dataset of > 8 species (mixtures), 6 soil types and 4 imaging systems. The generalisation potential of the derived DL models is determined on a distinct, unseen dataset. Results: The best performance was achieved by the U-Net models; the more complex the encoder the better the accuracy and generalisation of the model. The heterogeneous mixed MR dataset was a particularly challenging for the non-U-Net techniques. Data augmentation enhanced model performance. We demonstrated the improved performance of deep meta-architectures and feature extractors, and a reduction in the number of false positives. Conclusions: Although correction factors are still required to match human labelled root lengths, neural network architectures greatly reduce the time required to compute the root length. The more complex architectures illustrate how future improvements in root segmentation within MR images can be achieved, particularly reaching higher segmentation accuracies and model generalisation when analysing real-world datasets with artefacts—limiting the need for model retraining.

TidsskriftPlant Methods
Udgave nummer1
Antal sider15
StatusUdgivet - 2023

Bibliografisk note

Funding Information:
This project has received funding from the European Union's Horizon 2020 research and innovation programme under Grant Agreement No 777222 (ATTRACT project “NextMR-IAA”) & under grant agreement No 813114 (FutureArctic-ITN). BR and GB were funded by the University of Natural Resources and Life Sciences, Vienna (BOKU). BR was funded by the EU HE research and innovation programme under grant agreement N°101087262 during the MS revision phase.

Publisher Copyright:
© 2023, The Author(s).

ID: 372962578