A two-step registration-classification approach to automated segmentation of multimodal images for high-throughput greenhouse plant phenotyping

Background Automated segmentation of large amount of image data is one of the major bottlenecks in high-throughput plant phenotyping. Dynamic optical appearance of developing plants, inhomogeneous scene illumination, shadows and reflections in plant and background regions complicate automated segmen...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Plant methods Ročník 16; číslo 1; s. 95
Hlavní autoři: Henke, Michael, Junker, Astrid, Neumann, Kerstin, Altmann, Thomas, Gladilin, Evgeny
Médium: Journal Article
Jazyk:angličtina
Vydáno: London BioMed Central 09.07.2020
BioMed Central Ltd
Springer Nature B.V
BMC
Témata:
Algorithms
Automation
Biological Techniques
Biomedical and Life Sciences
Blurring
Cameras
Classification
color
Deep learning
Developmental stages
Flowers & plants
Fluorescence
Fluorescence imaging
Greenhouse plant phenotyping
Greenhouses
Ground truth
Identification and classification
Image acquisition
Image analysis
Image classification
Image detection
Image processing
Image segmentation
Life Sciences
lighting
Machine learning
Methodology
Methods
Multimodal image alignment
phenotype
Phenotyping
Physiological aspects
Plant Sciences
Plants (Organisms)
Principal components analysis
Registration
Relocation
Supervised image segmentation
Visible light imaging
Germany
Aachen Germany
Visible light imaging
Fluorescence imaging
Supervised image segmentation
Multimodal image alignment
Greenhouse plant phenotyping
Machine learning
ISSN:1746-4811, 1746-4811
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Background Automated segmentation of large amount of image data is one of the major bottlenecks in high-throughput plant phenotyping. Dynamic optical appearance of developing plants, inhomogeneous scene illumination, shadows and reflections in plant and background regions complicate automated segmentation of unimodal plant images. To overcome the problem of ambiguous color information in unimodal data, images of different modalities can be combined to a virtual multispectral cube. However, due to motion artefacts caused by the relocation of plants between photochambers the alignment of multimodal images is often compromised by blurring artifacts. Results Here, we present an approach to automated segmentation of greenhouse plant images which is based on co-registration of fluorescence (FLU) and of visible light (VIS) camera images followed by subsequent separation of plant and marginal background regions using different species- and camera view-tailored classification models. Our experimental results including a direct comparison with manually segmented ground truth data show that images of different plant types acquired at different developmental stages from different camera views can be automatically segmented with the average accuracy of 93 % ( S D = 5 % ) using our two-step registration-classification approach. Conclusion Automated segmentation of arbitrary greenhouse images exhibiting highly variable optical plant and background appearance represents a challenging task to data classification techniques that rely on detection of invariances. To overcome the limitation of unimodal image analysis, a two-step registration-classification approach to combined analysis of fluorescent and visible light images was developed. Our experimental results show that this algorithmic approach enables accurate segmentation of different FLU/VIS plant images suitable for application in fully automated high-throughput manner.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1746-4811
1746-4811
DOI:10.1186/s13007-020-00637-x