Search

Abstract 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 $$93\%$$ 93 % ( $$SD=5\%$$ 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.

Abstract With the introduction of high-throughput multisensory imaging platforms, the automatization of multimodal image analysis has become the focus of quantitative plant research. Due to a number of natural and technical reasons (e.g., inhomogeneous scene illumination, shadows, and reflections), unsupervised identification of relevant plant structures (i.e., image segmentation) represents a nontrivial task that often requires extensive human-machine interaction. Registration of multimodal plant images enables the automatized segmentation of ’difficult’ image modalities such as visible light or near-infrared images using the segmentation results of image modalities that exhibit higher contrast between plant and background regions (such as fluorescent images). Furthermore, registration of different image modalities is essential for assessment of a consistent multiparametric plant phenotype, where, for example, chlorophyll and water content as well as disease- and/or stress-related pigmentation can simultaneously be studied at a local scale. To automatically register thousands of images, efficient algorithmic solutions for the unsupervised alignment of two structurally similar but, in general, nonidentical images are required. For establishment of image correspondences, different algorithmic approaches based on different image features have been proposed. The particularity of plant image analysis consists, however, of a large variability of shapes and colors of different plants measured at different developmental stages from different views. While adult plant shoots typically have a unique structure, young shoots may have a nonspecific shape that can often be hardly distinguished from the background structures. Consequently, it is not clear a priori what image features and registration techniques are suitable for the alignment of various multimodal plant images. Furthermore, dynamically measured plants may exhibit nonuniform movements that require application of nonrigid registration techniques. Here, we investigate three common techniques for registration of visible light and fluorescence images that rely on finding correspondences between (i) feature-points, (ii) frequency domain features, and (iii) image intensity information. The performance of registration methods is validated in terms of robustness and accuracy measured by a direct comparison with manually segmented images of different plants. Our experimental results show that all three techniques are sensitive to structural image distortions and require additional preprocessing steps including structural enhancement and characteristic scale selection. To overcome the limitations of conventional approaches, we develop an iterative algorithmic scheme, which allows it to perform both rigid and slightly nonrigid registration of high-throughput plant images in a fully automated manner.

Abstract Background Automated plant phenotyping has been established as a powerful new tool in studying plant growth, development and response to various types of biotic or abiotic stressors. Respective facilities mainly apply non-invasive imaging based methods, which enable the continuous quantification of the dynamics of plant growth and physiology during developmental progression. However, especially for plants of larger size, integrative, automated and high throughput measurements of complex physiological parameters such as photosystem II efficiency determined through kinetic chlorophyll fluorescence analysis remain a challenge. Results We present the technical installations and the establishment of experimental procedures that allow the integrated high throughput imaging of all commonly determined PSII parameters for small and large plants using kinetic chlorophyll fluorescence imaging systems (FluorCam, PSI) integrated into automated phenotyping facilities (Scanalyzer, LemnaTec). Besides determination of the maximum PSII efficiency, we focused on implementation of high throughput amenable protocols recording PSII operating efficiency (ΦPSII). Using the presented setup, this parameter is shown to be reproducibly measured in differently sized plants despite the corresponding variation in distance between plants and light source that caused small differences in incident light intensity. Values of ΦPSII obtained with the automated chlorophyll fluorescence imaging setup correlated very well with conventionally determined data using a spot-measuring chlorophyll fluorometer. The established high throughput operating protocols enable the screening of up to 1080 small and 184 large plants per hour, respectively. The application of the implemented high throughput protocols is demonstrated in screening experiments performed with large Arabidopsis and maize populations assessing natural variation in PSII efficiency. Conclusions The incorporation of imaging systems suitable for kinetic chlorophyll fluorescence analysis leads to a substantial extension of the feature spectrum to be assessed in the presented high throughput automated plant phenotyping platforms, thus enabling the simultaneous assessment of plant architectural and biomass-related traits and their relations to physiological features such as PSII operating efficiency. The implemented high throughput protocols are applicable to a broad spectrum of model and crop plants of different sizes (up to 1.80 m height) and architectures. The deeper understanding of the relation of plant architecture, biomass formation and photosynthetic efficiency has a great potential with respect to crop and yield improvement strategies.

Abstract Background Plant phenotypic data shrouds a wealth of information which, when accurately analysed and linked to other data types, brings to light the knowledge about the mechanisms of life. As phenotyping is a field of research comprising manifold, diverse and time-consuming experiments, the findings can be fostered by reusing and combining existing datasets. Their correct interpretation, and thus replicability, comparability and interoperability, is possible provided that the collected observations are equipped with an adequate set of metadata. So far there have been no common standards governing phenotypic data description, which hampered data exchange and reuse. Results In this paper we propose the guidelines for proper handling of the information about plant phenotyping experiments, in terms of both the recommended content of the description and its formatting. We provide a document called “Minimum Information About a Plant Phenotyping Experiment”, which specifies what information about each experiment should be given, and a Phenotyping Configuration for the ISA-Tab format, which allows to practically organise this information within a dataset. We provide examples of ISA-Tab-formatted phenotypic data, and a general description of a few systems where the recommendations have been implemented. Conclusions Acceptance of the rules described in this paper by the plant phenotyping community will help to achieve findable, accessible, interoperable and reusable data.