Logo des Repositoriums

Auflistung nach Schlagwort "phenotyping"

1 - 5 von 5
  • Konferenzbeitrag
    CherryGraph: Encoding digital twins of cherry trees into a knowledge graph based on topology
    (44. GIL - Jahrestagung, Biodiversität fördern durch digitale Landwirtschaft, 2024) Andreas Gilson, Mareike Weule
    CherryGraph is a structural framework for mapping trees into an ontology-based knowledge graph that can be used as database backend for digital twins. Based on the reconstructed 3D topology of scanned trees, information is encoded in a knowledge graph that resembles the real canopy structure of trees. Thus, CherryGraph enables consistent navigation within the branching system of a tree over different time points regardless of natural fluctuations. The resulting knowledge graph can then be queried for arbitrary use cases or aggregated on different hierarchy levels. We demonstrate the potential of CherryGraph by using data of real cherry trees from the 2023 cherry season with exemplary queries that can be extended to include spatial and temporal dimensions for comparing indicators like elongation growth of shoots or tracking the development of other various tree traits over time.
  • Konferenzbeitrag
    Evaluating synthetic vs. real data generation for AI-based selective weeding
    (43. GIL-Jahrestagung, Resiliente Agri-Food-Systeme, 2023) Iqbal, Naeem; Bracke, Justus; Elmiger, Anton; Hameed, Hunaid; von Szadkowski, Kai
    Synthetic data has the potential to reduce the cost for ML training in agriculture but poses its own set of problems compared to real data acquisition. In this work, we present two methods of training data acquisition for the application of machine vision algorithms in the use case of selective weeding. Results from ML experiments suggest that current methods for generating synthetic data in the field of agriculture cannot fully replace real data but may greatly reduce the quantity of real data required for model training.
  • Konferenzbeitrag
    Field plant characterization method based on a multi-wavelength line profiling system
    (41. GIL-Jahrestagung, Informations- und Kommunikationstechnologie in kritischen Zeiten, 2021) Pamornnak, Burawich; Scholz, Christian; Nieberg, Dominik; Igelbrink, Matthias; Ruckelshausen, Arno
    Phenotyping of plant characteristics is essential for plant breeding. Especially the growth stages of plants during field emergence, described by parameters such as plant height and plant counting, are of interest. But large-scale manual phenotyping is very inconvenient due to the workload, the harsh weather conditions, and time-consumption. Therefore, an automated system is needed. This research describes a field plant characterization method implemented in a plot divider machine for rapeseeds. The method consists of a plant height estimation and a plant counting system. Based on a multi-wavelength line profiling (MWLP) sensor system, the 2D and 3D point cloud information from visible wavelengths to near-infrared (NIR) are automatically mapped without any need for a matching method. The plant characterization processes consist of two main steps, 1) plant detection, and 2) height estimation. These processes use the 2D NIR and 3D point cloud as the main features. The proposed method was demonstrated with highly accurate results in several rapeseeds, illustrating the potential of this method to become a basic tool for crop characterization in plant sciences
  • Konferenzbeitrag
    For5G: Systematic approach for creating digital twins of cherry orchards
    (43. GIL-Jahrestagung, Resiliente Agri-Food-Systeme, 2023) Meyer, Lukas; Gilson, Andreas; Uhrmann, Franz; Weule, Mareike; Keil, Fabian; Haunschild, Bernhard; Oschek, Joachim; Steglich, Marco; Hansen, Jonathan; Stamminger, Marc; Scholz, Oliver
    We present a systematic approach for creating digital twins of cherry trees in orchards as part of the project “For5G: Digital Twin”. We aim to develop a basic concept for 5G applications in orchards using a mobile campus network. Digital twins monitor the status of individual trees in every aspect and are a crucial step for the digitalization of processes in horticulture. Our framework incorporates a transformation of photometric data to a 3D reconstruction, which is subsequently segmented and modeled using learning-based approaches. Collecting objective phenotypic features from individual trees over time and storing them in a knowledge graph offers a convenient foundation for gaining new insights. Our approach shows promising results at this point for creating a detailed digital twin of a cherry tree and ultimately the entire orchard.
  • Konferenzbeitrag
    Ontologies for resolving semantic heterogeneity in information integration among plant phenomics databases
    (38. GIL-Jahrestagung, Digitale Marktplätze und Plattformen, 2018) Nafissi, Anahita; Bruns, Benjamin; Fiorani, Fabio
    Increasing amounts of heterogeneous data are produced every year by plant researchers. For data management relational databases with application-specific schemas are mainly used in this field. However, due to absence of widely shared standards, data integration and exchange between independently developed and heterogeneous databases becomes very challenging. A critical point is to achieve semantic interoperability among these databases. The authors propose to use Semantic Web features for this integration task. Ontologies are the main core of the Semantic Web and are suitable to resolve semantic heterogeneity. In this work a semi-automated ontology based approach is defined for integrating heterogeneous data stored in distributed phenomics databases. The results of a real-world case study show that this approach creates reasonable semantic correspondences between domain-specific databases and publicly available ontologies and can significantly save time compared to classic (specification-driven) engineering approaches.