Growth modeling of soybean plants from different land use intensities using close range RGB image time series

Machine Learning

In this thesis, the research question is whether regular close-range images with low-cost sensors (tablet camera) of certain field sections are suitable for growth modeling of soybean. Specifically, the effects of different land use intensities on soybean growth patterns shall be investigated using current methods of image analysis and plant phenotyping. Within the scope of the work, a comprehensive image data set along growth period will be generated. The development of a suitable experimental setup for stable and repeatable image acquisition at constant height and perspective with suitable georeferencing, as well as the execution of the photo campaign are essential parts of this work.

Master

This thesis requires a two month internship beginning in may 2022 to Leibniz Centre for Agricultural Landscape Research (ZALF) in Müncheberg 50km East of Berlin, Germany for two month. Within this that time the ZALF can offer regular german student salary and helps to find or offers accommodation. While in Müncheberg the student will take part of field work and generate weekly photo campaigns as part of the thesis.

We also offer similar projects in this field which differentiate plants or a related research questions.

Learning outcome

The student will how to run image analysis research from dataset generation to dateset analysis in agricultural environment. Further the student will learn how to train and evaluate neural networks using state-of-the-art techniques. Also, excellent opportunities to publish your research results in the form of a scientific publication.

Qualifications

Strong programming skills in one of the following programming languages: R, Python, Java
Knowledge in image analysis and openCVexperience with machine learning frameworks like PyTorch, KerasInterest on agricultural or environmental science or engineeringInterest in an interdisciplinary Master's thesisExperience in literature research and evaluation