Enabling next level research on roots - automatizing minirhizotron image acquisition and analysis

The project will develop an automatizing, modular minirhizotron (MR) image acquisition system (prototypes) for permanent field placement and an accompanying software solution (beta) to automatize root tracking (segregation) and soil water content determination. Objectives: - Design and build the prototype of an autonomous, connected, and modular MR camera carrier system for permanent installation and operation in MR tubes installed under controlled conditions (mesocosms) and in situ (arctic to desert environments). - Develop two imaging / camera modules to be used with the carrier system, a o low cost VIS RGB-based, UHD module (Imaging module 1, IM_1), and an o Advanced imaging module, combining RGB and selected multispectral (NIR) wavebands for advanced image analysis (IM_2). - Developing a Machine learning/neural network based analysis workflow incl. UI to allow for o Basic root segmentation and soil water content determination (IM_1) o Advanced root segmentation and classification, and soil water content determination (IM_2) on MR images.