Gillert, AlexanderAlexanderGillertPeters, BoBoPetersLukas, Uwe Freiherr vonUwe Freiherr vonLukasKreyling, JürgenJürgenKreylingBlume-Werry, GescheGescheBlume-Werry2023-04-242023-04-242023https://publica.fraunhofer.de/handle/publica/44044310.1109/WACV56688.2023.00369Plant roots are difficult to monitor and study since they are hidden belowground. Minirhizotrons offer an in-situ monitoring solution but their widespread adoption is still limited by the capabilities of automatic analysis methods. These capabilities so far consist only of estimating a single number (total root length) per image. We propose a method for a more fine-grained analysis which estimates the root turnover, i.e. the amount of root growth and decay between two minirhizotron images. It consists of a neural network that computes which roots are visible in both images and is trained in an unsupervised manner without additional annotations. Our code is available as a part of an analysis tool with a user interface ready to be used by ecologists. https://github.com/alexander-g/Root-TrackingenBranche: Bioeconomics and InfrastructureResearch Line: Computer vision (CV)Research Line: Machine learning (ML)LTA: Scalable architectures for massive data setsLTA: Machine intelligence, algorithms, and data structures (incl. semantics)Environmental monitoringEnvironmental problemsBiological processesconference paper