2020/02/21 by Yi Zhao, Zhao, Yi, Nils Wandel +7
Agricultural and Biological Sciences · Computer Science · #Artificial intelligence #Biology #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Computer vision #Environmental science #FOS: Computer and information sciences #Function (biology) #Geology #High resolution #Image (mathematics) #Image resolution #Noise (video) #Pattern recognition (psychology) #Plant Molecular Biology Research #Plant nutrient uptake and metabolism #Plant root #Remote sensing #Resolution (logic) #Root (linguistics) #SIGNAL (programming language) #Segmentation #Signal-to-noise ratio (imaging) #Smart Agriculture and AI #Soil science #cs.CV
paper · pdf · doi:10.48550/arxiv.2002.09317
published in arXiv (Cornell University) (Cornell University) · 6 pages, 5 figures, in the 28th European Symposium on Artificial Neural Networks
arxiv created 2020/02/21 · openalex publication_date 2020/02/21 · arxiv updated 2020/02/24 · openalex created_date 2020/03/06 · openalex updated_date 2026/08/06
Magnetic resonance imaging (MRI) enables plant scientists to non-invasively study root system development and root-soil interaction. Challenging recording conditions, such as low resolution and a high level of noise hamper the performance of traditional root extraction algorithms, though. We propose to increase signal-to-noise ratio and resolution by segmenting the scanned volumes into root and soil in super-resolution using a 3D U-Net. Tests on real data show that the trained network is capable to detect most roots successfully and even finds roots that were missed by human annotators. Our experiments show that the segmentation performance can be further improved with modifications of the loss function.