ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Publications Copernicus
Download
Citation
Articles | Volume IV-2/W7
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., IV-2/W7, 161–166, 2019
https://doi.org/10.5194/isprs-annals-IV-2-W7-161-2019
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., IV-2/W7, 161–166, 2019
https://doi.org/10.5194/isprs-annals-IV-2-W7-161-2019

  16 Sep 2019

16 Sep 2019

DETERMINATION OF DETAILED MORPHOLOGICAL FEATURES FOR PHENOTYPING OF SUGAR BEET PLANTS USING 3D-STEREOSCOPIC DATA

O. Scholz1, F. Uhrmann1, A. Wolff2, K. Pieger1, and D. Penk3 O. Scholz et al.
  • 1Fraunhofer Development Center X-ray Technology, 90768 Fürth, Germany
  • 2Strube Research GmbH, Hauptstr. 1, 38387 Söllingen, Germany
  • 3Friedrich-Alexander University Erlangen-Nuremberg, Computer Graphics Group, 91058 Erlangen, Germany

Keywords: Remote sensing, Phenotyping, Precision Farming, Plant morphology, Plant modelling, Sugar beet, Leaf model, 3D

Abstract. The sugar beet is the primary source of sugar in Europe and large parts of the world. Tools to determine plant traits with high precision and high throughput are required for the breeding process to quantify the effects of genetic and environmental factors on plant development and yield. In this work, we propose a method to gain a limited yet significant set of descriptive parameters for sugar beet plants. Using optical methods, a 3D representation of each plant is generated and subsequently segmented manually. A customized leaf model developed specifically for sugar beet plants then models the leaves, yielding a vector of descriptive parameters for each leaf. The resulting data is then compared to plant assessments of the same plants performed by sugar beet experts in order to evaluate the viability of automatic plant assessment in the sugar beet breeding process.