Spatial Referencing of Hyperspectral Images for Tracing of Plant Disease Symptoms

• DOI: 10.3390/jimaging4120143
• Publication Date: 2018-12-04T16:56:18Z
• Authors: Jan Behmann; David Bohnenkamp; Stefan Paulus; Anne-Katrin Mahlein
• Keywords: Tracing; Plant disease

The characterization of plant disease symptoms by hyperspectral imaging is often limited the missing ability to investigate early, still invisible states. Automatically tracing symptom position on leaf back in time could be a promising approach overcome this limitation. Therefore we present method spatially reference series close range images. Based points, robust presented derive suitable transformation model for each observation within experiment. A non-linear 2D polynomial has been selected cope with specific structure and growth processes wheat leaves. potential outlined an improved labeling procedure very early extracting spectral characteristics single represented Vegetation Indices over time. are extracted brown rust septoria tritici blotch wheat, based observations using VISNIR (400–1000 nm) camera.