Improved weed segmentation in UAV imagery of sorghum fields with a combined deblurring segmentation model.

BACKGROUND: Efficient and site-specific weed management is a critical step in many agricultural tasks. Image captures from drones and modern machine learning based computer vision methods can be used to assess weed infestation in agricultural fields more efficiently. However, the image quality of the captures can be affected by several factors, including motion blur. Image captures can be blurred because the drone moves during the image capturing process, e.g. due to wind pressure or camera settings. These influences complicate the annotation of training and test samples and can also lead to reduced predictive power in segmentation and classification tasks. RESULTS: In this study, we propose DeBlurWeedSeg, a combined deblurring and segmentation model for weed and crop segmentation in motion blurred images. For this purpose, we first collected a new dataset of matching sharp and naturally blurred image pairs of real sorghum and weed plants from drone images of the same agricultural field. The data was used to train and evaluate the performance of DeBlurWeedSeg on both sharp and blurred images of a hold-out test-set. We show that DeBlurWeedSeg outperforms a standard segmentation model that does not include an integrated deblurring step, with a relative improvement of [Formula: see text] in terms of the Sørensen-Dice coefficient. CONCLUSION: Our combined deblurring and segmentation model DeBlurWeedSeg is able to accurately segment weeds from sorghum and background, in both sharp as well as motion blurred drone captures. This has high practical implications, as lower error rates in weed and crop segmentation could lead to better weed control, e.g. when using robots for mechanical weed removal.

Thermal, rheological, and ion-transport properties of phosphonium-based ionic liquids.

Phosphonium-based ionic liquids with varying counteranions from commercially available ionic liquid precursors enabled tunable viscosity, ionic conductivity, and thermal stability. Thermogravimetric analysis revealed a relationship between thermal stability and anion composition where anions with lower basicity remained stable to higher temperatures. Determination of glass transition temperatures and melting temperatures using differential scanning calorimetry revealed supercooling, crystallization, and dependence on anion composition. Rheological and ionic conductivity measurements determined the temperature-dependence of the viscosity and ionic conductivity of the phosphonium-based ionic liquids. Arrhenius analyses of conductivity and viscosity provided activation energies, which showed a decrease toward larger, more delocalized anions. An assessment according to the Walden plot displayed their efficacy relative to other ionic liquids.

Chloride-free method to synthesise new ionic liquids with mixed borate anions.

Chloride avoided! A new chloride-free method to synthesise ionic liquids (ILs) with mixed borate anions, starting from tetrafluoroborate compounds, has been developed and a number of examples including some new ILs are presented (see scheme; [CAT](+) = cation). It is widely applicable and allows access to mixed borates with various types of ligands in a straightforward manner.