No abstract

No abstract

No abstract

No abstract

No abstract

Multispectral images (MSIs) are valuable for precision agriculture due to the extra spectral information acquired compared to natural color RGB (ncRGB) images. In this paper, we thus aim to generate high spatial MSIs through a robust, deep-learning-based reconstruction method using ncRGB images. Using the data from the agronomic research trial for maize and breeding research trial for rice, we first reproduced ncRGB images from MSIs through a rendering model, Model-True to natural color image (Model-TN), which was built using a benchmark hyperspectral image dataset. Subsequently, an MSI reconstruction model, Model-Natural color to Multispectral image (Model-NM), was trained based on prepared ncRGB (ncRGB-Con) images and MSI pairs, ensuring the model can use widely available ncRGB images as input. The integrated loss function of mean relative absolute error (MRAEloss) and spectral information divergence (SIDloss) were most effective during the building of both models, while models using the MRAEloss function were more robust towards variability between growing seasons and species. The reliability of the reconstructed MSIs was demonstrated by high coefficients of determination compared to ground truth values, using the Normalized Difference Vegetation Index (NDVI) as an example. The advantages of using “reconstructed” NDVI over Triangular Greenness Index (TGI), as calculated directly from RGB images, were illustrated by their higher capabilities in differentiating three levels of irrigation treatments on maize plants. This study emphasizes that the performance of MSI reconstruction models could benefit from an optimized loss function and the intermediate step of ncRGB image preparation. The ability of the developed models to reconstruct high-quality MSIs from low-cost ncRGB images will, in particular, promote the application for plant phenotyping in precision agriculture.

No abstract

Complexity of Automotive EE systems has grown exponentially during the past decade. Model-based function design and simulation are widely accepted and used by the Automotive EE community of today, to face some of the challenges. Emerging new standards -like AUTOSAR -bring standardized interfaces to low-level software, reducing cost and most importantly introducing a new level of abstraction to function implementers. Ease of software component reuse is another novel benefit brought by AUTOSAR. However, there is little guidance on how to translate the results of model-based function design into robust and efficient system implementations in a highly distributed environment. This paper outlines a proposed system level design methodology, supported by a set of point-tools, to bridge the Implementation Abyss. The flow covers: model transformation, architecture design, scheduling of networks and tasks distributed across multiple ECUs, harness design -followed by metrics and criteria-based evaluation of the resulting architecture. Automated creation of AUTOSAR-compliant configuration files for ECU generation is provided to complete the process.