The 2023–2028 OASYS research project, funded by the German Federal Ministry of Research, Technology, and Space (BMFTR), focuses on optoelectronic sensors for application-oriented systems. In the subproject A1, a team of scientists and industry experts is developing an ultra-compact, energy-efficient hyperspectral camera that uses artificial intelligence (AI) to perform complex material and quality analyses in real time. The integrated spectrometer records spectral characteristics, revealing chemical properties that are invisible to the human eye. This enables defects in food to be identified quickly and accurately.

The novel hyperspectral camera offers wide-ranging applications in industrial and agricultural processes. Its innovative approach combines conventional 2D imaging with AI and spectral analysis. A standard 2D camera first captures a high-resolution image of the target object. AI then analyzes the image in real time, automatically identifying regions of interest. The integrated spectrometer subsequently performs spectral analysis exclusively at these selected positions, determining the chemical composition.

This intelligent approach significantly enhances the efficiency of hyperspectral measurements. Rather than capturing spectral data across the entire image—a computationally intensive process—the system analyzes only the relevant measurement points. This targeted method substantially reduces data volumes, energy consumption, and processing time.

The information obtained helps improve quality control in food processing by detecting pressure marks and defects and enables an accurate assessment of plant condition and nutrient requirements in agriculture. Automated evaluation enables faster and more reliable decision-making. At the same time, processes become more sustainable, and economic resources are used more efficiently.

The components developed in the project will form the basis for future sensor systems that could significantly improve industry, recycling, agriculture, and the food sector.