The `Hyperimage´ project, a project funded by the EU under the Horizon Europe Program, is aiming to revolutionize the sector of geo surveillance drones and automated farming by developing a new spectral camera. The project will enhance quality assurance and operational efficiency thanks to its high-tech imaging system based on Artificial Intelligence machine learning algorithms. These algorithms will identify objects in a precise way, allowing scientists to analyze spectral data and spot anomalies like diseases in crops, poluttants, or paint.

Hyperspectral cameras are able to capture from infrared up to ultraviolet light, unlike regular cameras that only focus on red, green, and blue wavelengths.

The team working on this project is making efforts to reduce the drone weight by 10% to create extra space for a larger battery. Consequently, boosting flight time by 50%. Head of the Hyperimage project at Fraunhofer IWS, Alexander Kabardiadi-Virkovski, explained: `Tasks that use UAVs, like environmental monitoring, infrastructure inspection, disaster management, and agricultural surveys, could all be improved by the HyperImage system. By using hyperspectral imaging, drones will be able to capture detailed data across several different wavelengths, allowing them to detect subtle changes in vegetation, identify materials, or monitor the integrity of infrastructure with much better precision than traditional sensors.´

The `Hyperimage´ imaging system will also be used in other industries like automated vertical farming. It will allow farmers boost yields by up to 20%, how so? By detecting diseases early, monitoring crop health, and optimizing harvest times.

Kabardiadi-Virkovski added, `The integration of hyperspectral cameras into autonomous systems represents a significant advancement in both technology and application. This imaging technique promises to enhance productivity and sustainability in industry and agriculture. Although hyperspectral imaging has existed since the 1980s, it has never been used in real-time with artificial intelligence for the applications the HyperImage team is now exploring.´

The Hyperimage project brings together different partners like: Robotnik Automation, HySpex, Optotune, SILIOS Technologies, and others. The project is set to conclude in 2027.

‍