An EU-backed project’s cutting-edge spectral imaging system promises to not only boost crop yields but also increase drone flight times.
Researchers supported by the EU-funded HyperImage project are developing a new hyperspectral camera that could transform the monitoring of product condition, quality and safety. The novel spectral imaging system has a wide range of applications, one of which is vertical farming. It is expected to cut farming costs, reduce waste and boost yields. Thanks to the hyperspectral camera’s enhanced imaging capabilities, farmers growing crops such as salads, herbs and microgreens will be able to detect diseases in them at an early stage and precisely monitor crop health. According to the HyperImage team, the camera also allows farmers to optimise harvest times and increase yields by up to 20 %.
Not like a regular camera
The hyperspectral camera does not only capture red, green and blue light like regular cameras do, but also many different wavelengths of light ranging from the infrared to the ultraviolet bands. Using AI, scientists can analyse the data from these wavelengths in real time to instantly classify different materials and objects. In this way, things like paint, pollutants and plant diseases can be spotted instantly. “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,” states Alexander Kabardiadi-Virkovski, head of the HyperImage project at Fraunhofer IWS, in a news item posted on ‘Optics.org’. “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.”
Farming is not the only goal
Kabardiadi-Virkovski goes on to explain about the camera’s wide range of applications. “Our new system is being developed for automated vertical farming but is simultaneously being used to improve quality control, navigation in off-road autonomous driving, and vision systems for unmanned geo-surveillance drones. The innovative HyperImage approach will enable autonomous vehicles to perform detailed landscape analysis and make informed decisions regarding passability in outdoor environments. By standardising hyperspectral data across different camera manufacturers, we aim to create a universal solution for object recognition and quality control.” According to the researcher, the HyperImage system has the potential to improve numerous tasks that make use of drones, such as environmental monitoring, infrastructure inspection, disaster management and agricultural surveys. “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,” he observes. The HyperImage (A universal spectral imaging sensor platform for industry, agriculture and autonomous driving) team is working to reduce drone weight (in the 25 kg maximum take-off weight class) by 10 % through the lightweight hyperspectral camera it is developing. This will leave space for a larger battery, increasing flight time by 50 %.
More information CORDIS.
Leave a Reply