The HyperImage project will be the first initiative to develop a universal, fast, modular and cost-effective spectral image sensing technology platform suitable for both short- and long-range imaging applications. To achieve that, HyperImage will make use of innovative photonic components including electrically tunable liquid lenses, pixel shifters, fast steering mirrors, and configurable SMD style IR micro-emitter arrays. HyperImage will integrate these components into innovative, high-performance multi- and hyperspectral snapshot and line scan cameras. AI machine learning algorithms will translate spectral image data into relevant functional products properties and detect and classify objects for more accurate decision making e.g. in autonomous driving. The technology platform will be complemented with a cloud-based spectral image analysis platform and reference data repository that enables users to continuously improve image analysis accuracy and prediction models. The HyperImage technology platform will be validated in four industrial use cases: (1) quality control in manufacturing of high power electronics; (2) crop growth monitoring for fully automated vertical farming of salads, herbs and microgreens; (3) spectral image based vision and navigation in off-road autonomous driving; (4) light-weight, high-resolution hyperspectral vision system for unmanned geo-surveillance drones. Based on that, HyperImage will provide European Industry a universal, efficient and reliable solution for object recognition, detailed product and material analysis and reliable quality control in manufacturing. HyperImage solution will lead to strong benefits for the applications such as 10-20% increase yield and reduced cost in manufacturing and vertical farming, 20% fuel saving and up to 40% increased operation speed in autonomous offroad driving; and up to 10% drone weight reduction (25 kg MTOW class) yielding 50% increased flight time through space for a larger battery.
