Conventional multispectral and hyperspectral can't keep up (and integrate well) into existing sorting lines. They induce a slow-down in conveyer belt speeds or you have to install splitters and buy multiple $100K cameras.
(we're working to solve this problem though in the classic VC backed way - DM for more information!)
Living Optics | Software/Production/Systems Engineers | Full-time | Oxford, UK
Living Optics is a new Oxford University start-up building next-generation hyperspectral cameras. We are creating a leap forward in our capacity to easily see what is invisible to the naked eye. Using a combination of patented optical methods, machine learning, and applied mathematics, we are radically miniaturizing hyperspectral photography, bringing down costs while improving performance.
We're building a world-class team to bring our hyperspectral vision to life, and are looking for engineers who are excited for the challenge!
It reminds me of a Star Trek tricorder. Imagine having a camera where you can see easily ID greenhouse gases, quantify water/fat content in food, identify plant diseases, verify drug components, identify tumours, and measure blood oxygenation. On the machine vision side of things: it could probably outperform any conventional imaging + DNN combination, and you'd probably get pixel-wise segmentation for free while you're there.
There's been a lot of academic progress going on - it shouldn't be long until hyperspectral imaging makes its way into our lives.