Hello guys…
was wondering if anyone has managed to get data from OpenCV vision software to OpenHab? Here I think of something like use OpenCV to read license plate, and if it fits open the garage door or something like that… I can see that it’s possible with OpenCV - but can’t find a solution to get the data to OH 
I would go about it the following way. I’d use the Python bindings for OpenCV, mainly because that is what most of my other outside of OH automation code is written in and put all the recognition in a separate Python service. When a detection event occurs I would publish this to MQTT using the Paho library.
I don’t know much about OpenCV, but since I’ve already written somewhat of a framework for supporting this sort of thing in Python I would probably try to make it a module on that.
Even if I risk the old warning “if all you have is a hammer, all problems look like nails.”
With this solution we could also use OpenCV to read out water meter status directly from the number wheels … the other thread about the water meter read out with reading the 3 wheels doesn’t work for me since I only have one, so for getting a more accurate result I think the OpenCV would be a better solution…
Then it sounds like it is " doable" to integrate a link from OpenCV to openhab…