Hi everyone,
I had a small project in mind for some years now, and OpenCV might help me resolve it (hopefuly). I've read quite a bit (but surely not enough for some) on camera vision these days and I'd like to know if this would be do-able. To my point of view the answer is yes, but I need some guidance to start.
I'm trying to achieve a sub-mm precision on objects that moves in 3D from mm/sec to 100mm/sec. The frame -to begin with- will be 1500mm*1000mm.
I've seen projects that base their precisions on pixels fading and weight computation and achieve pretty good results (>0.1mm) but don't mention any environnement condition that could distord the results through time.
In order to move to this project with enough details, I'd like to have some information: Are 2 cameras enough ? I've read that a 3rd could help remove the blur and increase the precision, but is this enough, shall I order 100 of camera then :) ? If so, can OpenCV handle more than 2 camera without help of GSvideo ? Is a 4K camera needed? I'd say no, thanks to the spec of the IMX219PQ (but only one port to Raspberry...) To track with more accuracy with less filters, are IR trackers a good solution ?
Thanks in advance for your kind remarks and explanation. See you soon Philippe