Nodh's profile - activity

Thank you Tetragramm ! Have you performed some precision benchmark on your tool ? Any paper on what method is used in your code ?

This might be (old but) useful: http://cmp.felk.cvut.cz/~svoboda/Self...

Thanks again!

Sorry for the late reply.

It's because I read what was possible that I thought this project could help me.

Now, I'll be more than happy to learn about more suitable methods.

Please do share with us what technics you would use.

That will definitly help me ..and maybe others not to do the same mistake.

Cheers

Sorry for the late reply. Thanks for your answers.

I'll try the tracking ball exercice and let you know how wrong it goes :) Thanks again!

Not obviously real time, but as close as possible.

If I have to slave a XU4 board/camera to filter the frame and use parallel computing after, on order to keep the posttreatment fast, then why not.

Isn't timing, alignment and calibration already a stereovision problem? I''ve read a multicamera-auto-calibration paper done with a laser that works pretty well (as point is fixed, timing isn't answered :))

Because my hands aren't dirty -yet-, I can't figure out why this is a great issue. A lot of projects involve large views, speed detection and mm precisions (biomeca, sismic, traffic...).

I'm not forcing you to say "this is great, go on!"... Just want to understand the amateur feasable range :) Readings on the difficulties are more than welcome.

Thanks again for your valuable comments

(Sorry, the layout always comes wrong...)

Thank you matman for your quick answer.

I may have set my expectations too high. For my defense, as I've felt on this 2012-paper http://www.series.upatras.gr/userfiles/6_Peloso.pdf (http://www.series.upatras.gr/userfile...) I thought that 2016-technics could now achieve it with off the shelf products.

Anyway, let's correct my enthusiasm to achievable results (with your advice): Frame: 500*300mm Precision: 0.5mm From some camera spec, this seems to be more realistic.

I don't get your 2, can't variation be limited with redundancy ? 3. I understood that objective distortion affects all kind of camera. It just need to be sorted out individuality before and then, with all the cameras, isn't it.? 4 and 5: Is it more computational expensive (like... linear?) to process 4K@30fps or 720HD@200fps ? @200fps do you still get blurred images

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