I have a robotic application where I want to be able to create G-Code to select and then describe each object on a 610mm x 457 region of focus. I can place 1 or more cameras within 1m and can optimize the height for the application. The ROF will be stationary at the time of image capture. I can control the lighting through curtains or adding additional lighting.
I need g-code that is accurate to the .25mm or better. Is this a reasonable expectation/target to have? What accuracy should I be able to reach reasonably?
Nathan,
Thanks for the link to the datasheet. So using my distance, this would imply that I should not expect to get better accuracy than 11-12 mm. And certainly no where need my requirements of .25mm.
Am I understanding “Depth typical systematic error (accuracy)* < 11 mm + 0.1% distance” correctly?
Does running in stereo mode substantially improve this accuracy or tuning with HAAR? I am also going to a snapshot taken once the work has been positioned by the robot and stopped moving.
