WHAT'S NEW


03/29/2019
 
Posted By: Ryan Weaver





Imagine that you are using robot vision to recognize an object. But, there's a problem! When you used the teaching mode, there was something unusual about the object outline in the camera. Perhaps the object's shiny surface had a bright spot, or the camera picked up too many detailed features. Now, whenever you try to detect objects with the vision system, it does not recognize the object because it looks different in the camera.

This is a common problem in robot vision.

Ideally, you want to teach your vision system with a model which is accurate and only contains the necessary features. If the model you teach it has flaws, the outline of the object will be harder to detect and this will reduce the effectiveness of the whole system.

But, there is an unusual trick you can use to improve the teaching mode and make it more robust.

Check out the blog post by Robotiq to see what it is.

Copyright © Axis New England. All rights reserved.
Twitter LogoLinked In LogoYouTube Logo
Powered by DreamingCode