Subject:
|
Re: Working motorized focus for Vision Command
|
Newsgroups:
|
lugnet.robotics
|
Date:
|
Wed, 18 Dec 2002 16:59:07 GMT
|
Viewed:
|
1050 times
|
| |
|
|
In lugnet.robotics, Timothy Schroeder writes:
> I have no idea how to access the camera from a programming language, nor do
> I have any experience in raw vision proccessing. Do you know how to do any
> of these previously meantioned?
>
> Timothy
Timothy,
One source of inspiration for the focusing algorithm is to look at codes
that expand the depth of focus by stitching together the in-focus portions
of multiple images. This is used in microscopy quite a bit. The software has
to be able to identify which portions of the picture are in-focus. Here is a
link to a description of the technique: http://www.sgi.com/grafica/depth/.
One of the steps is to detect edges. ImageMagick will do that
http://www.imagemagick.org.
Good luck,
Andy
|
|
Message has 2 Replies:
 | | Re: Working motorized focus for Vision Command
|
| But how to I "weave" the SDK and the algorithms IN VC++? I am only wondering if this idea of an autofocusing lego cam is feasible. One day I may learn enough VC++ to be able to acomplish this project :-) I'm glad to know there is hope! Timothy (...) (22 years ago, 18-Dec-02, to lugnet.robotics)
| | | Re: Working motorized focus for Vision Command
|
| (...) from one end to another taking pictures as you go, and selecting the best parts of each, you'd end up with better-than-perfect focussing. I guess you'd want to be careful to mount the camera very rigidly so it doesn't wobble as you drive the (...) (22 years ago, 19-Dec-02, to lugnet.robotics)
|
Message is in Reply To:
15 Messages in This Thread:
 
 
- Entire Thread on One Page:
- Nested:
All | Brief | Compact | Dots
Linear:
All | Brief | Compact
This Message and its Replies on One Page:
- Nested:
All | Brief | Compact | Dots
Linear:
All | Brief | Compact
|
|
|
|
