Hi,

 

I’m prototyping some ideas concerning symbol grounding and cognition in the
context of AGI and would like to make use of vision. I’m looking for some
library or classes for Java that can do real time or “nearly real-time”
image/video processing.

 

I’m after either: fairly robust object segmentation; 2.5D or 3D
reconstruction; object recognition; or something like superquadric
reconstruction. Something that attempts to describe the physical structure
of the world seen through the camera.

 

I’m not actually after anything particularly fancy or general – I’m happy
even to craft the lighting and objects to suit the library – I’m more
interested in finding something that works reasonably well “out-of-the-box”
in some open ended domain so that I can conduct a few experiments. That is,
I’m after a library that does some kind of modest, but meaningful, image
processing.

 

I know this is possible – I see it done again and again at AI conferences;
but I can’t seem to be able to find any ready-to-use libraries for Java.
I’ve had a quick attempt at doing it myself, but used very naïve algorithms
and the result wasn’t very robust. I’d love to find something already
available before I dive deeper into the machine vision literature and
attempt to write my own.

 

I’m capturing video frames via the Java Media Framework, but could convert
the stream into images of any reasonable format.

 

Any pointers would be very much appreciated.

 

Thank you,

 

-Benjamin Johnston

-----
This list is sponsored by AGIRI: http://www.agiri.org/email
To unsubscribe or change your options, please go to:
http://v2.listbox.com/member/?member_id=8660244&id_secret=90512336-dca4e2

Reply via email to