To LUGNET HomepageTo LUGNET News HomepageTo LUGNET Guide Homepage
 Help on Searching
 
Post new message to lugnet.roboticsOpen lugnet.robotics in your NNTP NewsreaderTo LUGNET News Traffic PageSign In (Members)
 Robotics / 12066
12065  |  12067
Subject: 
Re: Stereo Vision
Newsgroups: 
lugnet.robotics
Date: 
Thu, 10 Aug 2000 11:30:56 GMT
Original-From: 
Marco C. <marco@soporcel.pt(antispam)>
Viewed: 
1529 times
  
Yup :)

I thought of, *after dealing with the mono vision*, going for a stereo
approach, because this is one way of dealing with distance measuring, or at
least, better object evaluation/recognition.

At first I thought of using two USB cams, but then, after thinking about
the technical problems dealing with two video sources, I thought of that
solution exactly. Using a kind of technic common to professional binocullars:

    Left     Right
     :        :
    \:..\**/..:/
    *\  :\/:  /* 4 Mirrors
        :  :
       |:  :|
       Camera

Well... in theory this works, but, in practice, I was expecting
difficulties when setting the angles of the mirrors correctly.

If more motor outputs were available, one could control the outside
mirrors, to deflect or inflect (just like we do with the eyes)
With angle-sensors attached, one could even do a crude distance measuring,
when trying to focus an individual object/point of reference.

Anyway, without the pair of motor/angle-sensor attached, it's still
possible to do crude distance measuring with the fixed angle.

Like this, we get better edge/object recognition

Oh well... when I have the time... but, anyway :) Laurentino, keep us up to
date with your project :)

At 11:05 10-08-2000 +0100, you wrote:
Hi
As you may know my current project has everything to do with image • recognition.
I was reading one tread in this newsgroup and suddenly it struck me that
many of the problems I currently have in finding the contours of the
objects can be overcome it I have stereo vision!
Then I figured that the only way to do that with just one camera was if I
can place a set of mirrors in the front to the camera and split vertically
the image in two, each set of mirrors giving an image a few centimeters apart.
Then all I have to do is to compare the left and the right parts of the • images and find the differences between them.
Any thoughts about that?
Laurentino Martins

____________________
Marco C. aka McViper



Message is in Reply To:
  Re: O'Reilly book news
 
(...) That's certainly their choice. I just hope they realize it's sending a mixed message. If you don't know how to recognize an Amazon.com associate ID when you see one, it looks as though TLC is finally (yay) supporting these two wonderful books, (...) (24 years ago, 8-Apr-00, to lugnet.robotics) ! 

45 Messages in This Thread:



























Entire Thread on One Page:
Nested:  All | Brief | Compact | Dots
Linear:  All | Brief | Compact
    

Custom Search

©2005 LUGNET. All rights reserved. - hosted by steinbruch.info GbR