View Single Post
  #3   Spotlight this post!  
Unread 07-01-2012, 22:10
biojae's Avatar
biojae biojae is offline
Likes Omni drives :)
AKA: Justin Stocking
FTC #5011 (BOT SQUAD) && FTC#72(Garage bots)&& FRC#0399 (Eagle Robotics)
Team Role: College Student
 
Join Date: Oct 2008
Rookie Year: 2008
Location: Lancaster
Posts: 276
biojae is a jewel in the roughbiojae is a jewel in the roughbiojae is a jewel in the rough
Re: Detecting the vision target

Quote:
Originally Posted by Greg McKaskle View Post
The LV installation contains a new example for rectangular image processing. Additionally, there should soon be a white paper posted to the NI site that will explain a few approaches.

The most obvious approach is to use the rectangle fit function, but it is quite picky, expecting angles to be quite close to 90 degrees and lines to be quite straight. Distortion due to lens and position easily cause the rectangle definition to fail its requirements.

The example in LV is particle based, and scores the particles for rectangularity, aspect ratio, and edge strength. If they score above the limits, the position and distance are calculated.
Is this example in the other languages? (C++, Java)
I don't have the software installed and updated yet.

Quote:
If the paper doesn't make it up soon, I'll be happy to answer other questions.

Greg McKaskle
Thank you very much.

EDIT:
Does the example depend on the lighting source being a certain color?
and does the distance calculation account for which target is seen (I would assume that it doesn't)?
__________________
FTC Team 72 - No site
FRC Team 399 - http://www.team399.org
2010 Rockwell Collins Innovation in Control Award - (Use of the CAN bus, among other reasons) Phoenix, Arizona!

Last edited by biojae : 08-01-2012 at 00:43.