Author Topic: What does stereoscopic vision not do?  (Read 548 times)

0 Members and 1 Guest are viewing this topic.

Offline jlrobodudeTopic starter

  • Jr. Member
  • **
  • Posts: 8
  • Helpful? 0
What does stereoscopic vision not do?
« on: March 10, 2012, 11:41:04 PM »
Dear forum,

I am wondering what some limitations to Stereo vision (2 cameras only) are. 
I know it gets tricky when something moves in front of another and stops (or does it? idk much about it). 
I find the field of stereoscopic image processing interesting . . . any help would be greatly appreciated.

Thank you in advance!

Offline mstacho

  • Supreme Robot
  • *****
  • Posts: 364
  • Helpful? 10
Re: What does stereoscopic vision not do?
« Reply #1 on: March 13, 2012, 11:11:44 AM »
A major issue (well, among many, many others) is that if your background is not textured enough, stereoscopic vision can have problems.  The overall goal is to be able to segment a vision stream into OBJECTS and BACKGROUND (well...simplificiation).  If your background is just a plain white wall, for example, then it might show up as being a distance of 0 away from the camera, since pixel matching or feature matching won't work.

Another major issue is segmentation.  how do you define an object?  When two books are on top of one another, are they two books or one object?  Why, and how do you explain that to a computer?

Ultimately, sterovision is great for giving you a depth map, as long as your background is textured enough.  But that's about it.  The rest is all processing!
Current project: tactile sensing systems for multifingered robot hands

Offline jlrobodudeTopic starter

  • Jr. Member
  • **
  • Posts: 8
  • Helpful? 0
Re: What does stereoscopic vision not do?
« Reply #2 on: March 13, 2012, 07:53:56 PM »
Thank you for your answer.  I just wanted to know.

 


Get Your Ad Here

data_list