0

I've been trying to read through the Stackoverflow questions for generating point clouds (x,y,z) coordinates from a left and right stereo image pair.

I haven't come to any definite solution, and I'm asking the community here for some help.

Problem statement: Given two stereo images, generate 3D (x,y,z) cartesian coordinate point clouds from those and do so in a way that lends itself to completing this point-cloud generation in a way that could work over a large set (thousands) of pairs of stereo images

My programming language experience lends itself to MATLAB, but I've dabbled in Python, and C++ is limited, but I may be able to work in that as well.

Speed is a factor here, so the the idea is to find a quick method of successively going through these pairs and generating the point cloud.

NOTE: I am not asking for the BEST as to avoid comparative solutions, I'm just asking for solutions.

Thank you very much!

Edit: After being recommended to utilize the Stereo Block Matching implementation in OpenCV, I may steer away from this method, as there is a wide variation in regards to texture of the topographical pictures that I'm dealing with.

black_bird
  • 115
  • 1
  • 5
  • 12
  • Have you looked at OpenCV? A better pointer could be found in this SO question: http://stackoverflow.com/questions/5893619/stereo-vision-with-opencv – seva titov Jun 01 '14 at 02:37
  • I have, but as it is robust I'm not aware of all of the features, I'll look at this right now! – black_bird Jun 01 '14 at 02:47

1 Answers1

0

What you probably want is called "Stereo Block Matching". If you don't feel like writing it yourself, OpenCV has an implementation ready to go (even a CUDA accelerated version).

Yeraze
  • 3,269
  • 4
  • 28
  • 42
  • After doing some light reading on Stereo Block Matching and block matching variations, is this a really good way to get even quasi-accurate point clouds? With a wide variance of textures present in the topography that I'm looking at, I don't know if this would be the answer. – black_bird Jun 02 '14 at 20:28