Stereo Match of equirectangular panorama images

asked 2017-04-09 13:48:01 -0600

NMisko
26 ●3

Hi there,

I've got two equirectangular panorama images, out of which I'd like to calculate a 3D point cloud of the surroundings.

Simply using 'samples/python/stereo_match.py' obviously yields a wrong image, due it expecting undistorted images.

How do I convert or undistort the panorama images such that stereo match is usable? Or should I use some other way?

Any help or suggestion is very appreciated.

edit retag flag offensive close merge delete

add a comment

1 answer

Sort by » oldest newest most voted

answered 2017-04-09 17:04:27 -0600

liquidmetal
71 ●3 ●8

Matching feature points directly won't work, as you've already discovered. There are two issues that you want to solve.

1) Use a narrower field of view. You can reproject pixels from the spherical map onto an image plane with a narrower fov. This would produce regular looking images on which you can use the standard feature matching techniques, computing the fundamental matrix, etc. You're looking for the inverse spherical projection equations for this.

2) Register the two panoramas. It is likely that the two panoramas are relatively shifted. Is the object at the left-most edge of the first panorama the same as in the second one?

Hopefully this helps!