I'm trying to reconstruct an objet from two images but the result is really poor. So I would like to know how to do a reconstruction using a bigger set of images, like 5 to 10 pictures for example.
You basically want to investigate structure from motion
https://docs.opencv.org/3.2.0/d4/d18/...
That the best match in OpenCV, but actually PCL would be a better framework for this!
Thank you for the comment Steven! I've seen this, but in my project I'm using Python. I belive that the only way to use more than two images is using the triangulatePoints() fungtions. So far I'm using the reprojectImageTo3D() function. If there was a way to use more than 2 images with reprojectImageTo3D() I would get better results.
Asked: 2018-01-12 07:22:14 -0600
Seen: 218 times
Last updated: Jan 12 '18
