I have three cameras separated by some distance, looking at a scene. I have calibrated them using checkerboard and I have their respective intrinsic parameters and their pose and rotation matrix, I am stuck as to how to do data/image fusion.

I think I have to do feature detection and feature matching and then do data fusion but I am not sure if I am on the right path.

Would be very helpful if anyone can point me to some answer or help me with it.

Or if I am wrong then what is the right method or steps to follow?

Would be really helpful even if someone can point to a resource or just guide. Thank you, good people

  • $\begingroup$ You should define data/image fusion clearly. As it is, it is difficult to understand what you are trying to do. $\endgroup$ Commented Jan 11, 2019 at 0:24

1 Answer 1


What do you mean by data fusion

Here's some definitions I can think of:

  1. Determine from the features in the scene the positions of the camera
  2. Determine from the positions of the camera the geometry of the scene
  3. Determine from the features of the scene the intrinsic parameters of the camera.

Since you say you have fully calibrated the three cameras jointly using a checkerboard, then 1 and 3 are done. That must leave 2.

Estimating positions of features, or structure from motion

To estimate the position of a feature in the world, you first define what features. All pixels? That would be called disparity mapping Just a few features? That you can do with triangulation.

  • $\begingroup$ I guess this is what I was looking for, thank you so much. $\endgroup$ Commented Jan 14, 2019 at 17:00

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.