3

I need to start learning about video stitching. I have studied about this and have some knowledge that the video should be converted into image sequences, then image alignment is done [geometric and photometric correction], and feature matching is used to match two video frames which are then blended together.

I don't know whether this is correct and I need to know if this process is correct and is there anything I missed? Is there anything I need to learn? Also I need to learn from basics. I want some knowledge about this.

  • Can you post a link to an example of what you're looking to do? There are lots of papers from SIGGRAPH on topics like this, but I'm not sure which ones to point you towards because it's not clear what your goal is. – user1118321 Jul 10 '15 at 15:47
  • airpano.com/360-videos.php – krishnakumar Jul 11 '15 at 6:35
  • Note a video is a image sequence so expanding it into individual files or reading individual frames from a stream is the same thing in a different wrapper. – joojaa Jul 15 '15 at 17:57
2

I've found 2 useful references:

LEVIN, A., ZOMET, A., PELEG, S., AND WEISS, Y. 2004. Seamless image stitching in the gradient domain. In European Conference on Computer Vision, 377–389.

and

PÉREZ, P., GANGNET, M., AND BLAKE, A. 2003. Poisson image editing. ACM Transactions on Graphics (SIGGRAPH ’03), 313– 318.

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

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