Forum

Author Topic: Quality measure of keypoints/tiepoints  (Read 1435 times)

UAV_project

  • Newbie
  • *
  • Posts: 25
    • View Profile
Quality measure of keypoints/tiepoints
« on: April 09, 2020, 03:57:43 PM »
Hey guys,

I found in previous posts that I can use the projections of the tie points to find the pixels which match within different images. However, I am now wondering, is it possible for me to get some information on how confident the algorithm is that these points are matched? Something like a similarity score for a given projection track?

Thanks!

UAV_project

  • Newbie
  • *
  • Posts: 25
    • View Profile
Re: Quality measure of keypoints/tiepoints
« Reply #1 on: April 14, 2020, 09:41:11 AM »
Any ideas on this? From searching to forums it seems no one has ever asked this question before, and there is no mention within the user's manual, but maybe someone has a hack for how I could achieve this?

UAV_project

  • Newbie
  • *
  • Posts: 25
    • View Profile
Re: Quality measure of keypoints/tiepoints
« Reply #2 on: April 16, 2020, 12:20:08 PM »
Sorry to keep bumping this, but maybe it is not clear what I meant with 'Quality'. I know there are measures (reprojection error, reconstruction uncertainty, projection accuracy) that are associated to the tie points, but these are not what I mean.
I am wondering if there is also a 'dissimilarity' score which is based on the features of the pixels (shape, color, ect). This would help us to correct our images which were accidentally taken using automatic exposure settings (so exposures were not constant).

Thanks!

Alexey Pasumansky

  • Agisoft Technical Support
  • Hero Member
  • *****
  • Posts: 14813
    • View Profile
Re: Quality measure of keypoints/tiepoints
« Reply #3 on: April 19, 2020, 11:55:23 PM »
Hello UAV_project,

Such information if not stored in the project after the process is completed. However, even if it is saved, it wouldn't be informative in the current state of implementation, as the metric used is not that sensitive to the exposition, as it is intentionally selected in such a way in order to provide the corresponding points effectively between the images with the different exposure.

You can try to use Calibrate Colors option to reduce the unwanted effect from the images taken with the different camera serttings.
Best regards,
Alexey Pasumansky,
Agisoft LLC