Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Get points cloud with actual GPS #242

Open
cst2825023 opened this issue Jun 13, 2019 · 4 comments
Open

Get points cloud with actual GPS #242

cst2825023 opened this issue Jun 13, 2019 · 4 comments

Comments

@cst2825023
Copy link

Hello,
I have some images taken from a drone with known GPS positions. I'd like to use those positions within Hybid-Sfm to get points cloud with actual GPS, but I don't know where to start. Would it be possible to provide camera GPS positions to the application build_reconstruction?
Any help on this would be very grateful. Many thanks for this useful library!

@sweeneychris
Copy link
Owner

sweeneychris commented Jun 13, 2019 via email

@cst2825023
Copy link
Author

Thank you for your reply. I have a few questions below. Firstly, I have input images with GPS information in the metadata, and converted to ECEF. But the points cloud position generated by Hybid-Sfm are random. I want to know if I need to convert reconstruction points to actual coordinate system using actual camera position by myself or modify part codes in sfm to combine points with actual GPS.

@sweeneychris
Copy link
Owner

sweeneychris commented Jul 6, 2019 via email

@Aleksei91
Copy link

Can I modify bundle adjustment somehow to use prior information about camera position, so result of reconstruction/pose estimation whould not differ much? Now I sometimes get dramaticaly wrong reconstruction results (camera positions almost random), maybe I can improve it with this info or it's useless and my photos just too hard for feature matching?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants