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

Coordinate Transform #6

Closed
rland93 opened this issue Oct 30, 2021 · 4 comments
Closed

Coordinate Transform #6

rland93 opened this issue Oct 30, 2021 · 4 comments
Assignees
Labels
odcl Object Detection, Classification, and Localization

Comments

@rland93
Copy link
Member

rland93 commented Oct 30, 2021

We need to transform the coordinate system from image coordinates to "world" coordinates. We use this by leveraging the information that we know about the system:

  • Current heading
  • Current altitude
  • Camera FOV, vertical and horizontal

We need to compute the transform between the camera coordinates to world coordinates, as shown in this image:
coords

Finding this transformation is related to finding the viewing frustum.

Unfortunately, we will not be able to test your solution until we do an actual flight test with localization.

@rland93
Copy link
Member Author

rland93 commented Nov 17, 2021

this was fixed in #9 but I want to review before closing

@rland93 rland93 added this to the 0.1.0 Release milestone Apr 13, 2022
@rland93 rland93 self-assigned this Apr 13, 2022
@rland93 rland93 added the core label Apr 13, 2022
@rland93
Copy link
Member Author

rland93 commented Apr 13, 2022

Added 714a793

But leaving open pending integration.

@rland93
Copy link
Member Author

rland93 commented Apr 21, 2022

Since this isn't integrated yet, I'm going to move it to an unspecified (later) release.

@rland93 rland93 added odcl Object Detection, Classification, and Localization and removed core labels Apr 23, 2022
@rland93 rland93 removed this from the 0.1.0 Release milestone Apr 23, 2022
dangthanhan507 referenced this issue May 6, 2022
@rland93
Copy link
Member Author

rland93 commented May 6, 2022

@dangthanhan507 Looks good. Yeah, that is intentional, since we want as much surface area in the python package rather than in the ROS codebase. The merging of attitude data and object coordinate data will have to happen in #54

@rland93 rland93 closed this as completed May 26, 2022
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
odcl Object Detection, Classification, and Localization
Projects
None yet
Development

No branches or pull requests

2 participants