-
Notifications
You must be signed in to change notification settings - Fork 4.8k
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
question about align the color and depth image #9001
Comments
Hi @yuan0623 If you are aligning in librealsense with the Align Processing Block (align_to) then the processing block resizes the field of view (FOV) size of the stream that is being aligned to the FOV size of the stream that is being aligned to. So if depth to color alignment is being performed then the depth FOV is resized to the color FOV size. On the D435 / D435i models where the color FOV is smaller than the depth FOV, this can cause the outer regions of the depth image to be cut off. The opening section of the documentation for the SDK's C++ rs-align example provides further information about the principles of alignment. https://github.com/IntelRealSense/librealsense/tree/master/examples/align |
Hi Marty, Thanks again for your patience explanation, Here is my understanding:
|
Whilst you can custom-define the size of the image resolution for each stream type in the roslaunch instruction or in the launch file (e.g 848x480 for both depth and color), as far as I know align_depth does not change the intrinsics of the individual streams. |
MartyG Thanks so much for your explanation! Best |
You are very welcome @yuan0623 - thanks very much for the update! |
Issue Description
I have a question about the align the color and depth image.
What exactly is aligned here?
I use
roslaunch realsense2_camera rs_camera.launch align_depth:=true
, and I check the camera info from/camera/aligned_depth_to_color/camera_info
and/camera/color/camera_info
, I find that they have same K (intrinsic).Then my understanding is: align means to make sure the color camera and depth camera have the same K (intrinsic)
However, in my cpp project, the camera intrinsic between the color camera and depth camera is still different after I aligned them. So what exactly are aligned here? Am I doing it wrong?
Here is my cpp code for aligning the color camera and the depth camera:
However, from the output, we know that the intrinsic of the color camera and the depth camera is not the same.
Am I understanding it wrong?
Best
Yuan
The text was updated successfully, but these errors were encountered: