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

Request for Camera Intrinsics and Association Details #22

Open
XuweiyiChen opened this issue Oct 30, 2023 · 2 comments
Open

Request for Camera Intrinsics and Association Details #22

XuweiyiChen opened this issue Oct 30, 2023 · 2 comments

Comments

@XuweiyiChen
Copy link

I'm currently working on a project that makes use of the images and trajectory data from bridge data v2. To fully utilize this data, I would like to the camera intrinsics for each camera used.

Specifically, I would like to know:

  • Camera intrinsics for each camera being used
  • Association of each camera with the corresponding trajectory data.
  • Association between each camera and the corresponding images folder.

I see camera's assignment and depth camera's assignment from the config:

  "camera_topics": [
      "/D435/color/image_raw",
      "/yellow/image_raw",
      "/blue/image_raw"
  ],
  "depth_camera_topics": [
      "/D435/depth/image_rect_raw"
  ],

However, can you point me where I will be able to find camera intrinsics? Many thanks in advance.

@HomerW
Copy link
Contributor

HomerW commented Nov 2, 2023

We mostly used Logitech C920 webcams, though some of the data uses an Intel RealSense D435 for the fixed camera view. All of the wrist camera images are from an Arducam. The setup guide has specific links to the exact models so that you can look up the intrinsics.

Each data collection attempt folder in the raw data (e.g. bridge_data_v2/datacol2_toysink2/pnp_push_sweep/00/2023-06-13_15-08-44) has a file config.json with the camera topics. The order of the cameras in this list determines how the images get labeled. The first camera is associated with the image folder images0, the second is associated with images1 etc. The mapping between names of topics and cameras is:

  • "/D435/color/image_raw" -> RealSense D435
  • "/yellow/image_raw", "/blue/image_raw", "cam0/image_raw", "cam1/image_raw", "cam2/image_raw" -> Logitech C920
  • "/wrist/image_raw" -> Arducam

@archana53
Copy link

archana53 commented Mar 5, 2024

Hi @XuweiyiChen ,

Were you able to figure out this: "Association of each camera with the corresponding trajectory data"? How did you convert from the world coordinates to the camera coordinates?

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