rail-berkeley/bridge_data_v2

Request for Camera Intrinsics and Association Details

XuweiyiChen opened this issue · 2 comments

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.

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

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?