Megvii-BaseDetection / Megvii-BaseDetection/BEVStereo
Why there are two kinds of ego2global.
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 282
- Forks
- 14
- PR merge metrics
- No merged PRs in 30d
Description
Hi,
I'm confused about the two kinds of ego2global value in the line 342 and in the line 419.
Why there are two kinds of ego2global.
What's the difference between them.
# Get mean pose of all cams.
ego2global_rotation = np.mean(
[key_info[cam]['ego_pose']['rotation'] for cam in cams], 0)
ego2global_translation = np.mean(
[key_info[cam]['ego_pose']['translation'] for cam in cams], 0)
# sweep ego to global
w, x, y, z = cam_info[cam]['ego_pose']['rotation']
sweepego2global_rot = torch.Tensor(
Quaternion(w, x, y, z).rotation_matrix)
sweepego2global_tran = torch.Tensor(
cam_info[cam]['ego_pose']['translation'])
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start in dataset/nusc_mv_det_dataset.py at the cited lines 342 and 419, then trace how cam_info and key_info provide their ego_pose values. Compare the sweep pose with the mean pose used for the key frame, and document the distinction and why each is used.】【。
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision
- Issue type
- Documentation
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 30/100