Looking for Feature descriptors mapped with Feature ID
Nobody has claimed this yet.
Assessment
- Difficulty
- 5/5
- Estimated time
- Over a week
- Newbie friendliness
- 25/100
- Issue type
- Feature
- Clarity
- Needs clarification
- Activity status
- Stale
- Tech stack
- numpy, opencv, python
- Domain
- computer-vision
Research direction
Start by examining tracks.csv alongside the per-frame npz data, including descriptors.npy and points.npy, to determine what identifiers and ordering are available. A complete result would map each feature ID to its descriptor, track ID, and image ID, with the proposed database structure documented or implemented.
Written by the indexing model from the issue text.
Description
I'm looking for feature descriptors for their respective feature id. I haven't been able to fetch that.
However, I found a npz array with respect to each image frame(which has points, instances, descriptors etc.)
-
Size of descriptors.npy (numpy array): [5716,128]
-
Size of points.npy (numpy array) - [5716,4]
So, for every feature point, there exists a feature descriptor. But I'm not able to map these feature points to their respective feature id's. (Feature ID's that you obtain in tracks.csv)
Can someone point out some resources? which can help in my case.
Potentially, aim to develop a db of feature id's & their respective feature descriptors, along with track id's and image id's.
- Dominant language
- Python
- Stars
- 3.8k
- Forks
- 898
- PR merge metrics
- No merged PRs in 30d
Getting set up
- No Dockerfile or Docker Compose file
- No pull request template
- Read the contributing guide
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.
More from mapillary/OpenSfM
-
Difficulty 2/5 1-3 hours Newbie friendliness 74/100
-
Potential compatibility issues with matplotlib.cm.get_cmap (Incompatible with Matplotlib 3.9.0)Open
Difficulty 2/5 1-3 hours Newbie friendliness 65/100
-
The streetOpen
Difficulty 5/5 Over a week Newbie friendliness 10/100
-
Difficulty 4/5 3-5 days Newbie friendliness 45/100
-
Issue with ODMOpen
Difficulty 4/5 3-5 days Newbie friendliness 35/100
All issues in mapillary/OpenSfM
Similar issues
-
Difficulty 2/5 1-3 hours Newbie friendliness 82/100
aicell-lab/bioengine#232 ·
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 74/100
modelscope/evalscope#1836 ·
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
-
bug
Difficulty 1/5 Under an hour Newbie friendliness 78/100
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
jbaruch/speaker-toolkit#480 ·
Maintainers usually reply within 1 day