Better matching for the input images by yaw, pitch, roll
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 3.8k
- Forks
- 899
- PR merge metrics
- No merged PRs in 30d
Description
Hello,
There is ongoing discussion in https://t.me/openaerialmap on how to best work with oblique imagery in OpenDroneMap. Distance-based matching does not seem to help much, so @aliaksandr960 implemented a prototype for matching based on imagery view cones intersection if the yaw, pitch, roll angles are recorded in the data. Could you please guide us what would be the best way to contribute this into OpenSfM?
https://github.com/aliaksandr960/opensfm_pairing_draft/blob/main/cone_pairing_opensfm.ipynb
Contributor 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.
Research direction
Start by reviewing the linked cone_pairing_opensfm.ipynb and the OpenSfM matching-related entry points to understand the prototype and how yaw, pitch, and roll are represented. Before implementation, clarify the intended scope, supported input data, tests, and acceptance criteria with the maintainers; the issue currently does not define what done looks like.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100