microsoft / microsoft/GlobalMLBuildingFootprints
Light Colored Roof -> False Negative
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 2k
- Forks
- 277
- PR merge metrics
- No merged PRs in 30d
Description
Hi, I've noticed a lot of missing buildings that have white roofs. Take the example below from suburban Dallas, Texas
The ML algo seems to miss a lot of these types of roofs, and was wondering if the algo could be trained to capture them more frequently.
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
The issue mentions no files, tests, or training entry points. Start by locating the model and training-data pipeline responsible for building-footprint detection, then establish a representative white-roof evaluation set and a measurable improvement criterion before attempting a fix.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision, machine-learning
- Issue type
- Bug
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100