Overlap filter doesn't work on segmented models, converts masks to bounding boxes
Open
Nobody has claimed this yet.
bug
- Dominant language
- Python
- Stars
- 2.5k
- Forks
- 319
- Avg merge
- 1d 14h
- Merged PRs (30d)
- 133
Description
Search before asking
- I have searched the Inference issues and found no similar bug report.
Bug
The code here implicitly converts segmented/masked Dectections to its xy-xy defined bounding box, which causes incorrect overlap detection in the case of irregularly shaped segments without any warning to the user
Environment
No response
Minimal Reproducible Example
No response
Additional
No response
Are you willing to submit a PR?
- Yes I'd like to help by submitting a PR!
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 with inference/core/workflows/core_steps/analytics/overlap/v1.py and trace how segmented Detections are handled during overlap checks. Reproduce the behavior with irregularly shaped masks, then verify that overlap detection no longer silently treats them as bounding boxes; add regression coverage if the surrounding test structure identifies a suitable location.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Active
- Clarity
- Mostly clear
- Newbie friendliness
- 65/100