microsoft / microsoft/GlobalMLBuildingFootprints

350.000 'buildings' in Spitsbergen

Open
#113 0 comments 2 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
2k
Forks
277
PR merge metrics
No merged PRs in 30d

Description

The dataset contains many false positive buildings around Spitsbergen. It seems that the algorithm may have difficulties with icebergs or rocks? They appear all around the island, but it seems most are in the sea right next to the coast.

There are false positives all around the world, but I haven't seen this many errors in one place yet.

image

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Begin by reproducing the Spitsbergen area from the dataset and reviewing the attached image, then trace the Python algorithm or model stage responsible for those detections. Done should mean the false positives are characterized and a concrete cause or correction path is established, but the issue names no files or tests to guide that work.

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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.