mapillary / mapillary/OpenSfM

Question : How to extract 3D feature coordinates in WGS84

Open
#961 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
3.8k
Forks
899
PR merge metrics
No merged PRs in 30d

Description

Hi,

I am totally new to Opensfm, I am exploring to find out the 3D feature coordinates specifically the z coordinate. As in tracks.csv - there is no z coordinate.

Potential Approach: I thought was-
merged.ply gives out - x, y,z , nz, ny, nz , r, g, b
tracks.csv gives out - image_id, track_id, feature_id, x , y, r, g, b,

So if I find an x,y from the tracks.csv and run through the merged.ply after parsing it, I'll be able to find the z coordinate of the features.

I am not sure if my approach is correct or not. If not, please guide me with the same. The end goal is to find the 3D coordinates in WGS84 format.

Contributor guide

Open the contributing guide

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

Start with the relationship between tracks.csv and merged.ply, including their image, track, feature, and coordinate fields. Determine whether matching the listed x,y values identifies the corresponding 3D point and what is required to express that point in WGS84; done means documenting a reliable extraction path or explaining why the proposed approach is insufficient.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.