JuliaImages / JuliaImages/ImageTracking.jl

FYI SensorFeatureTracking.jl, maybe good overlap

Open
#17 1 comment 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Julia
Stars
27
Forks
9
PR merge metrics
No merged PRs in 30d

Description

Hi,

Just wanted to mention work on KLT tracking from a few months back, but we have been bad about tagging and upkeep. Just wanted to share in case you had not seen this before -- package is through initial development but not registered yet:
https://github.com/JuliaRobotics/SensorFeatureTracking.jl

Let us know if you have any preference for future work etc. Robotics really likes to use KLT, and we were thinking about reaching out to JuliaImages but hadn't gotten so far. Probably better to have images code in JuliaImages and then JuliaRobotics can import and build on that?

I think we would want to build out things like 2D and 3D point cloud tracking; various camera feature tracking methods; etc. I would like to combine the code with filtering and estimation frameworks, and start down the path of data-fusion, but this will take a good while to happen. The original idea behind SensorFeatureTracking was anything in scope of tracking (such as this early 2D laser scanner Vimeo)

AprilTags.jl might also be of interest.

Thanks for putting this out there -- very cool! Maybe we can move the conversation if there is a better venue?

cc @Affie, @AndreHat, @rdeits, @pvazteixeira

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

The issue points to SensorFeatureTracking.jl and mentions AprilTags.jl, but names no file, test, or concrete change in ImageTracking.jl. Start by reviewing the linked package and discussing scope with the maintainers. Done would require an agreed, specific tracking feature and acceptance criteria rather than the broad future-work ideas listed here.

Written by the indexing model from the issue text.

Assessment

Tech stack
julia
Domain
computer-vision
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
15/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.