Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[iOS] video vs livestream model coordinates #5780

Open
mosolab opened this issue Dec 15, 2024 · 0 comments
Open

[iOS] video vs livestream model coordinates #5780

mosolab opened this issue Dec 15, 2024 · 0 comments
Assignees
Labels
platform:ios MediaPipe IOS issues task:hand landmarker Issues related to hand landmarker: Identify and track hands and fingers type:support General questions

Comments

@mosolab
Copy link

mosolab commented Dec 15, 2024

Hi team!

Have question about hand landmark detection model modes for iOS and outputs.
Now experimenting with two options to initialise HandLandmarker on iOS:

  • options.runningMode = .video
  • options.runningMode = .liveStream

Landmarks output seems to differ for these two modes.

Here [https://ai.google.dev/edge/mediapipe/solutions/vision/hand_landmarker] mentioned different types of output for decoded video frames and live video feed as:

  • Landmarks of detected hands in image coordinates
  • Landmarks of detected hands in world coordinates

What is difference and is there a way to convert them between each other?

@mosolab mosolab added the type:others issues not falling in bug, perfromance, support, build and install or feature label Dec 15, 2024
@kuaashish kuaashish added type:support General questions platform:ios MediaPipe IOS issues task:hand landmarker Issues related to hand landmarker: Identify and track hands and fingers and removed type:others issues not falling in bug, perfromance, support, build and install or feature labels Dec 16, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
platform:ios MediaPipe IOS issues task:hand landmarker Issues related to hand landmarker: Identify and track hands and fingers type:support General questions
Projects
None yet
Development

No branches or pull requests

2 participants