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

skeleton mediapipe #2

Open
animeesh opened this issue Dec 23, 2021 · 1 comment
Open

skeleton mediapipe #2

animeesh opened this issue Dec 23, 2021 · 1 comment

Comments

@animeesh
Copy link

is there any way we can keep anything instead of a skeleton ?
like a cartoon hand.

@ibaiGorordo
Copy link
Owner

Hi,

It will depend on how you want to overlay it, but it should be possible. You need to select few points (2, 3 or 4) in the origin (carton) image, and you just need to calculate the transform matrix between the coordinates of those points in the cartoon image and in the detected body landmarks. If you check the code, you will see the example for 2 (for the bones) and 3 points (for the torso and head). In the case of 4 points, instead of an affine transform, you should estimate the perspective transform.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants