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

About the result_pose #12

Open
MoronHugh opened this issue Jul 2, 2019 · 1 comment
Open

About the result_pose #12

MoronHugh opened this issue Jul 2, 2019 · 1 comment

Comments

@MoronHugh
Copy link

First, thanks for your sharing. But these days, I had been confused by the usage of result_pose that described in the paper with 27 parameters. Would you please to help me figure out the order of result_pose? I'm really want to verify the effect of this algorithm in the 3D space.

@padeler
Copy link
Member

padeler commented Jul 4, 2019

Hello,

The 27 parameters represent global position and orientation as well as finger joint angles. The global position and orientation are encoded in the first 7 numbers (3 translation + 4 quaternion rotation). The rest correspond to joint angles for each finger joint. The base of each finger has two degrees of freedom while the rest have only one.

You can "decode" these numbers into 3D points in space using the corresponding decode functions (check the code for an example). For more info about the hand parameters check the Oikonomidis et al, BMVC11 paper.

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