Sitelet https://web.archive.org/web/20220522022529/https://github.com/google/mediapipe/issues/1452
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

Jump to bottom

Getting the landmark data every frame for the new holistic model (Extracting Landmark Coordinate Data) #1452

Open
pkaske opened this issue Dec 29, 2020 · 5 comments
Open

Getting the landmark data every frame for the new holistic model (Extracting Landmark Coordinate Data) #1452

pkaske opened this issue Dec 29, 2020 · 5 comments
Assignees
@ivan-grishchenko
Labels
good first issue solution:holistic stat:awaiting googler type:research

Comments

@pkaske
Copy link

@pkaske pkaske commented Dec 29, 2020 •
edited

I figured out a way to get the (x,y,z) data points for each frame from one hand previously. but im not sure how to do that for the new holistic model that they released. I am trying to get the all landmark data points for both hands as well as parts of the chest and face. does anyone know how to extract the holistic landmark data/print it to a text file? or at least give me some directions as to how.

(please note i got this done successfully in python, but now want to do it in c++)
@pkaske pkaske changed the title Getting the landmark data every frame for the new holistic model Getting the landmark data every frame for the new holistic model (Extracting Landmark Coordinate Data) Dec 29, 2020
@eknight7
Copy link
Collaborator

@eknight7 eknight7 commented Jan 29, 2021

Hi - definitely - extracting landmarks should be similar to extracting landmarks as shown in other MediaPipe solutions. Where are you trying to do this exactly?

@eknight7 eknight7 self-assigned this Jan 29, 2021
@eknight7 eknight7 added good first issue solution:holistic type:research stat:awaiting response labels Jan 29, 2021
@shadow111
Copy link

@shadow111 shadow111 commented Feb 25, 2021

Hi - definitely - extracting landmarks should be similar to extracting landmarks as shown in other MediaPipe solutions. Where are you trying to do this exactly?

can you please put me on the right track i want all the landmarks together but still can't figured it out

@pkaske
Copy link
Author

@pkaske pkaske commented Feb 25, 2021 •
edited

Hi - definitely - extracting landmarks should be similar to extracting landmarks as shown in other MediaPipe solutions. Where are you trying to do this exactly?

well last time i used the landmark_letterbox_removal_calculator.cc file (mediapipe/mediapipe/calculators/util/landmark_letterbox_removal_calculator.cc) and just printed the x,y,z coordinates for the 21 landmarks (one hand) by manually creating a .txt that wrote them every frame. but I'm not sure how to do that for the new holistic (how/where do i do that? what calculators,etc). I need both the hands now (21 points each) plus some of the pose coordinate landmarks as well. so how do i do that all at once
@ivan-grishchenko
@eknight7

@sgowroji sgowroji added stat:awaiting googler and removed stat:awaiting response labels Mar 24, 2021
@SayedHamdiF
Copy link

@SayedHamdiF SayedHamdiF commented Apr 1, 2021

@pkaske
could you please share with me code i want to save all keypoints in csv files. untill now i ca't , please help

@Wansh619
Copy link

@Wansh619 Wansh619 commented Feb 21, 2022

is this issue still open?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@ivan-grishchenko ivan-grishchenko

Labels
good first issue solution:holistic stat:awaiting googler type:research
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
7 participants
@eknight7 @ivan-grishchenko @shadow111 @sgowroji @pkaske @SayedHamdiF @Wansh619