google-ai-edge / mediapipe

Cross-platform, customizable ML solutions for live and streaming media.
https://ai.google.dev/edge/mediapipe
Apache License 2.0
26.82k stars 5.09k forks source link

multipleperson pose estimation using mediapipe #4261

Closed sidh1603 closed 1 year ago

sidh1603 commented 1 year ago

Hi,

I want to pose estimation for multiple person using media pipe , Would it be possible to make a multiple pose detection on MediaPipe?

even i tried to find solution on this link https://github.com/Gidrian/Mediapipe-YOLO_Multiperson.git but this link is no more active.

Thanks

kuaashish commented 1 year ago

Hello @sidh1603, Thank you for your interest in MediaPipe Solutions, BlazePose, Pose model can only detect single person from a image/video frame cropped to contain only one person. If you check page 4->Attributes section of Pose Model Card, you will find the following information:

Human Full-body cropped from the captured frame should contain a single person placed in the center of the image.

google-ml-butler[bot] commented 1 year ago

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you.

google-ml-butler[bot] commented 1 year ago

Closing as stale. Please reopen if you'd like to work on this further.

google-ml-butler[bot] commented 1 year ago

Are you satisfied with the resolution of your issue? Yes No

adrianloy commented 8 months ago

This is actually now supported directly by mediapipe, just set the num_pose parameter to something greater than 1, see https://developers.google.com/mediapipe/solutions/vision/pose_landmarker. However, I found the performance for detecting multiple person not to be very high.