How to generate these diagrams in your paper and save detected results of the 3D human skeleton?

[BenoitKAO]

How to generate these diagrams in your paper and save detected results of the 3D human skeleton? https://reurl.cc/Zn8RNp https://reurl.cc/A1XE9j https://reurl.cc/RdRK2Z https://reurl.cc/5gX7XM

Could you please give some video streaming examples for inputs as OpenPose that can generate output files in format? https://github.com/CMU-Perceptual-Computing-Lab/openpose/blob/master/doc/output.md

Thank you.

[kdy1999]

How to generate these diagrams in your paper and save detected results of the 3D human skeleton? https://reurl.cc/Zn8RNp https://reurl.cc/A1XE9j https://reurl.cc/RdRK2Z https://reurl.cc/5gX7XM

Could you please give some video streaming examples for inputs as OpenPose that can generate output files in format? https://github.com/CMU-Perceptual-Computing-Lab/openpose/blob/master/doc/output.md

Thank you.

It would be great if video streaming examples could be provided

[BenoitKAO]

Surely, this is the video streaming which is often demoed for the results (outputs) by using OpenPose:

Crazy Uptown Funk flashmob in Sydney https://www.youtube.com/watch?v=2DiQUX11YaY

Input: video stream

Output: https://github.com/CMU-Perceptual-Computing-Lab/openpose/blob/master/doc/output.md

In viz.py, I found: def draw_3d_pose(keypoints, ax, keypoints_mask=None, kind='cmu', radius=None, root=None, point_size=2, line_width=2, draw_connections=True):

However, you may not release source codes in using these methods for generating results.

Thank you.

[karfly]

Hi, @BenoitKAO and @junhao1999.

1. All plots of 3D skeletons are drawn with this function.

2. We're not planning to release a streaming demo. It's quite a difficult engineering task to implement a general multi-camera imaging pipeline, which will be common for all camera setups, due to variety of camera brands and SDKs. E.g. OpenPose supports multi-camera 3D human pose estimation only for FLIR cameras.

[BenoitKAO]

Thank you for your replay.

Could you give examples on how to use draw_3d_pose method to plot?

[karfly]

from matplotlib import pylab as plt
from mpl_toolkits.mplot3d import axes3d, Axes3D

fig = plt.figure()
ax = fig.add_subplot(111, projection='3d')

vis.draw_3d_pose(keypoints_3d, ax, kind='coco')