Movenet Detection - 3.5 English

Vitis AI Library User Guide (UG1354)

Document ID
Release Date
3.5 English
The library is used to detect posture of the human body. It is represented by a array of 17 joint points. Joint points are arranged in the following order.

0: 'nose', 1: 'left_eye', 2: 'right_eye', 3: 'left_ear', 4: 'right_ear',
5: 'left_shoulder', 6: 'right_shoulder', 7: 'left_elbow', 8: 'right_elbow',
9: 'left_wrist', 10 : 'right_wrist', 11: 'left_hip', 12: 'right_hip', 
13: 'left_knee', 14: 'right_knee', 15: 'left_ankle', 16: 'right_ankle'

This network can only detect for one person and the input of this network is 192x192.

Note: Use a square picture for input. To detect pictures with other size ratios, use a network with the same input size ratio.

The following table lists the Movenet detection models supported by the Vitis AI Library.

Table 1. Movenet Detection Models
No Model Name Framework
1 movenet_ntd_pt PyTorch