Pose Detection - 1.1 English

Vitis AI Library User Guide (UG1354)

Document ID
Release Date
1.1 English

This library is used to detect posture of the human body. This library includes a neural network which can mark 14 key points of the human body (you can use our SSD detection library). The input is a picture that is detected by the pedestrian detection neural network. The output is a structure containing coordinates of each point .

The following image shows the result of pose detection.

Figure 1. Pose Detection Example

The following table shows the pose detection model supported by the AI Library.

Table 1. The pose detection model list
No Model Name Framework
1 sp_net Caffe
Note: If the input image is arbitrary and the user does not know the exact location of the person, we must perform the SSD detection first. See the test_jpeg_posedetect_with_ssd.cpp file. If the input picture is the picture of the person who has been cut out, you can only perform pose detection. See the test_jpeg_posedetect.cpp file.