Demo 2: MultiTask Segmentation + Car Detection and Pose Detection - 2.0 English

Vitis AI Library User Guide (UG1354)
Document ID
UG1354
Release Date
2022-01-20
Version
2.0 English

Target Application

  • ADAS/AD
  • Smartcity

AI Model, Performance, and Power

FPN
960x540, 1ch, 30fps
Openpose
960x540, 1ch, 30fps
20W @ ZU9EG

Building and Running the Demo

Build the demo in the host and copy the program to the target board.

cd Vitis-AI/demo/Vitis-AI-Library/apps/seg_and_pose_detect
bash -x build.sh
scp seg_and_pose_detect_x seg_and_pose_detect_drm root@IP_OF_BOARD:~/

To use OpenCV display, run the following command:

#./seg_and_pose_detect_x seg_960_540.avi pose_960_540.avi -t 4 -t 4 >/dev/null 2>&1
If you want to use DRM display, connect to the board using SSH and run the following command:
#./seg_and_pose_detect_drm seg_960_540.avi pose_960_540.avi -t 4 -t 4 >/dev/null 2>&1
Note:
  1. The video files are in the vitis_ai_library_r2.0.0_video.tar.gz. Download the package from here.
  2. Due to limitations of the Docker environment, the MultiTask demos cannot run in the DRM mode on Cloud devices.
Figure 1. Segmentation and Pose Detection Demo Picture