Real-Time Pose Detection Demo YOLOv8n-Pose is available on Edge2, VIM3 and VIM4.
Lightweight Model - The demo uses lightweight models YOLOv8n-Pose . The fastest detection speed can reach up to 30 frames.
Inherits YOLOv8 - YOLOv8n-Pose inherits the powerful object detection backbone and neck architecture of YOLOv8n.
Integrate Pose Head - YOLOv8n-Pose integrates dedicated pose estimation layers onto its head. This allows it to not only detect people (bboxes) but also simultaneously predict the spatial positions (keypoints) of their anatomical joints (e.g., shoulders, elbows, knees, ankles).
Multi-target Detection - Like YOLOv8, YOLOv8n can detect multiple targets and their pose points simultaneously.
Easy to use - We have released the Real-Time Pose Detection Demo to help you get started more easily. The only thing you need to do is replace the models with your trained models.
Doc
Edge2 - YOLOv8n-Pose OpenCV Edge2 Demo - 8 [Khadas Docs]
VIM3 - YOLOv8n-Pose VIM3 Demo Lite - 8 [Khadas Docs]
VIM3 - YOLOv8n-Pose KSNN Demo - 8 [Khadas Docs]
VIM4 - YOLOv8n-Pose OpenCV VIM4 Demo - 8 [Khadas Docs]
VIM4 - YOLOv8n-Pose KSNN Demo - 8 [Khadas Docs]