Pose estimation

Detects human keypoints (17 COCO joints) in addition to bounding boxes. The pipeline draws skeleton overlays on the output video automatically.

models:
  - name: "yolo-pose"
    type: "pose"
    architecture: "yolo_pose11"
    onnx_file: /path/to/yolo11n-pose.onnx
    label_file: /path/to/labels.txt

Fields

Field	Type	Required	Default	Description
architecture	string	Yes	—	Pose architecture (see supported architectures)
active_classes	list of int	No	all classes	Only detect these class IDs

Plus the common model fields (name, onnx_file, label_file, batch_size, precision).

Supported architectures

Architecture	Description
yolo_pose8	YOLOv8 Pose (n/s/m/l/x variants)
yolo_pose11	YOLO11 Pose (n/s/m/l/x variants)
yolo_pose26	YOLO26 Pose (n/s/m/l/x variants)