Overview

This node parses the output of "Pose Detection" model to extract the human pose keypoints and line segments.

Requires Model Inference Node (Pose Detection) prior to it in order to function properly.

Inputs & Outputs

Inputs : 1, Media Format : Raw Video
Outputs : 1, Media Format: Raw Video
Output Metadata: parsed pose keypoints/segments under nodes.<node_id> and on matching objects.

Properties

Property	Description	Type	Default	Required
`draw_poses`	If enabled, human pose points and body joints connections will be drawn on video.	`bool`	`true`	No
`draw_labels`	Display body joints labels on video?	`bool`	`false`	No
`accuracy`	Higher accuracy allows detecting smaller bodies, typically at a bigger distance from camera, but will also increase the processing time. Options: Low (`low`); Medium (`medium`); High (`high`).	`enum`	`low`	Yes

Output Metadata

The fields below are declared by this node's metadata schema; the JSON values are representative examples.

Path	Type	Description
`nodes.<node_id>.poses.<pose_id>.rect`	`array`	Array of four numbers containing left, top, width, and height.
`nodes.<node_id>.poses.<pose_id>.keypoints.<keypoint_name>.x`	`integer`	Horizontal pixel coordinate of this keypoint.
`nodes.<node_id>.poses.<pose_id>.keypoints.<keypoint_name>.y`	`integer`	Vertical pixel coordinate of this keypoint.
`nodes.<node_id>.poses.<pose_id>.segments`	`array`	Array of keypoint-name pairs that form the pose skeleton.
`nodes.<node_id>.poses_count`	`integer`	Total number of poses in the view right now
`nodes.<node_id>.type`	`string`	Identifies the node type that produced this metadata.

JSON example

{
    "nodes":{
        "annotate_pose1":{
            "type":"annotate_pose",
            "poses_count":<int>,
            "poses":{
                "<pose_id>":{
                    "keypoints":{
                        "l_ank":{"x":<int>, "y":<int>},
                        "l_ear":{"x":<int>, "y":<int>},
                        "l_elb":{"x":<int>, "y":<int>},
                        "l_eye":{"x":<int>, "y":<int>},
                        "l_hip":{"x":<int>, "y":<int>},
                        "l_knee":{"x":<int>, "y":<int>},
                        "l_sho":{"x":<int>, "y":<int>},
                        "l_wri":{"x":<int>, "y":<int>},
                        "neck":{"x":<int>, "y":<int>},
                        "nose":{"x":<int>, "y":<int>},
                        "r_ank":{"x":<int>, "y":<int>},
                        "r_ear":{"x":<int>, "y":<int>},
                        "r_elb":{"x":<int>, "y":<int>},
                        "r_eye":{"x":<int>, "y":<int>},
                        "r_hip":{"x":<int>, "y":<int>},
                        "r_knee":{"x":<int>, "y":<int>},
                        "r_sho":{"x":<int>, "y":<int>},
                        "r_wri":{"x":<int>, "y":<int>}
                    },
                    "rect":[<int>, <int>, <int>, <int>],
                    "segments":[
                        ["neck", "r_sho"],
                        ["neck", "l_sho"],
                        ["r_sho", "r_elb"],
                        ["r_elb", "r_wri"],
                        ["l_sho", "l_elb"],
                        ["l_elb", "l_wri"],
                        ["neck", "r_hip"],
                        ["r_hip", "r_knee"],
                        ["r_knee", "r_ank"],
                        ["neck", "l_hip"],
                        ["l_hip", "l_knee"],
                        ["l_knee", "l_ank"],
                        ["neck", "nose"],
                        ["nose", "r_eye"],
                        ["r_eye", "r_ear"],
                        ["nose", "l_eye"],
                        ["l_eye", "l_ear"]
                    ]
                }
            }
        }
    }
}

Additional details

The keypoint IDs use abbreviations as follows:

l_ank: left ankle
l_ear: left ear
l_elb: left elbow
l_eye: left eye
l_hip: left hip
l_knee: left knee
l_sho: left shoulder
l_wri: left wrist
neck: neck
nose: nose
r_ank: right ankle
r_ear: right ear
r_elb: right elbow
r_eye: right eye
r_hip: right hip
r_knee: right knee
r_sho: right shoulder
r_wri: right wrist

Object labels and attributes

Object labels/classes added: Each detected pose is added as a person object with class 0.
Object attribute labels/classes added: None.