Body Tracking Overview

The body tracking module focuses on a person’s bones detection and tracking. A detected bone is represented by its two endpoints also called keypoints. The ZED camera can provide 2D and 3D information on each detected keypoints. Furthermore, it produces local rotation between neighbor bones.

How It Works

The overall process is very similar to the ZED SDK Object detection module. They share some information in outputs like the 3D position and 3D velocity of each person. The body tracking module also uses a neural network for keypoints detection and then calls depth and positional tracking of the ZED SDK module to get the final 3D position of each keypoint. The ZED SDK supports multiple body formats :

Body 18

Body 34

Body 38

The BODY_18 body format contains 18 keypoints following the COCO18 skeleton representation

Each keypoint is indexed by an integer from 0 to 17 :

keypoint index	keypoint name	keypoint index	keypoint name
0	NOSE	9	RIGHT_KNEE
1	NECK	10	RIGHT_ANKLE
2	RIGHT_SHOULDER	11	LEFT_HIP
3	RIGHT_ELBOW	12	LEFT_KNEE
4	RIGHT_WRIST	13	LEFT_ANKLE
5	LEFT_SHOULDER	14	RIGHT_EYE
6	LEFT_ELBOW	15	LEFT_EYE
7	LEFT_WRIST	16	RIGHT_EAR
8	RIGHT_HIP	17	LEFT_EAR

The ZED SDK can output 3 levels of information: raw 2D/3D body detection, 3D body tracking and 3D body fitting.

2D/3D Body detection

The ZED SDK first uses the ZED camera image to infer all 2D bones and keypoints using neural networks. Then the SDK depth module and positional tracking module are used together to extract the correct 3D position of each bone and keypoint.

3D body tracking

If tracking is enabled, the ZED SDK will assign an identity to each detected body over time. At the same time, by filtering the raw body detection, it will output a more stable 3D body estimation.

3D body fitting

Moreover, a user can enable fitting to unlock even more information about each identity. The fitting process takes the history of each tracked person to deduce all missing keypoints thanks to the human kinematic’s constraint used by the body tracking module. It is also able to extract local rotation between a pair of neighbor bones by solving the inverse kinematic problem. These data will be compatible with some known software for avataring for example. Here is an example where BODY_FORMAT::BODY_34 were used to animate an avatar in Unreal.

Detection Outputs

Each detected person is stored as a structure in the ZED SDK called sl.BodyData.

Body Data	Description	Output
ID	Fixed ID for identifying an object over time.	`Integer`
Unique Object ID	Unique id to help identify and track AI detections.	`String`
Tracking state	Defines if an object is currently tracked or lost.	`Ok`, `Off`, `Searching`, `Terminate`
Action state	Defines if an object is currently idle or moving.	`Idle`, `Moving`
Position	Provides the 3D position of the object according to the camera as a 3D vector (x,y,z).	`[x, y, z]`
Velocity	Provides the velocity of the object in space as a 3D vector (x,y,z).	`[vₓ, vᵧ, v_z]`
Position covariance	Covariance matrix of the 3D position.	array of 6 values
2D bounding box	Defines the box surrounding the object in the image represented as four 2D points.	Four pixel coordinates
Mask	Provides the pixels which really belong to the object and those of the background.	Binary mask
Detection confidence	A lower confidence means the object might not be localized perfectly or that its label is uncertain.	`0 - 100`
3D bounding box	Defines the box surrounding the object in space represented as eight 3D points.	Eight 3D coordinates
Dimensions	Provides the width, height and length of the object.	`[width, height, length]`
2D keypoint	A set of useful points representing the human body, expressed in 2D.	a vector of `[x, y]`
Keypoint	A set of useful points representing the human body, expressed in 3D.	a vector of `[x, y, z]`
2D head bounding box	Bounds the head with four 2D points.	Four pixel coordinates
3D head bounding box	Bounds the head with eight 3D points.	Eight 3D coordinates
Head position	3D head centroid	`[x, y, z]`
Keypoint confidence	Per keypoint detection confidence	a vector of float
Keypoint covariance	Per keypoint covariance	a vector of 6 values array
Local position per joint	Local position of each keypoint	a vector of `[x, y, z]`
Local orientation per joint	Local rotation of each keypoint	a vector of `[x, y, z, w]`
Global root orientation	Global root orientation of the Body	`[x, y, z, w]`

For more information on Body Tracking, see the Using the API page.