Structure containing data of a detected body/person such as its bounding_box, id and its 3D position. More...
Data Fields | |
int | id |
Body/person identification number. More... | |
unsigned char | unique_object_id [37] |
Unique id to help identify and track AI detections. More... | |
enum SL_OBJECT_TRACKING_STATE | tracking_state |
Body/person tracking state. | |
enum SL_OBJECT_ACTION_STATE | action_state |
Body/person action state. | |
struct SL_Vector3 | position |
Body/person 3D centroid. More... | |
struct SL_Vector3 | velocity |
Body/person 3D velocity. More... | |
float | position_covariance [6] |
Covariance matrix of the 3D position. More... | |
float | confidence |
Detection confidence value of the body/person. More... | |
int * | mask |
Mask defining which pixels which belong to the body/person (in bounding_box_2d and set to 255) and those of the background (set to 0). More... | |
struct SL_Vector2 | bounding_box_2d [4] |
2D bounding box of the body/person represented as four 2D points starting at the top left corner and rotation clockwise. More... | |
struct SL_Vector3 | head_position |
3D centroid of the head of the body/person. More... | |
struct SL_Vector3 | dimensions |
3D body/person dimensions: width, height, length. More... | |
struct SL_Vector3 | bounding_box [8] |
3D bounding box of the body/person represented as eight 3D points. More... | |
struct SL_Vector3 | head_bounding_box [8] |
3D bounding box of the head of the body/person represented as eight 3D points. More... | |
struct SL_Vector2 | head_bounding_box_2d [4] |
2D bounding box of the head of the body/person represented as four 2D points starting at the top left corner and rotation clockwise. More... | |
struct SL_Vector2 | keypoint_2d [38] |
Set of useful points representing the human body in 2D. More... | |
struct SL_Vector3 | keypoint [38] |
Set of useful points representing the human body in 3D. More... | |
float | keypoint_confidence [38] |
Array of detection confidences for each keypoint. More... | |
float | keypoint_covariances [38][6] |
Array of detection covariance for each keypoint. More... | |
struct SL_Vector3 | local_position_per_joint [38] |
Array of local position (position of the child keypoint with respect to its parent expressed in its parent coordinate frame) for each keypoint. More... | |
struct SL_Quaternion | local_orientation_per_joint [38] |
Array of local orientation for each keypoint. More... | |
struct SL_Quaternion | global_root_orientation |
Global root orientation of the skeleton. More... | |
Structure containing data of a detected body/person such as its bounding_box, id and its 3D position.
int SL_BodyData::id |
Body/person identification number.
It is used as a reference when tracking the body through the frames.
unsigned char SL_BodyData::unique_object_id[37] |
Unique id to help identify and track AI detections.
It can be either generated externally, or by using sl_generate_unique_id() or left empty.
struct SL_Vector3 SL_BodyData::position |
Body/person 3D centroid.
struct SL_Vector3 SL_BodyData::velocity |
Body/person 3D velocity.
SL_InitParameters.coordinate_unit / s
and expressed in SL_RuntimeParameters.reference_frame. float SL_BodyData::position_covariance[6] |
Covariance matrix of the 3D position.
position_covariance[i]
float SL_BodyData::confidence |
Detection confidence value of the body/person.
From 0 to 100, a low value means the body might not be localized perfectly.
int* SL_BodyData::mask |
Mask defining which pixels which belong to the body/person (in bounding_box_2d and set to 255) and those of the background (set to 0).
struct SL_Vector2 SL_BodyData::bounding_box_2d[4] |
2D bounding box of the body/person represented as four 2D points starting at the top left corner and rotation clockwise.
[0, 0]
is the top left corner. struct SL_Vector3 SL_BodyData::head_position |
3D centroid of the head of the body/person.
struct SL_Vector3 SL_BodyData::dimensions |
3D body/person dimensions: width, height, length.
struct SL_Vector3 SL_BodyData::bounding_box[8] |
3D bounding box of the body/person represented as eight 3D points.
struct SL_Vector3 SL_BodyData::head_bounding_box[8] |
3D bounding box of the head of the body/person represented as eight 3D points.
struct SL_Vector2 SL_BodyData::head_bounding_box_2d[4] |
2D bounding box of the head of the body/person represented as four 2D points starting at the top left corner and rotation clockwise.
[0, 0]
is the top left corner. struct SL_Vector2 SL_BodyData::keypoint_2d[38] |
Set of useful points representing the human body in 2D.
[0, 0]
is the top left corner. struct SL_Vector3 SL_BodyData::keypoint[38] |
Set of useful points representing the human body in 3D.
float SL_BodyData::keypoint_confidence[38] |
Array of detection confidences for each keypoint.
float SL_BodyData::keypoint_covariances[38][6] |
Array of detection covariance for each keypoint.
struct SL_Vector3 SL_BodyData::local_position_per_joint[38] |
Array of local position (position of the child keypoint with respect to its parent expressed in its parent coordinate frame) for each keypoint.
struct SL_Quaternion SL_BodyData::local_orientation_per_joint[38] |
Array of local orientation for each keypoint.
SL_Quaternion q = SL_Quaternion(qx, qy, qz, qw);
) struct SL_Quaternion SL_BodyData::global_root_orientation |
Global root orientation of the skeleton.
The orientation is also represented by a quaternion with the same format as local_orientation_per_joint.