Class containing data of a detected body/person such as its bounding_box, id and its 3D position. More...
Functions | |
| int | id (self) |
| Body/person identification number. More... | |
| str | unique_object_id (self) |
| Unique id to help identify and track AI detections. More... | |
| OBJECT_TRACKING_STATE | tracking_state (self) |
| Body/person tracking state. | |
| OBJECT_ACTION_STATE | action_state (self) |
| Body/person action state. | |
| np.array[float] | position (self) |
| Body/person 3D centroid. More... | |
| np.array[float] | velocity (self) |
| Body/person 3D velocity. More... | |
| np.array[float][float] | bounding_box (self) |
| 3D bounding box of the body/person represented as eight 3D points. More... | |
| np.array[int][int] | bounding_box_2d (self) |
| 2D bounding box of the body/person represented as four 2D points starting at the top left corner and rotation clockwise. More... | |
| float | confidence (self) |
| Detection confidence value of the body/person. More... | |
| np.array[float][float] | keypoints_covariance (self) |
| NumPy array of detection covariance for each keypoint. More... | |
| np.array[float] | position_covariance (self) |
| Covariance matrix of the 3D position. More... | |
| Mat | mask (self) |
| 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... | |
| np.array[float] | dimensions (self) |
| 3D body/person dimensions: width, height, length. More... | |
| np.array[float][float] | keypoint (self) |
| Set of useful points representing the human body in 3D. More... | |
| np.array[int][int] | keypoint_2d (self) |
| Set of useful points representing the human body in 2D. More... | |
| np.array[float][float] | head_bounding_box (self) |
| 3D bounding box of the head of the body/person represented as eight 3D points. More... | |
| np.array[int][int] | head_bounding_box_2d (self) |
| 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... | |
| np.array[float] | head_position (self) |
| 3D centroid of the head of the body/person. More... | |
| np.array[float] | keypoint_confidence (self) |
| NumPy array of detection confidences for each keypoint. More... | |
| np.array[float][float] | local_position_per_joint (self) |
| NumPy array of local position (position of the child keypoint with respect to its parent expressed in its parent coordinate frame) for each keypoint. More... | |
| np.array[float][float] | local_orientation_per_joint (self) |
| NumPy array of local orientation for each keypoint. More... | |
| np.array[float] | global_root_orientation (self) |
| Global root orientation of the skeleton (NumPy array). More... | |
Class containing data of a detected body/person such as its bounding_box, id and its 3D position.
| int id | ( | self | ) |
Body/person identification number.
It is used as a reference when tracking the body through the frames.
| str unique_object_id | ( | self | ) |
Unique id to help identify and track AI detections.
It can be either generated externally, or by using generate_unique_id() or left empty.
| np.array[float] position | ( | self | ) |
Body/person 3D centroid.
| np.array[float] velocity | ( | self | ) |
Body/person 3D velocity.
sl.InitParameters.coordinate_units / s and expressed in sl.RuntimeParameters.measure3D_reference_frame. | np.array[float][float] bounding_box | ( | self | ) |
3D bounding box of the body/person represented as eight 3D points.
| np.array[int][int] bounding_box_2d | ( | self | ) |
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. | float confidence | ( | self | ) |
Detection confidence value of the body/person.
From 0 to 100, a low value means the body might not be localized perfectly.
| np.array[float][float] keypoints_covariance | ( | self | ) |
NumPy array of detection covariance for each keypoint.
| np.array[float] position_covariance | ( | self | ) |
Covariance matrix of the 3D position.
position_covariance[i] | Mat mask | ( | self | ) |
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).
mask.is_init() == False). | np.array[float] dimensions | ( | self | ) |
3D body/person dimensions: width, height, length.
| np.array[float][float] keypoint | ( | self | ) |
Set of useful points representing the human body in 3D.
| np.array[int][int] keypoint_2d | ( | self | ) |
Set of useful points representing the human body in 2D.
[0, 0] is the top left corner. | np.array[float][float] head_bounding_box | ( | self | ) |
3D bounding box of the head of the body/person represented as eight 3D points.
| np.array[int][int] head_bounding_box_2d | ( | self | ) |
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. | np.array[float] head_position | ( | self | ) |
3D centroid of the head of the body/person.
| np.array[float] keypoint_confidence | ( | self | ) |
NumPy array of detection confidences for each keypoint.
| np.array[float][float] local_position_per_joint | ( | self | ) |
NumPy array of local position (position of the child keypoint with respect to its parent expressed in its parent coordinate frame) for each keypoint.
| np.array[float][float] local_orientation_per_joint | ( | self | ) |
NumPy array of local orientation for each keypoint.
| np.array[float] global_root_orientation | ( | self | ) |
Global root orientation of the skeleton (NumPy array).
The orientation is also represented by a quaternion.