Contains batched data of a detected object More...
Attributes | |
| int | numData = 0 |
| How many data were stored. Use this to iterate through the top of position/velocity/bounding_box/...; objects with indexes greater than numData are empty. More... | |
| int | id = 0 |
| The trajectory id More... | |
| OBJECT_CLASS | label = OBJECT_CLASS.LAST |
| Object Category. Identity the object type More... | |
| OBJECT_SUBCLASS | sublabel = OBJECT_SUBCLASS.LAST |
| Object subclass More... | |
| OBJECT_TRACKING_STATE | trackingState = OBJECT_TRACKING_STATE.TERMINATE |
| Defines the object tracking state More... | |
| Vector3[] | positions = new Vector3[(int)Constant.MAX_BATCH_SIZE] |
| A sample of 3d position More... | |
| float[,] | positionCovariances = new float[(int)Constant.MAX_BATCH_SIZE, 6] |
| a sample of the associated position covariance More... | |
| Vector3[] | velocities = new Vector3[(int)Constant.MAX_BATCH_SIZE] |
| A sample of 3d velocity More... | |
| ulong[] | timestamps = new ulong[(int)Constant.MAX_BATCH_SIZE] |
| The associated position timestamp More... | |
| Vector3[,] | boundingBoxes = new Vector3[(int)Constant.MAX_BATCH_SIZE, 8] |
| A sample of 3d bounding boxes More... | |
| Vector2[,] | boundingBoxes2D = new Vector2[(int)Constant.MAX_BATCH_SIZE, 4] |
| 2D bounding box of the person represented as four 2D points starting at the top left corner and rotation clockwise. Expressed in pixels on the original image resolution, [0, 0] is the top left corner. A ---— B | Object | D ---— C More... | |
| float[] | confidences = new float[(int)Constant.MAX_BATCH_SIZE] |
| a sample of object detection confidence More... | |
| OBJECT_ACTION_STATE[] | actionStates = new OBJECT_ACTION_STATE[(int)Constant.MAX_BATCH_SIZE] |
| a sample of the object action state More... | |
| Vector2[,] | keypoints2D = new Vector2[(int)Constant.MAX_BATCH_SIZE, 18] |
| a sample of 2d person keypoints. Not available with DETECTION_MODEL::MULTI_CLASS_BOX. in some cases, eg. body partially out of the image or missing depth data, some keypoint can not be detected, they will have non finite values. More... | |
| Vector3[,] | keypoints = new Vector3[(int)Constant.MAX_BATCH_SIZE, 18] |
| a sample of 3d person keypoints Not available with DETECTION_MODEL::MULTI_CLASS_BOX. in some cases, eg. body partially out of the image or missing depth data, some keypoint can not be detected, they will have non finite values. More... | |
| Vector2[,] | headBoundingBoxes2D = new Vector2[(int)Constant.MAX_BATCH_SIZE, 8] |
| bounds the head with four 2D points. Expressed in pixels on the original image resolution. Not available with DETECTION_MODEL.MULTI_CLASS_BOX. More... | |
| Vector3[,] | headBoundingBoxes = new Vector3[(int)Constant.MAX_BATCH_SIZE, 8] |
| bounds the head with eight 3D points. Defined in sl.InitParameters.UNIT, expressed in RuntimeParameters.measure3DReferenceFrame. Not available with DETECTION_MODEL.MULTI_CLASS_BOX. More... | |
| Vector3[] | headPositions = new Vector3[(int)Constant.MAX_BATCH_SIZE] |
| 3D head centroid. Defined in sl.InitParameters.UNIT, expressed in RuntimeParameters.measure3DReferenceFrame. Not available with DETECTION_MODEL.MULTI_CLASS_BOX. More... | |
| float[,] | keypointConfidences = new float[(int)Constant.MAX_BATCH_SIZE, 18] |
| Per keypoint detection confidence, can not be lower than the ObjectDetectionRuntimeParameters.detectionConfidenceThreshold. Not available with DETECTION_MODEL.MULTI_CLASS_BOX. in some cases, eg. body partially out of the image or missing depth data, some keypoint can not be detected, they will have non finite values. More... | |
Contains batched data of a detected object
| int numData = 0 |
How many data were stored. Use this to iterate through the top of position/velocity/bounding_box/...; objects with indexes greater than numData are empty.
| int id = 0 |
The trajectory id
| OBJECT_CLASS label = OBJECT_CLASS.LAST |
Object Category. Identity the object type
| OBJECT_SUBCLASS sublabel = OBJECT_SUBCLASS.LAST |
Object subclass
| OBJECT_TRACKING_STATE trackingState = OBJECT_TRACKING_STATE.TERMINATE |
Defines the object tracking state
| Vector3 [] positions = new Vector3[(int)Constant.MAX_BATCH_SIZE] |
A sample of 3d position
| float [,] positionCovariances = new float[(int)Constant.MAX_BATCH_SIZE, 6] |
a sample of the associated position covariance
| Vector3 [] velocities = new Vector3[(int)Constant.MAX_BATCH_SIZE] |
A sample of 3d velocity
| ulong [] timestamps = new ulong[(int)Constant.MAX_BATCH_SIZE] |
The associated position timestamp
| Vector3 [,] boundingBoxes = new Vector3[(int)Constant.MAX_BATCH_SIZE, 8] |
A sample of 3d bounding boxes
| Vector2 [,] boundingBoxes2D = new Vector2[(int)Constant.MAX_BATCH_SIZE, 4] |
2D bounding box of the person represented as four 2D points starting at the top left corner and rotation clockwise. Expressed in pixels on the original image resolution, [0, 0] is the top left corner. A ---— B | Object | D ---— C
| float [] confidences = new float[(int)Constant.MAX_BATCH_SIZE] |
a sample of object detection confidence
| OBJECT_ACTION_STATE [] actionStates = new OBJECT_ACTION_STATE[(int)Constant.MAX_BATCH_SIZE] |
a sample of the object action state
| Vector2 [,] keypoints2D = new Vector2[(int)Constant.MAX_BATCH_SIZE, 18] |
a sample of 2d person keypoints. Not available with DETECTION_MODEL::MULTI_CLASS_BOX. in some cases, eg. body partially out of the image or missing depth data, some keypoint can not be detected, they will have non finite values.
| Vector3 [,] keypoints = new Vector3[(int)Constant.MAX_BATCH_SIZE, 18] |
a sample of 3d person keypoints Not available with DETECTION_MODEL::MULTI_CLASS_BOX. in some cases, eg. body partially out of the image or missing depth data, some keypoint can not be detected, they will have non finite values.
| Vector2 [,] headBoundingBoxes2D = new Vector2[(int)Constant.MAX_BATCH_SIZE, 8] |
bounds the head with four 2D points. Expressed in pixels on the original image resolution. Not available with DETECTION_MODEL.MULTI_CLASS_BOX.
| Vector3 [,] headBoundingBoxes = new Vector3[(int)Constant.MAX_BATCH_SIZE, 8] |
bounds the head with eight 3D points. Defined in sl.InitParameters.UNIT, expressed in RuntimeParameters.measure3DReferenceFrame. Not available with DETECTION_MODEL.MULTI_CLASS_BOX.
| Vector3 [] headPositions = new Vector3[(int)Constant.MAX_BATCH_SIZE] |
3D head centroid. Defined in sl.InitParameters.UNIT, expressed in RuntimeParameters.measure3DReferenceFrame. Not available with DETECTION_MODEL.MULTI_CLASS_BOX.
| float [,] keypointConfidences = new float[(int)Constant.MAX_BATCH_SIZE, 18] |
Per keypoint detection confidence, can not be lower than the ObjectDetectionRuntimeParameters.detectionConfidenceThreshold. Not available with DETECTION_MODEL.MULTI_CLASS_BOX. in some cases, eg. body partially out of the image or missing depth data, some keypoint can not be detected, they will have non finite values.
